Construction site task scheduling method and system based on multiple agents

Abstract

The invention relates to the technical field of task scheduling, in particular to a multi-agent-based construction site task scheduling method and system, and the method comprises the following steps: obtaining task starting and resource in-place time, matching task demands, setting priorities, judging task conflicts, generating a section structure table, extracting completion data, activating tasks, and generating a trigger chain. And constructing path fragments to establish a task continuous relationship, and judging section adjacent reconstruction scheduling to generate a parallel control result. According to the method, task screening is guided through cross judgment of the task starting time and the resource in-place state, priority information is dynamically given in combination with operation type requirements, intelligent recognition of task triggering conditions is achieved, and the mutual exclusion conflict relation is marked in time through overlapping comparison of regional task time intervals; the scheduling behavior is promoted to have the pre-recognition capability for resource conflicts, and the scheduling continuity and resource consistency in multi-agent task cooperative execution are enhanced.

Description

Technical Field

[0001] This invention relates to the field of task scheduling technology, and in particular to a construction site task scheduling method and system based on multi-agent systems. Background Technology

[0002] Task scheduling technology primarily involves the optimal allocation and rational arrangement of limited resources over time. Its core aspects include task prioritization, resource allocation strategies, time dependency management, and multi-objective coordination and control. Task scheduling technology is widely applied in manufacturing management, transportation dispatch, project construction, and information systems. By establishing task queues, defining dependencies, and optimizing task execution order, it maximizes resource utilization and minimizes time costs. Task scheduling in construction management is a crucial branch of this field, involving personnel arrangement, equipment allocation, material delivery, and work schedule planning. It is characterized by high real-time performance, strong collaboration, and complex process dependencies. Traditional construction site task scheduling methods involve manually creating construction schedules and using basic project management tools to arrange various tasks on the construction site. The key technical issue it addresses is how to rationally coordinate task order, resource allocation, and schedule continuity in an environment of multiple trades, asynchronous operations, and overlapping construction locations. Traditional methods rely on construction drawings and project contract requirements, combined with experience to determine the start and end times of each process. Worker, machinery, and material usage time are allocated according to a calendar using spreadsheet tools or general scheduling software. The scheduling sequence is manually adjusted with reference to information such as weather forecasts and material arrival records in order to complete the construction organization tasks at each stage.

[0003] Existing technologies rely on manual setting of schedule plans and general scheduling tools in task scheduling, lacking a dynamic matching mechanism based on task attributes and resource status. When multiple trades are working together, it is impossible to perceive the spatiotemporal conflicts between tasks in real time, resulting in static lag problems in the scheduling process. Manual adjustment methods are not timely in response to sudden resource changes and task delays. Furthermore, the task execution order is determined by subjective experience and lacks a mechanism based on task status feedback. In scenarios with complex process dependencies and frequent resource flows on construction sites, it is easy to cause phenomena such as work rhythm disconnection and repeated use of resources, resulting in decreased scheduling efficiency and deviations in progress control. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a multi-agent-based construction site task scheduling method and system.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a multi-agent-based construction site task scheduling method, comprising the following steps: S1: Obtain the start time range, resource arrival time and unit operation efficiency record of the tasks to be executed by the intelligent agents in the construction area, make time period coverage judgment on the task start time and resource arrival time, match the unit operation efficiency record and task type requirements, and form a multi-agent task execution priority group. S2: Based on the multi-agent task execution priority group, call the estimated execution time of the job and the job space number, and compare the overlapping intervals of the start time and end time of the tasks in the same area to determine whether there are concurrent or cross conflicts in the same scheduling cycle, and generate a site scheduling behavior segment structure table. S3: Call the completed task number in the construction site scheduling behavior segment structure table, extract the corresponding work completion flag, operation content quantity and location record time, set the approved task as the active task, and generate a scheduling task trigger state chain. S4: Based on the task number that can be started in the scheduling task triggering state chain, extract the construction area label, operation type label and rhythm control identifier, merge the three labels to construct a path segment, and then compare the number of consecutive items in the path segment to generate a task content logical continuity graph.

[0006] As a further aspect of the present invention, the multi-agent task execution priority group includes a task start time interval, a resource availability determination result, and a priority corresponding to the task type; the construction site scheduling behavior segment structure table includes a mutual exclusion identifier, a task number mapping relationship, and a work space segment number; the scheduling task trigger state chain includes an activated task number, a next-order task start marker, and a task state mapping chain; and the task content logical continuity graph includes a path segment sequence, a content continuity relationship between tasks, and a work rhythm control identifier.

[0007] As a further aspect of the present invention, the step of obtaining the multi-agent task execution priority group specifically includes: S111: Obtain the start time range, resource arrival time and unit work efficiency record of the tasks to be executed by the intelligent agent in the construction area, and make interval coverage judgment between the resource arrival time and the task start time range of each task. Filter out the tasks whose task start time range is completely covered by the resource arrival time and generate the resource coverage task interval. S112: Call the resource coverage task range, extract the corresponding task type requirements and construction site task records, compare the consistency between the task identifier and the task type field, filter the tasks whose task types match the construction site task records, and generate a set of matching task types. S113: Based on the matching task type task set, extract the job types corresponding to multiple tasks, divide the tasks into groups according to job types, extract the resource input, unit job efficiency, required task duration and job obstacle factor of the tasks in the group, calculate the job execution priority of the tasks in each job type group, sort the tasks in the job type in descending order of value, and obtain the multi-agent task execution priority group.

[0008] As a further aspect of the present invention, the steps for obtaining the site scheduling behavior segment structure table are as follows: S211: Based on the multi-agent task execution priority group, call the estimated execution time of the job and the job space number, filter the task combinations in the same area, obtain the start time and end time of the task, compare the time overlap interval, determine whether cross-conflict occurs in the same scheduling cycle, and obtain the cross-conflict task combinations. S212: Based on the cross-conflicting task combination, identify the task combination that generates cross-conflict within the same scheduling cycle, extract the corresponding job space number, classify and register it according to the segment range, and obtain a list of conflicting job space segment numbers. S213: Call the list of conflicting work space segment numbers, compare the work space range and execution time between tasks in the conflict combination, extract the spatial overlap length and task priority value, and calculate the mutual exclusion conflict identifier value between task pairs in combination with the spatial intersection density, set the mutual exclusion identifier, and establish a site scheduling behavior segment structure table.

[0009] As a further aspect of the present invention, the step of obtaining the scheduling task trigger state chain specifically includes: S311: Call the completed task number in the construction site scheduling behavior segment structure table, extract the corresponding work completion flag, operation content quantity and location record time, match the three types of data with the numbering and reconstruct them by unifying the numbering dimension to form a work status data combination item; S312: Based on the multiple number contents in the job status data combination item, determine the job completion flag as the identifier value, perform structural offset processing on the number of operation contents and the task number group value, calculate the single task combination response quantity, record the task number with a single task combination response quantity greater than zero, and obtain the activated task number item. S313: Call the activated task number item, retrieve the corresponding next task number, assign a start identifier field to the next task, establish a mapping path relationship between the activated task number and the next task, and generate a scheduling task trigger state chain.

[0010] As a further aspect of the present invention, the steps for obtaining the task content logical continuity graph are as follows: S411: Based on the task number that can be started in the scheduling task triggering state chain, extract the corresponding construction area label, operation type label and rhythm control identifier, establish a corresponding label item set using the task number and the three label contents, and then splice the three label contents in the order of task number to generate a path segment sequence set. S412: Call the path segment sequence set, extract the sequential position of the tag items in the sequence for continuous task path segments, perform consistency judgment between adjacent segments, identify path segment combinations with related features of tag content, obtain the tag comparison relationship in the path segment group, and generate tag consistency comparison results; S413: Based on the label consistency comparison results and the task number sequence information, determine whether the label combination features between adjacent task path segments have a continuous relationship. Construct a unidirectional connection path for task numbers with a continuous relationship, organize the task nodes according to the path structure, and generate a task content logical continuity graph.

[0011] As a further aspect of the present invention, the method further includes step S5: S5: Call the task number in the task content logical succession diagram, perform adjacency judgment on the segment number of the tasks that form a succession relationship, and enter the scheduling reconstruction of the task group that is determined to be successful. Compare the operation rhythm identifier with the real-time segment operation rhythm, verify the synchronization group and merge it into the same segment to generate the parallel control result of the construction site task. The parallel control results of the construction site tasks include synchronous operation groups within the section, consistency verification results of scheduling rhythm, and the set of scheduling reconstructed sections.

[0012] As a further aspect of the present invention, the step of obtaining the parallel control result of the construction site task specifically includes: S511: Based on the task number in the task content logical succession diagram, call each pair of task numbers that form a succession relationship and the segment number in which they are located. According to the order between the numbers, by comparing whether the segment numbers of adjacent tasks form a continuous relationship, perform a segment number adjacency judgment on the task pairs that form a succession relationship and generate adjacent task pair number groups. S512: Based on the adjacent task pair numbering group, extract the operation rhythm identifier corresponding to each group of tasks and the operation rhythm value of the real-time segment. By comparing the consistency between the task operation rhythm identifier and the real-time segment operation rhythm value, filter the task combinations with synchronized operation rhythms to obtain a list of synchronized task combinations. S513: Call the set of segment numbers and task numbers in the synchronous task combination list, merge the tasks in the same combination into the corresponding segment, identify the task number control relationship under the corresponding segment, and generate the parallel control result of the construction site tasks.

[0013] The multi-agent-based construction site task scheduling system is used to execute the aforementioned multi-agent-based construction site task scheduling method. The system includes: The task triggering module obtains the start time range, resource arrival time and unit operation efficiency record of the tasks to be executed by the intelligent agents in the construction area, judges the coverage interval of the task start time and resource arrival time, defines the tasks that match the unit operation efficiency record as triggerable tasks, sets the task execution priority, and generates a multi-agent task execution priority group. The conflict detection module calls the task start time, job space number and expected execution time in the multi-agent task execution priority group, compares the start and end times of tasks in the same area across intervals, marks the task combinations that cause cross-conflicts and their corresponding space segment numbers, and establishes a site scheduling behavior segment structure table. The status judgment module calls the work completion flag, operation content quantity and location record time of the construction site scheduling behavior segment structure table, marks the tasks that meet the conditions as active, and generates a scheduling task trigger status chain. The path construction module extracts the construction area label, operation type label and rhythm control identifier based on the startable task number in the scheduling task trigger state chain, compares the number of consecutive items in the path segment, and obtains the task content logical continuity graph. The parallel control module calls the task pair segment number in the task content logical sequence diagram, performs spatial segment adjacency judgment and compares the rhythm control mark with the real-time operation rhythm, merges rhythm-synchronized tasks into the same segment, and generates the construction site task parallel control result.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, task selection is guided by cross-judgment of task start time and resource availability status, and priority information is dynamically assigned based on job type requirements to achieve intelligent identification of task triggering conditions. By comparing the overlap of regional task time intervals, mutual exclusion and conflict relationships are marked in a timely manner, enabling scheduling behavior to have the ability to identify resource conflicts in advance. Combining task status data to reflect activation conditions enables subsequent tasks to have a real-time response mechanism. Establishing a path continuity identification relationship in the task sequence effectively supports the coherent advancement of rhythm control. By judging the adjacency and synchronicity of spatial segments, job group fusion is achieved, promoting the accurate matching of job rhythm consistency, ensuring the synchronous achievement of logical relationships and spatial allocation between tasks, and enhancing the scheduling continuity and resource consistency in multi-agent task collaborative execution. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the workflow of the present invention; Figure 2This is a flowchart illustrating the process of obtaining the multi-agent task execution priority group in this invention. Figure 3 This is a flowchart illustrating the process of obtaining the site scheduling behavior segment structure table in this invention. Figure 4 This is a flowchart illustrating the process of obtaining the scheduling task trigger state chain in this invention. Figure 5 This is a flowchart illustrating the process of obtaining the logical sequence diagram of task content in this invention. Figure 6 This is a flowchart illustrating the process of obtaining the parallel control results of construction site tasks in this invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] Please see Figure 1 This invention provides a technical solution: a multi-agent-based construction site task scheduling method, comprising the following steps: S1: Obtain the start time range, resource arrival time and unit operation efficiency record of the tasks to be executed by the intelligent agents in the construction area. Make time period coverage judgment on the task start time and resource arrival time, match the unit operation efficiency record and task type requirements, set the tasks that meet the conditions as triggerable tasks, set the execution priority of triggerable tasks according to the operation type, and form a multi-agent task execution priority group. S2: Based on the multi-agent task execution priority group, the estimated execution time of the job and the job space number are called. By comparing the overlapping intervals of the start time and end time of the tasks in the same area, it is determined whether there are concurrent or cross-conflicts in the same scheduling cycle. Mutual exclusion flags are set for the task combinations with cross-conflicts, the task number and the corresponding segment number of the job space are registered, and the site scheduling behavior segment structure table is generated. S3: Call the completed task number in the construction site scheduling behavior segment structure table, extract the corresponding work completion flag, operation content quantity and location record time, perform status judgment and value comparison on the three data, set the task that passes the judgment as the active task, mark the corresponding next task as startable, and generate the scheduling task trigger state chain. S4: Based on the task number that can be started in the scheduling task triggering status chain, extract the construction area label, operation type label and rhythm control identifier, merge the three labels to construct a path segment, then compare the number of consecutive items in the path segment, establish a content continuity identifier relationship between tasks, and generate a task content logical continuity graph. S5: Call the task number in the task content logic continuation graph, perform adjacency judgment on the segment number of the tasks that form a continuation relationship, and enter the scheduling reconstruction of the task group that is determined to be true. Compare the operation rhythm identifier with the real-time segment operation rhythm, and merge the synchronous group into the same segment after verification to generate the parallel control result of the construction site task. The multi-agent task execution priority group includes the task start time interval, resource availability judgment result, and priority corresponding to task type. The site scheduling behavior segment structure table includes mutual exclusion identifiers, task number mapping relationship, and work space segment number. The scheduling task trigger state chain includes the activated task number, the next order task start mark, and the task state mapping chain. The task content logical continuity graph includes the path segment sequence, the content continuity relationship between tasks, and the work rhythm control identifier. The site task parallel control result includes the synchronous work group within the segment, the scheduling rhythm consistency verification result, and the scheduling reconstructed segment set.

[0019] Please see Figure 2 The specific steps for obtaining the multi-agent task execution priority group are as follows: S111: Obtain the start time range, resource arrival time and unit work efficiency record of the tasks to be executed by the intelligent agent in the construction area, and make interval coverage judgment between the resource arrival time and the task start time range of each task. Filter out the tasks whose task start time range is completely covered by the resource arrival time and generate the resource coverage task interval. The planned start time of a task is set as an upper and lower bound of an interval. The upper bound is set to 5 minutes later than the planned start time, and the lower bound is set to 5 minutes earlier. The resource arrival time is recorded in minutes. The task time record and resource arrival data are read sequentially, and a matching operation is performed using the task number as the key. The resource arrival time of each task is compared with the boundary of its start time interval. For example, if the resource arrival time is 15:25, and the task's start time interval is 15:20 to 15:30, then the comparison result satisfies that the resource arrival time is within the start time interval, and the coverage relationship is determined to be valid. If not, the resource is excluded. This kind of judgment is performed on resource time points, and tasks that meet the condition that "the resource time point is completely surrounded by the task time interval" are filtered out, marked as executable tasks, and added to the resource coverage task interval list. When processing batch tasks, a batch judgment mechanism is used for vectorized operation. Matrix A is a two-dimensional array of task time intervals, and matrix B is a resource time array. Fast filtering is achieved by judging the interval inclusion between each element, generating resource coverage task intervals.

[0020] S112: Call the resource coverage task range, extract the corresponding task type requirements and construction site task records, compare the consistency between the task identifier and the task type field, filter the tasks whose task types match the construction site task records, and generate a set of matching task types. The task type field is extracted item by item and matched with the task type identifier in the construction site task record. First, the task types are uniformly converted into strings of uniform length. The type similarity is extracted by comparing the strings character by character. Let the task type be "concrete pouring" and the construction site task record be "concrete construction". Their codes are 11001 and 11010 respectively. The Hamming distance between the two is taken as 1, which is less than the set threshold of 2. The task is judged to be of the same type and included in the matching result. In this process, the task types are compared one by one to build a similarity matrix. The judgment is made according to the set matching threshold. The threshold of 2 is based on empirical data and the field error tolerance range. The setting process is detailed in Table 1. The optimal threshold range is evaluated by comparing the results of 5 construction site task types with system task types. Table 1: Task Type Similarity Threshold Setting Table

[0021] As shown in Table 1, when the Hamming distance does not exceed 2, the matching rate remains above 85%, which meets the requirements for determining the type of engineering task. Based on the selected matching results, a set of matching task types is formed.

[0022] S113: Based on the task set matching task types, extract the job types corresponding to multiple tasks, divide the tasks into groups according to job types, and extract the resource input, unit work efficiency, required work period, and job obstacle factors for each group, using the following formula: , Calculate the task execution priority within each task type group, sort the tasks within the task type in descending order of their numerical values, and obtain the multi-agent task execution priority group. in, For the first In the type of assignment, the first The task execution priority, Representing the In the type of assignment, the first The amount of resources required for this task Representing the In the type of assignment, the first The unit resource output efficiency of the task. For the first In the type of assignment, the first The task's operational obstacles Representing the In the type of assignment, the first Standard resource requirements for this task Total number of tasks; Formula calculation logic explanation: By constructing a fractional structure, comprehensively considering task resource input, resource efficiency, task standard requirements, and construction obstacles, the numerator calculates the absolute value of the difference between the actual resource output and the standard requirements in each task, which is used to reflect the degree of deviation between task resource allocation and actual needs; then, the square value of resource input and the square value of unit output of the task are added together and divided by the unit output value to construct the moderating effect of resource intensity on work efficiency. The sum of these two items constitutes the numerator of the priority index, and the denominator is the linear sum of resource input and output rate of each task, which serves as a normalization factor to control the impact of scale differences caused by different task numbers, and outputs a task priority value under a unified metric. The formula as a whole obtains a sortable numerical result by simultaneously evaluating the difference between resource supply and demand, work efficiency, and task intensity. Job execution priority is a numerical indicator used to measure how much priority a task should be given under the current resource allocation. The higher the value, the more priority the task should be scheduled under conditions of resource efficiency, demand matching, and capacity conflict. Parameter meaning and calculation process: The amount of resources required for the task, expressed in person-hours; This refers to the unit resource output rate, expressed in square meters per hour. This is a resource obstacle factor, reflecting the impact of obstacles such as congestion in the work area and construction difficulty, with a value range of 0.1 to 1.5; The standard resource requirements for the task, expressed in person-hours; Suppose there are 3 tasks under the template job type, and their parameters are shown in Table 2: Table 2: Template Job Type Task Parameter Table

[0023] As shown in Table 2, substituting into the above formula: For T1 mission: ; ; The total is 65; For T2 missions: ; ; The total is 138.5; For T3 missions: ; ; The total is 81.8; The sum of the numerators is: ; The denominator is: ; Substitute into the formula to calculate: ; The result indicates that the average priority of task execution in the template job type is 5.49, a value that can be used in the subsequent task sorting process. The advantage of the formula is that by quantifying the deviation between resources and expectations through a composite expression of resources and output rate, the rationality of task resource allocation can be effectively evaluated, and the goal of dynamic priority ranking in multi-task scenarios can be achieved in the overall system.

[0024] Please see Figure 3 The specific steps for obtaining the site scheduling behavior segment structure table are as follows: S211: Based on the multi-agent task execution priority group, the estimated execution time and job space number of the job are called to filter the task combinations in the same area, obtain the start time and end time of the task, compare the time overlap interval, determine whether there is cross conflict within the same scheduling cycle, and obtain the cross conflict task combination. The system retrieves the estimated execution time parameter of each task and its corresponding job space number, categorizing tasks into their respective job areas based on their space numbers. For task combinations within the same area, it extracts the planned start and end times for each task and constructs a task execution time overlap judgment mechanism using a pairwise comparison approach. For example, if task A's time range is 08:00 to 09:00 and task B's time range is 08:30 to 09:30, the overlapping portion is 08:30 to 09:00, with an overlap duration of 30 minutes. The judgment action involves extracting the start and end times of tasks A and B and calculating the overlap interval length by taking the difference between their maximum start and minimum end times. If the result is greater than 0, a conflict exists; if it is 0 or negative, there is no overlap. This process is repeated to process task pairs within the same task group within the same area, generating task pairs with execution time conflicts within the same scheduling cycle. In real-world scenarios, if high-altitude operations and concrete pouring tasks are scheduled simultaneously in the same area, conflicts will arise due to equipment and personnel mutual exclusion, requiring inclusion in the subsequent conflict identification judgment process to obtain cross-conflicting task combinations.

[0025] S212: Based on the cross-conflicting task combinations, identify the task combinations that generate cross-conflicts within the same scheduling cycle, extract the corresponding job space numbers, classify and register them according to the segment range, and obtain a list of conflicting job space segment numbers. The task space number is identified group by group. This number is used to establish the location of conflicting task areas. The pre-set task space code field in the task parameter table is called. The task ID and space number are matched as keys to identify the position index of the task in the space number list. The conflicting tasks are classified and summarized according to the spatial range dimension. The space code prefix is ​​used for classification and identification. For example, the space number is set as "X101", "X102", etc., and "X10" is used as a common prefix to group the spatial segments. Information such as the number of tasks and task distribution density in each segment is extracted and sorted in ascending order of space number to obtain the list of conflicting task space segment numbers.

[0026] S213: Call the list of conflicting job space segment numbers, compare the job space range and execution time between tasks in the conflict combination, extract the spatial overlap length and task priority value, and combine this with the spatial intersection density, using the formula: ; Calculate the mutual exclusion conflict flag values ​​between task pairs, set mutual exclusion flags, and establish a site scheduling behavior segment structure table; in, For the task and The mutual exclusion conflict flag value, Representative task With the task The frequency density of conflicts occurring within a unit of work area per unit of time. Representative task Within the spatial segment Cross density values ​​for each region , Representing tasks respectively With the task Priority value; Formula calculation logic: A fractional structure is used, with the numerator representing the frequency of conflict between task pairs per unit time. Based on this, the sum of the cross-density of task a in each segment of space is superimposed. By summarizing the cross-density in each segment, the degree of interference of task a is reflected. The denominator is the sum of the priority values ​​of tasks a and b, which is used to normalize the dependence of the conflict index on the scheduling priority attribute of the task itself. The entire formula integrates the conflict frequency and spatial density in a weighted manner and outputs a standardized mutually exclusive conflict identification value. The operation structure has a two-layer structure of linear summation and proportional control to ensure that the severity of the conflict can be quantitatively expressed. The mutual exclusion conflict flag value is a numerical indicator used to quantify the degree to which two tasks overlap and interfere with each other in space and time. This value takes into account the unit time conflict frequency, spatial crossover density and execution priority of the tasks. The larger the flag value, the stronger the exclusivity between the tasks. In scheduling, simultaneous execution should be avoided. Parameter meaning and calculation process: For a unit of time and The frequency density of collisions occurring within the same section (unit: times / hour); Indicates task In the space segment Cross density values ​​in; , Representing tasks respectively and The priority value is a dimensionless coefficient, and the denominator is used for normalization. In the specific operation, the task is set. With the task The collision frequency within the same space segment is 4 times per hour, mission Within this spatial segment, there are three cross-density values: 1.2, 1.0, and 0.8. (Task) and The priorities are 3.0 and 4.0 respectively, so the calculation process is as follows: Calculate the numerator: ; Calculate the denominator: ; Substitute into the formula to calculate: ; The results show that the conflict identification value of the task pair is 1.00, providing a numerical basis for further scheduling, sorting and judgment; Table 3: Example Table of Parameters for Conflict Tasks

[0027] As shown in Table 3, the conflict identification value for tasks T105 and T109 is 1.00, and the conflict identification value for tasks T106 and T110 is 1.12. The higher the value, the stronger the conflict, and the more it should be avoided in subsequent scheduling.

[0028] Please see Figure 4 The specific steps for obtaining the scheduling task trigger state chain are as follows: S311: Call the completed task number in the construction site scheduling behavior segment structure table, extract the corresponding work completion flag, operation content quantity and location record time, match the three types of data with the numbering and reconstruct them by unifying the numbering dimension to form a work status data combination item; The process involves retrieving the completed task number field and mapping it to the task status field recorded in the task completion flag table. Tasks marked with a completion status of "1" are extracted, along with their corresponding task flag values. The process also calls the corresponding operation content quantity record table and location record table to extract the total number of operations involved in each task and their spatial location information, constructing a three-dimensional task status array. During construction, the three data dimensions are reconstructed and aligned according to the task number, set as Dimension A: Task Completion Flag Set, Dimension B: Operation Content Quantity Set, and Dimension C: Spatial Location Set, in triplets format. If task T201 has a completion status of "1", four operations, and a job space of "X105", then the triple is denoted as (T201). 1 4 X105) performs this type of triplet assembly action on the task data to form a combination of job status data items.

[0029] S312: Based on the multiple numbered items in the job status data combination, determine the job completion flag as the identifier value, and perform structural offset processing on the operation content quantity and task number group value, using the formula: ; Calculate the combined response of a single task, record the task number whose combined response of a single task is greater than zero, and obtain the activated task number item. in, Representing the The single-task combined response volume of a task Representing the The completion indicator for each task. Representing the The number of operations per task. Representing the The median number of operations within the same task group with the same task number. Representing the The number of operation nodes corresponding to each task in the job phase. Represents task number Corresponding to the dispatch response interference factor within the construction site area, Representative number The product of the number of operations in the task and the number of matching tasks. Representative number The number of reverse waits during task execution; Formula calculation logic: Combining three levels of substructures, completion markers are used in the molecular structure. As a control switch item, the difference between the number of operation items and the number of operation items and interference factors The interaction effect term is used to reflect the cumulative effect of the actual completed task on local disturbances; the denominator uses the weighted number of nodes. Used for normalization, so that the impact of the difference in the number of operation terms on the response is balanced by the node complexity; square root term Used to convert area to linear space so that the task load area does not expand by the square of the area; the last term is the linear priority level number. The advantage of the formula is that by combining task completion, operational complexity, spatial factors and execution level, it can achieve accurate response screening before the task chain is triggered. The single-task combination response is a quantitative indicator that measures the activation and execution of a task in the current job state. It comprehensively reflects multiple factors such as its operational complexity, node density, spatial interference, and priority. The larger the value, the more significant the impact of the task on the current scheduling structure and the stronger the execution triggering conditions. Extract the task number field from each combination sequentially. Iterate through the completion status flags of each task to determine if it is in a completed state. If the flag is "1", proceed to the calculation process to extract the number of operations performed on that task. Average number of operations per task with the same task number within the task number group Number of operation nodes in the relevant work phase Interference factors in the work area Operation content parameters area value Task priority numbering ; The parameters are defined as follows: Let 1 be the task completion flag and 0 be the incomplete flag. Taking task T305 as an example, let its completion marker be 1, the number of operation items be 6, the average number of operation items per number group be 4, the number of operation nodes in the operation phase be 2, the interference factor be 1.1, and the operation area be 36m². 2 The priority number is 2. Substituting it into the formula, the calculation is as follows: Calculate the difference term and multiply it by the interference factor: ; Add the normalized node factor: ; Square root area term: ; Substitute into the formula to calculate: ; The results show that the combined response of a single task is 8.733. This value is used to determine whether the activation threshold is met when activating the task number item (the activation threshold is set to 5). If so, the task meets the activation condition. Table 4: Example Table for Calculating Unit Task Combination Response Quantity

[0030] As shown in Table 4, tasks T305 and T306 received response values ​​of 8.733 and 6.000 respectively, both of which are greater than the activation threshold of 5. Therefore, both will be marked as activated tasks.

[0031] S313: Call the activation task number item, retrieve the corresponding next task number, assign a start identifier field to the next task, establish a mapping path relationship between the activation task number and the next task, and generate a scheduling task trigger state chain. Search for the successor task identifier in the task chain list. Obtain the next-order task number that depends on the activated task number through the task relationship mapping table. Iterate through the successor tasks of each activated task, marking each next-order task as a triggerable task. Register each pair of "activated task - next-order task" relationships in the task mapping table, forming a bidirectional searchable structure using task number pairs. Set the next-order tasks of activated task T305 as T309 and T311, and construct the relationship pair (T305... T309), (T305) T311) is recorded in the mapping linked list structure. The subsequent scheduling process triggers the task state chain operation based on this structure to generate the scheduling task trigger state chain.

[0032] Please see Figure 5 The specific steps for obtaining the task content logic continuation graph are as follows: S411: Based on the task number that can be started in the scheduling task triggering status chain, extract the corresponding construction area label, operation type label and rhythm control identifier, establish a corresponding label item set using the task number and the three label contents, and then splice the three label contents in the order of task number to generate a path segment sequence set. Read the field content from the task attribute table, extract the construction area label, operation type label, and rhythm control identifier corresponding to the task. Set the area corresponding to task T001 as "Southeast Zone 1", the operation type as "reinforcement layout", and the rhythm control identifier as "rhythm segment A". Repeat the extraction operation for task numbers T002, T003, etc. The three types of labels for each task need to be located from the structured data table according to the task number. After reading the fields, merge and splice the three labels in order. Set T001 to be spliced ​​as "Southeast Zone 1 - Reinforcement Layout - Rhythm Segment A" and T002 as "Southeast Zone 1 - Concrete Pouring - Rhythm Segment A" to form a label path segment. After all splicing is completed, organize them in the order of task number to establish a path segment sequence set. This sequence set can be stored in the task path tracking table for later use. The splicing operation is completed by connecting the label field content with hyphens. If the label T003 is "Northwest Zone 2, Formwork Installation, Rhythm Segment B", after splicing, it becomes "Northwest Zone 2 - Formwork Installation - Rhythm Segment B", and the path segment sequence set is obtained.

[0033] S412: Call the path segment sequence set, extract the sequential position of the label items in the sequence for continuous task path segments, perform consistency judgment between adjacent segments, identify path segment combinations with related label content, obtain the label comparison relationship in the path segment group, and generate label consistency comparison results; A label comparison operation is performed on any two adjacent path segments to determine whether there is a correlation between their contents. Adjacent pairs are extracted according to the order in which the path segments appear, such as 1st and 2nd, 2nd and 3rd, etc. Then, the label composition of each group of path segments is identified, and the construction area label, work type label, and rhythm control mark are compared in sequence. If the label contents of two path segments are completely the same, they are considered highly consistent; if two labels are the same, they are moderately consistent; if only one label is the same, they are lowly consistent; if they are completely inconsistent, they are considered discontinuous. Path segment 1 is "Southeast Zone 1 - Reinforcement Layout - Rhythm Segment A", and path segment 2 is "Southeast Zone 1 - Formwork Installation - Rhythm Segment A". The construction area and rhythm control mark are the same, so it is judged as moderately consistent. The comparison of path segment 2 and path segment 3 continues. If path segment 3 is "Southeast Zone 1 - Formwork Installation - Rhythm Segment B", then only the work type is the same, so it is judged as lowly consistent. In actual operation, the comparison level of each group of path segments needs to be marked on the path label comparison for recording, and the label consistency comparison result is generated.

[0034] S413: Based on the label consistency comparison results and the task number sequence information, determine whether the label combination features between adjacent task path segments have a continuous relationship. For task numbers with a continuous relationship, construct a unidirectional connection path, organize the task nodes according to the path structure, and generate a task content logical continuity graph. Based on the sequential structure of task numbers in the original scheduling task chain, determine which adjacent tasks have continuous label combination features. Path segment pairs marked as "highly consistent" or "moderately consistent" in the comparison results can be considered to have a continuous label combination relationship. If tasks T002 and T003 are moderately consistent, then a one-way connection is established between their task numbers, that is, T002 is connected to T003. Then check whether T003 and T004 have the same relationship. If they meet the requirements, continue to add connections to form a path sequence structure. Continuous numbered paths such as T002→T003→T004 are used as connection paths. Collect connection path structures that meet the conditions, and use task numbers to construct a graph structure. It can be drawn as a linear directed graph through the connection relationship between task numbers. This graph uses task numbers as nodes and one-way connections as edges. In the actual construction process, node mapping can be carried out using number indexes, and the connection paths can be organized into an adjacency information list for storage to ensure that the continuous logical structure between task nodes is clearly displayed in the graph, generating a task content logical continuity graph.

[0035] Please see Figure 6 The specific steps for obtaining the parallel control results of construction site tasks are as follows: S511: Based on the task number in the task content logical succession graph, call each pair of task numbers that form a succession relationship and the segment number in which they are located. According to the order between the numbers, by comparing whether the segment numbers of adjacent tasks form a continuous relationship, perform the segment number adjacency judgment on the task pairs that form a succession relationship and generate adjacent task pair number groups. The task pair number list and the corresponding task segment number list that form a successive relationship in the map need to be extracted. The task numbers are generally non-repeating integer codes, such as T1, T2, T3, etc., and the segment numbers are sequential numbers representing their physical locations, such as Z101, Z102, Z103, etc. After extraction, a structure recognition operation is performed on each task pair number, that is, based on the sequential order of the numbers, such as T1→T2, T2→T3, etc., the connection direction between the task pairs is constructed, and the segment number Z of the two tasks in the corresponding task pair is extracted. a The criteria for determining the continuity of segment numbers can be set by comparing the segment number difference ΔZ = Zb - Zb. aWhether it is an integer multiple of the smallest unit segment number spacing, without setting a specific value, this difference can be used as a logical continuity standard. Setting: If the number spacing between Z101 and Z102 is set to ΔZ=1 unit segment, then Z102 and Z101 are continuous segments. This judgment process can be completed by iterating through the task pair set and calling the corresponding segment number set to perform logical judgment operations. In the example, if there is a task pair T12→T13, its corresponding segment is Z202→Z203. Judging from ΔZ=203-202=1, it satisfies the continuity relationship. Then the task pair is judged as an adjacent task pair. The task pair numbers that satisfy the continuity relationship are structurally combined to obtain the adjacent task pair number group.

[0036] S512: Based on the adjacent task pairs numbering groups, extract the operation rhythm identifier corresponding to each group of tasks and the operation rhythm value of the real-time segment. By comparing the consistency between the task operation rhythm identifier and the real-time segment operation rhythm value, filter the task combinations with synchronized operation rhythms to obtain a list of synchronized task combinations. Extract the task rhythm identifier corresponding to each group of numbers and its corresponding real-time segment rhythm value. The task rhythm identifier can be the rhythm number of the task execution, such as J101, J102, etc., while the real-time segment rhythm value can be the standard rhythm identifier currently set or collected in real time within each physical segment. Set the rhythm value corresponding to segment Z101 to J101. By checking whether the task rhythm identifier and the segment rhythm value are consistent, identify whether the task and its segment have a matching relationship in terms of rhythm, and determine the comparison method used in the operation. The method involves comparing characters or numbers. If JTn = JZn, the task rhythms are consistent; otherwise, they are inconsistent. By extracting task combinations with consistent relationships, a list of task combinations with synchronized rhythms is constructed. For example, tasks T15 and T16 are both located in segment Z205. The rhythm identifier of T15 is J201, and the real-time rhythm value of Z205 is also J201. Therefore, T15 is a synchronized task. If T16 is J202, it is removed, and only synchronized rhythm task combinations are retained. This process is repeated to filter all adjacent task pairs in the number group that satisfy the rhythm consistency. Through set classification operations, a list of synchronized task combinations is obtained.

[0037] S513: Call the set of section numbers and task numbers in the synchronous task combination list, merge the tasks in the same combination into the corresponding section, identify the task number control relationship under the corresponding section, and generate the parallel control result of the construction site tasks. It is necessary to establish a merge relationship operation for the tasks within the combination in the physical segment, that is, to simultaneously incorporate multiple tasks in the combination into the parallel control mechanism of the same segment, and extract the task number set {T1, T2, ..., T...} from the combination. nThe task set mapping is performed on Zx, which is the corresponding segment number Zx, so that the number belongs to the same segment node. After the structure mapping is performed, the task control belonging relationship within each combination is identified. Through the succession logic graph between task numbers and the spatial topology structure under the same segment, parallel control links between task numbers are established. In the actual construction process, the control relationship between task pairs adopts the task sequence index matching method. If combination A contains tasks T21, T22, and T23, and the task sequence is T21→T22→T23, and the corresponding segment is Z301, then the combination is merged into the parallel control task chain under Z301. Through this chain structure, a task parallel control rule set can be established. Each rule set is represented as the mapping structure {Z301:[T21, T22, T23]}, generating the construction site task parallel control result.

[0038] The multi-agent-based construction site task scheduling system is used to execute the above-mentioned multi-agent-based construction site task scheduling method. The system includes: The task triggering module obtains the start time range, resource arrival time and unit operation efficiency record of the tasks to be executed by the intelligent agents in the construction area, judges the coverage interval of the task start time and resource arrival time, defines the tasks that match the unit operation efficiency record as triggerable tasks, sets the task execution priority, and generates a multi-agent task execution priority group. The conflict detection module calls the task start time, job space number and expected execution time in the multi-agent task execution priority group, compares the start and end times of tasks in the same area across intervals, marks the task combinations that cause cross-conflicts and their corresponding space segment numbers, and establishes a site scheduling behavior segment structure table. The status judgment module calls the work completion flag, operation content quantity and location record time of the construction site scheduling behavior segment structure table, marks the tasks that meet the conditions as active, and generates a scheduling task trigger status chain. The path construction module extracts the construction area label, operation type label and rhythm control identifier based on the startable task number in the scheduling task trigger status chain, compares the number of consecutive items in the path segment, and obtains the task content logical continuity graph. The parallel control module calls the task pair segment number in the task content logic continuation diagram, performs adjacency judgment of spatial segments and compares the rhythm control mark with the real-time operation rhythm, merges tasks with synchronized rhythm into the same segment, and generates the parallel control result of construction site tasks.

[0039] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A construction site task scheduling method based on multi-agent, characterized in that, The method comprises the following steps: S1: obtaining the starting time range of the tasks to be executed by the agents in the construction area, the resource arrival time and the unit work efficiency record, performing time period coverage judgment on the task starting time and the resource arrival time, matching the unit work efficiency record and the task type demand, and forming a multi-agent task execution priority group; S2: based on the multi-agent task execution priority group, calling the predicted execution time of the work and the work space number, comparing the start time and end time of the tasks in the same area, judging whether concurrent or cross conflict occurs in the same scheduling period, and generating a construction site scheduling behavior section structure table; S3: calling the completed task number in the construction site scheduling behavior section structure table, corresponding to extracting the work completion flag, the operation content quantity and the positioning record time, judging the passed tasks as active tasks, and generating a scheduling task trigger state chain; S4: according to the startable task number in the scheduling task trigger state chain, extracting the construction area label, the work type label and the rhythm control identifier, merging the three labels to build a path segment, and comparing the number of consecutive items of the path segment, and generating a task content logical connection graph.

2. The multi-agent based construction site task scheduling method according to claim 1, characterized in that, The multi-agent task execution priority group comprises a task starting time interval, a resource arrival determination result and a task type corresponding priority, the construction site scheduling behavior section structure table comprises a mutual exclusion identifier, a task number mapping relationship and a work space section number, the scheduling task trigger state chain comprises an active task number, a next task starting mark and a task state mapping chain, and the task content logical connection graph comprises a path segment sequence, a content continuity relationship between tasks and a work rhythm control identifier. 3.The multi-agent based construction site task scheduling method of claim 1, wherein, The acquisition step of the multi-agent task execution priority group is specifically: S111: obtaining the starting time range of the tasks to be executed by the agents in the construction area, the resource arrival time and the unit work efficiency record, performing interval coverage judgment on the resource arrival time and the task starting time range of each task, screening tasks whose task starting time range is completely covered by the resource arrival time, and generating a resource coverage task interval; S112: calling the resource coverage task interval, extracting the corresponding task type demand and the construction site task record, and screening tasks whose task type matches the construction site task record by comparing the consistency of the task identifier and the task type field, and generating a matching task type task set; S113: based on the matching task type task set, extracting the work type corresponding to multiple tasks, dividing the tasks into groups according to the work type, extracting the resource input, unit work efficiency, task required period and work hindering factor of the tasks in the group, calculating the work execution priority of the tasks in each work type, sorting the tasks in the work type in descending order of numerical value, and obtaining a multi-agent task execution priority group.

4. The multi-agent based construction site task scheduling method according to claim 3, characterized in that, The acquisition step of the construction site scheduling behavior section structure table is specifically: S211: Based on the multi-agent task execution priority group, the scheduled execution time and the job space number of the job are called to screen the task combination in the same area, obtain the start time and end time of the task, perform time overlap interval comparison, judge whether there is cross conflict in the same scheduling cycle, and obtain the cross conflict task combination; S212: According to the cross conflict task combination, the task combination that produces cross conflict in the same scheduling cycle is identified, the corresponding job space number is extracted, classified according to the section range, and the conflict job space section number list is obtained; S213: Call the conflict job space section number list, compare the job space range and execution time between the tasks in the conflict combination, extract the space overlap length, task priority value, and combine the space cross density to calculate the mutual exclusion conflict identification value between the task pairs, set the mutual exclusion identification, and establish the construction site scheduling behavior section structure table.

5. The multi-agent based construction site task scheduling method according to claim 4, characterized in that, The acquisition step of the scheduling task trigger state chain is specifically: S311: Call the completed task number in the construction site scheduling behavior section structure table, correspondingly extract the job completion flag, operation content quantity and positioning record time, match the three types of data with numbers and reconstruct them in a unified number dimension to form a job state data combination item; S312: According to the multiple number contents in the job state data combination item, judge the job completion flag as an identification value, and perform structure offset processing on the operation content quantity and task number group value, calculate the single task combination response quantity, record the task number of the single task combination response quantity greater than zero, and obtain the activated task number item; S313: Call the activated task number item, retrieve the corresponding next task number, assign a start identification field to the next task, and establish a mapping path relationship between the activated task number and the next task to generate a scheduling task trigger state chain.

6. The multi-agent based construction site task scheduling method according to claim 5, wherein, The acquisition step of the task content logical connection graph is specifically: S411: According to the startable task number in the scheduling task trigger state chain, extract the corresponding construction area label, job type label and rhythm control identification, use the task number and the three label contents to establish a corresponding label item set, and then splice the three label contents according to the task number sequence to generate a path segment sequence set; S412: Call the path segment sequence set, extract the order position of the label item in the sequence for the continuous task path segment, perform consistency judgment between adjacent segments, identify the path segment combination with associated features of the label content, obtain the label comparison relationship in the path segment group, and generate a label consistency comparison result; S413: According to the label consistency comparison result, combined with the task number sequence information, judge whether the label combination features between adjacent task path segments have a continuous relationship, construct a one-way connection path for the task number with a continuous relationship, organize the task nodes according to the path structure, and generate a task content logical connection graph.

7. The multi-agent based construction site task scheduling method of claim 1, wherein, The method further comprises the S5 step: S5: calling the task number in the task content logical connection graph, judging the adjacent of the section number of the task pair forming the connection relationship, and entering the scheduling reconstruction of the task group with the judgment, comparing the operation rhythm identifier with the real-time section operation rhythm, verifying the synchronization group, and merging into the same section to generate the construction task parallel control result; The construction task parallel control result includes a synchronous operation group in a section, a scheduling rhythm consistency verification result, and a scheduling reconstruction section set.

8. The multi-agent based construction site task scheduling method according to claim 7, characterized in that, The acquisition step of the construction task parallel control result is specifically: S511: based on the task number in the task content logical connection graph, calling each pair of task numbers forming the connection relationship and the section number, comparing whether the section numbers of adjacent tasks form a continuous relationship according to the order before and after the numbers, judging the adjacent of the section number of the task pair forming the connection relationship, and generating the adjacent task pair number group; S512: according to the adjacent task pair number group, extracting the operation rhythm identifier corresponding to each task group and the operation rhythm value of the real-time section, comparing the consistency between the task operation rhythm identifier and the real-time section operation rhythm value, screening the synchronous task combination, and obtaining the synchronous task combination list; S513: calling the section number and task number set in the synchronous task combination list, merging the tasks in the same combination into the corresponding section, identifying the task number control relationship under the corresponding section, and generating the construction task parallel control result.

9. A multi-agent based construction site task scheduling system, characterized by, The system is used to realize the multi-agent based construction task scheduling method of any one of claims 1-8, and the system comprises: The task triggering module acquires the starting time range of the agent to be executed task in the construction area, the resource access time and the unit operation efficiency record, judges the coverage interval of the task starting time and the resource access time, defines the task matched with the unit operation efficiency record as a triggerable task, sets the task execution priority, generates a multi-agent task execution priority group, and triggers the task. The conflict detection module calls the task starting time, operation space number and expected execution time in the multi-agent task execution priority group, compares the start and end time of the tasks in the same area, marks the task combination and corresponding space section number with intersection conflict, and establishes a construction scheduling behavior section structure table; The state judgment module calls the operation completion flag, operation content quantity and positioning record time of the construction scheduling behavior section structure table, marks the tasks meeting the conditions as active state, generates a scheduling task triggering state chain, and triggers the task. The path construction module extracts the construction area label, operation type label and rhythm control identifier according to the startable task number in the scheduling task triggering state chain, compares the number of continuous items of the path segment, and obtains a task content logical connection graph. The parallel control module calls the task pair section number in the task content logical connection graph, judges the adjacent of the space section and compares the rhythm control identifier with the real-time operation rhythm, merges the rhythm synchronous tasks into the same section, and generates a construction task parallel control result.

Images