A method and system for monitoring progress and quality at a construction site

Abstract

The present invention provides a method for monitoring the progress and quality of a construction site, the method comprising: determining the construction site conditions based on the construction site data; determining the progress estimate based on the structural completion, process progress, material availability and worker attendance rate; and generating a construction log according to a preset template based on the construction site conditions and the progress estimate.

Description

Technical Field

[0001] The present invention relates to the field of construction monitoring, and in particular to a method and system for monitoring the progress and quality of a construction site. Background Art

[0002] As the construction industry moves towards digital transformation, the management of construction sites has become more systematic and intelligent. However, the current online monitoring of the progress and quality of the construction process is often carried out only after the construction is completed, and rectification and acceptance are carried out. Without continuous monitoring of the progress and quality of the construction process, it may lead to delays in the construction progress, difficulty in ensuring construction quality, and waste of construction materials.

[0003] In order to continuously monitor the progress and quality of the construction process, CN115345446A proposed a project completion acceptance method based on drone line inspection and point cloud data. The inspection tasks are planned according to the quality acceptance report so that the drone can perform the inspection tasks. The project quality is compared and analyzed based on the point cloud data collected by the drone and the standard acceptance model to generate a new quality acceptance report. However, it does not involve continuous monitoring of the progress of each process during the construction process.

[0004] Therefore, it is hoped to provide a progress and quality monitoring method and system for construction sites, so as to realize timely and continuous monitoring of the progress and quality during the construction process, and store the results of continuous monitoring for traceability at any time, so as to avoid delays in construction progress or impacts on construction quality due to untimely monitoring. Summary of the invention

[0005] One or more embodiments of the present specification provide a method for monitoring the progress and quality of a construction site, the method comprising: determining a construction site condition based on construction site data, the construction site condition comprising at least one of a structural completion degree, a process progress, a material availability rate, and a worker attendance rate; determining a progress estimate based on the structural completion degree, the process progress, the material availability rate, and the worker attendance rate, the progress estimate being used to reflect the overall progress of the construction project; generating a construction log according to a preset template based on the construction site condition and the progress estimate, the preset template comprising a process segmentation progress summary, the process segmentation progress summary being used to reflect the process segmentation progress.

[0006] One or more embodiments of the present specification provide a progress and quality implementation monitoring system for a construction site, the system comprising a processing module, a sensor module, and a display module, the processing module being configured to: determine a construction site condition based on construction site data, the construction site condition comprising at least one of a structural completion degree, a process progress, a material availability rate, and a worker attendance rate; determine a progress estimate based on the structural completion degree, the process progress, the material availability rate, and the worker attendance rate, the progress estimate being used to reflect the overall progress of the construction project; generate a construction log based on the construction site condition and the progress estimate in accordance with a preset template, the preset template comprising a process segmentation progress summary, the process segmentation progress summary being used to reflect the process segmentation progress.

[0007] One or more embodiments of the present specification provide a progress and quality implementation monitoring device for a construction site, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the progress and quality implementation monitoring method for a construction site described in the above embodiments.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the progress and quality monitoring method for a construction site as described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 It is a system module diagram of a progress and quality implementation monitoring system for a construction site according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a method for monitoring progress and quality of a construction site according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flowchart of determining and adjusting a task allocation scheme according to some embodiments of this specification;

[0013] Figure 4 is an exemplary schematic diagram of a score prediction model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] When the operations are performed according to the step description in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, the steps may be omitted, and other steps may be included in the operation process.

[0018] Figure 1 It is a system module diagram of a progress and quality implementation monitoring system for a construction site according to some embodiments of this specification.

[0019] In some embodiments, a progress and quality implementation monitoring system 100 for a construction site (hereinafter referred to as monitoring system 100 ) may include a sensor module 110 , a processing module 120 , and a display module 130 .

[0020] The sensor module 110 is configured as a module for acquiring sensor data. The sensor module 110 is set at the construction site. For more information about sensor data, please refer to Figure 2 and its related description.

[0021] In some embodiments, the sensor module 110 may include a camera, a temperature sensor, a humidity sensor, a vibration sensor, a laser rangefinder, a radio frequency identification, and / or a barcode scanner.

[0022] The camera is configured to capture the activities of personnel and equipment in different construction areas of the construction site. The construction area refers to the area where different processes are carried out in the construction site, such as the steel bar tying area, the concrete pouring area, etc.

[0023] In some embodiments, the camera may include multiple fixed cameras, mobile cameras and / or camera pan / tilts.

[0024] The fixed camera is configured to capture the activities of personnel and equipment in a construction area. In some embodiments, the fixed camera can be set at a first position in different construction areas of the construction site. The first position refers to a position where the shooting range of the fixed camera can cover the entire area. In some embodiments, the first position can be pre-set based on historical experience.

[0025] The mobile camera and / or camera pan / tilt are configured to move to capture the activities of personnel and equipment in different construction areas of the construction site. In some embodiments, the mobile camera and / or camera pan / tilt can be arranged around the construction site and move.

[0026] The temperature sensor is configured to monitor the ambient temperature of the construction site. The humidity sensor is configured to monitor the ambient humidity of the construction site. In some embodiments, the temperature sensor and the humidity sensor can be set at a second position in the construction area. The second position refers to a position in the construction area where temperature and humidity monitoring is required. In some embodiments, the second position can be pre-set based on historical experience.

[0027] The vibration sensor is configured to monitor the operating status of the device. In some embodiments, the vibration sensor can be set at a monitoring position of the device. The monitoring position refers to the position where the vibration of the device is desired to be monitored. For example, if the vibration of the bearing of a mechanical device is desired to be monitored, the monitoring position is near the bearing of the mechanical device.

[0028] The laser rangefinder is configured to measure the size and shape of a building structure. In some embodiments, the laser rangefinder can be arranged around a building structure. A building structure refers to the structure of a building under construction.

[0029] The RFID and / or barcode scanners are configured to track the locations of construction materials, equipment, and workers and the time points corresponding to the arrival of the construction materials, equipment, and workers at the locations. In some embodiments, the RFID and / or barcode scanners may be arranged around the construction site.

[0030] In some embodiments, RFID tags may be attached to construction materials and equipment, and workers may wear equipment with RFID tags attached to allow RFID devices to identify and track them.

[0031] The processing module 120 is configured to process information or data related to the monitoring system 100. In some embodiments, the processing module 120 can be configured to determine the construction site conditions based on the construction site data; determine the progress estimate based on the structural completion, process progress, material availability and worker attendance; and generate a construction log according to a preset template based on the construction site conditions and the progress estimate.

[0032] In some embodiments, the processing module 120 can be further configured to obtain sensor data through a sensor module; and obtain image data through drone inspection.

[0033] In some embodiments, the processing module 120 may be further configured to determine the structural completion by a structural prediction model based on the image data.

[0034] In some embodiments, the processing module 120 can be further configured to determine a task allocation plan based on the workers' comprehensive scores, team collaboration, and task decomposition rules; in response to the completion status of the subdivided task items not meeting preset conditions, adjust the task priority corresponding to the subdivided task items, and adjust the workers corresponding to the subdivided task items based on preset rules.

[0035] In some embodiments, the processing module 120 may be further configured to determine a comprehensive score of the worker through a score prediction model based on skill matching, historical performance, teamwork, health and safety score, and experience level.

[0036] In some embodiments, the processing module 120 may be further configured to update the rating prediction model based on the skill matching and recent performance.

[0037] In some embodiments, the processing module 120 may be further configured to: in response to obtaining user input information, generate a construction log based on the construction site data.

[0038] In some embodiments, the processing module 120 is further configured to determine whether there is an abnormal situation in the construction log based on the construction log; in response to the existence of an abnormal situation in the construction log, generate and send an early warning message to the supervisor.

[0039] In some embodiments, the processing module 120 may further include a processor. In some embodiments, the processor may process information and / or data related to the monitoring system 100 to perform one or more functions described in the present application. In some embodiments, the processor may include one or more engines (e.g., a single-chip processing engine or a multi-chip processing engine). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc., or any combination thereof.

[0040] In some embodiments, the processing module 120 may also include a storage device. The storage device may be used to store data, instructions, and / or any other information. In some embodiments, the storage device may store data and / or information obtained from at least one module of the monitoring system 100 or an external data source. For example, the storage device may store a construction log. In some embodiments, the storage device may store data and / or instructions that the processor uses to execute or use to complete the exemplary methods described in this specification.

[0041] In some embodiments, the storage device may store the work information of all workers. Work information refers to all information related to workers. For example, name, length of service, type of work, skill matching, historical performance, recent performance, teamwork, health and safety score, and experience level. In some embodiments, work information may be input and obtained by managers. Managers refer to people who manage and evaluate workers.

[0042] In some embodiments, the storage device may include mass storage, removable storage, etc., or any combination thereof. In some embodiments, the storage device may be integrated into the processor.

[0043] The display module 130 is configured to display information and / or data related to the monitoring system 100 .

[0044] In some embodiments, the display module 130 can be configured to display a construction log. For more information about the construction log, see Figure 2 and its related description.

[0045] For more details about the sensor module 110, the processing module 120 and the display module 130, see Figure 2-Figure 4 and its related description.

[0046] It should be understood that Figure 1 The system and its modules shown can be implemented in various ways. It should be noted that the above description of the progress and quality monitoring system and its modules for construction sites is only for the convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The sensor module 110, processing module 120 and display module 130 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the scope of protection of this specification.

[0047] Figure 2 is an exemplary flow chart of a method for monitoring the progress and quality of a construction site according to some embodiments of this specification. In some embodiments, process 200 is executed by a processor. Figure 2 As shown, process 200 includes the following steps:

[0048] Step 210, determining the construction site conditions based on the construction site data.

[0049] Construction site data refers to data related to the actual conditions at the construction site.

[0050] In some embodiments, the construction site data may include sensor data and image data of the construction site. In some embodiments, the processor may obtain sensor data through a sensor module and obtain image data through a drone inspection. For more information about the sensor module, see Figure 1 and its related description.

[0051] Sensor data refers to the data obtained by the sensor module.

[0052] In some embodiments, the sensor data may include at least one of the location of workers and equipment, material availability, equipment operating status, process time, worker working hours and efficiency, hazard indicators and event reports, worker attendance data, and environmental parameters.

[0053] The positioning of workers and equipment can reflect the actual position of workers and equipment at the construction site. In some embodiments, the processor can obtain the actual position of workers and equipment at the construction site uploaded by the radio frequency identification device, and determine the actual position of workers and equipment at the construction site as the positioning of workers and equipment.

[0054] In some embodiments, the construction site may be represented by a plan view or the like.

[0055] In some embodiments, the locations of workers and equipment may be represented by points on a plan view representing the construction site.

[0056] The material availability can reflect the usage of the building materials at the construction site. In some embodiments, the material availability can include the quantity and time point of the building materials actually arriving at the corresponding construction area, and the time when the building materials are scheduled to arrive at the corresponding construction area.

[0057] In some embodiments, the processor may obtain the number and time of the construction materials arriving at the corresponding construction area uploaded by the RFID device. The time when the construction materials are scheduled to arrive at the corresponding construction area may be input by the management personnel.

[0058] In some embodiments, the device operation status may include the device's working time, operating speed, and abnormal state. The working time refers to the time the device is running. The operating speed refers to the speed at which the device is running. The abnormal state may include device abnormality and device no abnormality.

[0059] In some embodiments, since the vibration sensor and the device operate synchronously, the processor may obtain the operating time of the vibration sensor uploaded by the vibration sensor, and determine the operating time of the vibration sensor as the working time.

[0060] In some embodiments, since the vibration signal can reflect the operating speed and abnormal state of the equipment, the processor can query the reference operating speed and reference abnormal state corresponding to the vibration signal in the equipment table based on the vibration signal uploaded by the vibration sensor, and determine the reference operating speed and reference abnormal state as the operating speed and abnormal state of the equipment. Among them, the equipment table can be pre-set based on historical data, including multiple vibration signals and corresponding reference operating speeds and reference abnormal states. The reference operating speed and reference abnormal state can be determined by a technician inspecting the equipment.

[0061] The process duration refers to the time from the start time of the process to the current time. A process refers to the steps in the construction of a building. For example, positioning and setting out, steel bar tying, concrete pouring, etc. A process can include multiple construction steps. For example, the concrete pouring process includes the preparation for concrete pouring, concrete pouring, and concrete curing.

[0062] In some embodiments, the processor may subtract the process start time from the current time and determine the difference as the process duration.

[0063] In some embodiments, the processor can obtain the time point corresponding to the image at the beginning of the process uploaded by the camera, and the time point corresponding to the current image, and determine the time point corresponding to the image at the beginning of the process and the time point corresponding to the current image as the moment when the process starts and the current moment.

[0064] The working hours of workers refer to the time that workers enter the construction area to work. In some embodiments, the processor can obtain the time that the workers stay in the corresponding construction area uploaded by the radio frequency identification device, and determine the time that the workers stay in the corresponding construction area as the working hours.

[0065] In some embodiments, the processor may determine the efficiency of the worker through an efficiency index based on the amount of work completed by the worker and the working hours. The efficiency index refers to an index that guides the determination of the efficiency of the worker. In some embodiments, the efficiency index may be pre-set, including a ratio of the amount of work completed by the worker to the working hours and a level corresponding to the ratio, the higher the level, the higher the efficiency of the worker.

[0066] In some embodiments, the workload completed by the worker can be represented by a numerical value, and the larger the numerical value, the more workload the worker has completed. In some embodiments, the manager can evaluate the workload completed by the worker and input it to the processor through a terminal device. The terminal device can include a mobile phone, a desktop computer, etc.

[0067] Danger index refers to the number of dangerous events that occur at the construction site. Dangerous events are events that affect the safety of the construction site. For example, illegal operation, falling construction materials, electric shock, etc.

[0068] In some embodiments, the processor can determine whether a dangerous event has occurred and the number of times it has occurred through the sensor data uploaded by the sensor module. For example, the sensor module can upload the location of the building materials to the processor. In response to the location of the building materials not being within the corresponding prescribed area, the processor can determine that the building materials are not placed within the prescribed area, that is, an illegal operation has occurred. The prescribed area refers to an area for placing building materials. The prescribed area can be pre-set by the user based on historical experience.

[0069] An event report refers to data related to a dangerous event at a construction site. In some embodiments, the event report may include an image of the dangerous event. In some embodiments, the processor may obtain an image of the construction site uploaded by the sensor module and select an image corresponding to the dangerous event as the event report.

[0070] Worker attendance data can record the attendance of workers. Attendance can include normal attendance and abnormal attendance. Abnormal attendance can include lateness and early departure. In some embodiments, the processor can obtain the time point when the worker enters the construction site and the time point when the worker leaves the construction site uploaded by the sensor module; compare the time point when the worker enters the construction site with the working time, and in response to the time point when the worker enters the construction site being later than the working time, determine that the worker's attendance is late; compare the time point when the worker leaves the construction site with the time when the worker leaves the construction site, and in response to the time when the worker leaves the construction site being earlier than the time when the worker leaves the construction site, determine that the worker's attendance is early departure. Among them, the working time and the time when the worker leaves the construction site can be set in advance.

[0071] Environmental parameters refer to parameters related to the environment of the construction site. In some embodiments, the environmental parameters may include temperature and humidity. In some embodiments, the processor may obtain environmental parameters uploaded by the sensor module. The sensor module may collect temperature and humidity through a temperature sensor and a humidity sensor.

[0072] Image data refers to pictures or videos related to changes at the construction site, such as images of completed parts of the building structure, images of temporary facilities being arranged, etc.

[0073] In some embodiments, the processor can obtain image data captured by the drone during the inspection process. In some embodiments, the image data captured by the drone during the inspection can be used to supplement the image captured by the camera. The drone is equipped with a high-resolution camera, a temperature sensor, a humidity sensor, a vibration sensor, a laser rangefinder, a radio frequency identification and / or a barcode scanner.

[0074] In some embodiments, the number of drones may be positively correlated with the size of the construction site, that is, the larger the construction site, the greater the number of drones.

[0075] In some embodiments, the processor may send a preset inspection plan to the drone to control the drone to perform inspection photography according to the preset inspection plan. The preset inspection plan may be pre-set, including an inspection route within a preset inspection period. The preset inspection period refers to a period that does not affect the construction progress, such as 6:00 to 7:00.

[0076] The inspection route refers to the route that the drone inspects. In some embodiments, the inspection route may include areas where the sensor module cannot collect data.

[0077] In some embodiments of the present specification, the construction site data includes sensor data and image data of the construction site, so that the data reflecting the actual situation of the construction site is richer. By acquiring sensor data through the sensor module and image data through the drone, more comprehensive construction site data can be obtained, which is conducive to determining a more accurate construction site situation.

[0078] The construction site situation can reflect the actual situation of the construction site. In some embodiments, the construction site situation can include structural completion, process progress, material availability, and worker attendance.

[0079] The structural completion degree can reflect the completion degree of the building structure. In some embodiments, the structural completion degree can be expressed by a percentage or the like.

[0080] In some embodiments, the processor may determine the degree of structural completion in a variety of ways. For example, the processor may match key features of the building structure with reference features in the building renderings, and determine the ratio of the number of successfully matched key features to the number of reference features as the degree of structural completion, wherein the key features of the building structure refer to the main structures of the building structure, such as floors, beams, columns, etc.

[0081] The architectural rendering refers to a simulated image of the building structure when it is completed as a whole, including multiple reference features. The reference feature refers to the main structure in the simulated image when the building structure is completed as a whole. For example, floors, beams, columns, etc. In some embodiments, the architectural rendering can be pre-set.

[0082] For example, the key features of the building structure are the 1st floor and 3 columns, and the reference features of the building rendering are the 1st floor, 2nd floor and 4 columns. The ratio of the number of successfully matched key features to the number of reference features is 66%, that is, the structural completion degree is 66%.

[0083] In some embodiments, the processor can extract key features of the building structure from the images taken by the camera and the image data obtained by the drone inspection through image recognition technology based on the images taken by the camera and the image data obtained by the drone inspection.

[0084] In some embodiments, the processor may determine the structural completion using a structural prediction model based on the image data.

[0085] The structure prediction model refers to a model used to determine the degree of structure completion. In some embodiments, the detection model can be a machine learning model. For example, the structure prediction model can include any one or combination of a convolutional neural network (CNN) model or other customized model structures.

[0086] In some embodiments, the input to the structure prediction model may include image data and the output may include structure completion.

[0087] In some embodiments, the processor may input multiple first training samples with first labels into the initial structure prediction model, construct a loss function through the first labels and the prediction results of the initial scoring prediction model, iteratively update the parameters of the initial structure prediction model based on the loss function through methods such as gradient descent, and complete the structure prediction model training when the loss function of the initial structure prediction model meets preset conditions, wherein the preset conditions may be that the loss function converges, the number of iterations reaches a set value, etc.

[0088] The first training sample may include sample image data of a sample building structure, and the first label of the first training sample may be the actual completion degree of the sample building structure. In some embodiments, the first training sample may be obtained based on historical data, and the first label may be determined based on manual annotation.

[0089] In some embodiments of the present specification, by processing image data through a structural prediction model, the self-learning ability of the machine learning model can be utilized to find patterns from a large amount of data, obtain the correlation between the image data and the structural completeness, and improve the accuracy and efficiency of determining the structural completeness.

[0090] The process progress refers to the degree to which the process has been carried out. In some embodiments, the process progress can be expressed as a percentage or the like.

[0091] In some embodiments, the processor may query the reference process progress corresponding to the key feature in the process feature table based on the key feature of the process, and determine the obtained reference process progress as the process progress. The key feature of the process refers to the main activities of executing the process. For example, moving equipment into place, pouring, and maintenance.

[0092] In some embodiments, the process feature table may be pre-set, including a plurality of key features and corresponding reference process schedules. The reference process schedule may be obtained by user input.

[0093] Exemplarily, the key feature of the process is pouring concrete, and the reference process progress corresponding to the key feature in the process feature table is 30%, so the processor determines that the process progress is 30%.

[0094] In some embodiments, the processor can extract key features of the process from the images taken by the camera and the image data obtained by the drone inspection through image recognition technology based on the images taken by the camera and the image data obtained by the drone inspection.

[0095] The material availability rate may reflect the amount of building materials that have arrived at the corresponding construction area. In some embodiments, the material availability rate may be expressed as a percentage or the like. In some embodiments, a process corresponds to a material availability rate, and a corresponding material availability rate corresponds to a process. The material availability rate corresponding to a process may reflect the amount of building materials required for the process that have arrived at the corresponding construction area.

[0096] In some embodiments, the processor may extract the number of building materials arriving at the corresponding construction area from the material arrival situation, and determine the material arrival rate as the ratio of the number of building materials arriving at the corresponding construction area to the planned arrival number of the building materials. The planned arrival number refers to the number of building materials planned to arrive at the corresponding construction area without delaying the overall construction progress. The planned arrival number may be input in advance by the user.

[0097] The worker attendance rate may reflect the number of workers who are present. In some embodiments, the worker attendance rate may be expressed as a percentage or the like. In some embodiments, a process corresponds to a worker attendance rate, and a corresponding worker attendance rate corresponds to a process. The worker attendance rate corresponding to a process may reflect the number of workers who are present in charge of the process.

[0098] In some embodiments, the processor may extract the number of workers who are late or leave early from the worker attendance data, and determine the ratio of the number of workers who are not late or leave early corresponding to the process to the total number of workers corresponding to the process as the worker attendance rate corresponding to the process. In some embodiments, the processor may obtain the total number of workers corresponding to the process from a storage device.

[0099] In some embodiments, the construction site conditions may further include at least one of environmental parameters, hazard indicators, and event reports. For details about environmental parameters, hazard indicators, and event reports, please refer to the above description.

[0100] In some embodiments of the present specification, the construction site conditions include environmental parameters, hazard indicators and event reports, which can reflect the actual conditions of the construction site more realistically.

[0101] Step 220, determining a progress estimate based on the structural completion, process progress, material availability, and worker attendance rate.

[0102] The progress estimate value refers to the evaluation result of the overall construction progress. In some embodiments, the progress estimate value can be expressed in percentage or the like.

[0103] In some embodiments, the processor may determine the progress estimate value through a preset algorithm based on the construction site data. The preset algorithm may include a decision tree algorithm. The decision tree algorithm includes a parent node, a child node, a leaf node, and a reference progress estimate value corresponding to the leaf node. The parent node is the parent node of the child node, the leaf node is the child node at the bottom of the decision tree, and one leaf node corresponds to one reference progress estimate value. Each node represents at least one of the structural completion degree, the process progress of the process, and the material availability rate and worker attendance rate corresponding to the process.

[0104] In some embodiments, the processor can search for leaf nodes corresponding to the structural completion degree, the process progress of the process, and the material availability rate and worker attendance rate corresponding to the process in the decision tree algorithm based on the structural completion degree, the process progress of the process, and the material availability rate and worker attendance rate corresponding to the process, and determine the reference progress estimation value corresponding to the leaf node as the progress estimation value.

[0105] Exemplarily, the processor can traverse the child nodes of the first-layer nodes (nodes representing the degree of structural completion) in the decision tree algorithm (i.e., the second-layer nodes used to represent the process progress), and select the second-layer nodes that are the same as the process progress of the process; traverse the child nodes of the second-layer nodes (i.e., the third-layer nodes used to represent the material availability rate), and select the third-layer nodes that are the same as the material availability rate of the process; traverse the child nodes of the second-layer nodes (i.e., the fourth-layer leaf nodes used to represent the worker attendance rate), select the leaf node that is the same as the worker attendance rate of the process, and determine the reference progress estimate value corresponding to the leaf node as the progress estimate value.

[0106] In some embodiments, when the processor determines the progress estimate through a preset algorithm, each process can be divided according to the division criteria, and the process progress of each process can be matched with the interval of the division criteria to obtain the process division progress of each process, and the progress estimate can be determined based on the process division progress of each process.

[0107] The segmentation standard refers to the standard according to which the progress of the process is divided into different intervals. In some embodiments, the segmentation standard can be preset. In some embodiments, the segmentation standard can be represented by a vector, and the elements in the vector represent the segmentation points. For example, the segmentation standard is (0%, 40%, 70%, 100%), where 0%, 40%, 70%, 100% are the segmentation points, 0%-70% is an interval, 40%-70% is an interval, and 70%-100% is an interval.

[0108] The process segmentation progress refers to the process progress after the process is segmented according to the segmentation standard. In some embodiments, the process segmentation progress can be represented by the median of the interval of the process progress in the segmentation standard. For example, if the process progress of the process is 60%, and the process progress is between 40% and 70% of the segmentation standard, then the process segmentation progress is 55%.

[0109] In some embodiments, the processor can search for nodes in the decision tree algorithm that correspond to the degree of structural completion, the progress of process segmentation of the process, and the material availability rate and worker attendance rate corresponding to the process based on the degree of structural completion, the progress of process segmentation of the process, and the material availability rate and worker attendance rate corresponding to the process, and determine the reference progress estimation value used by the node as the progress estimation value.

[0110] In some embodiments, the processor may use the data in the second training sample as nodes of the initial decision tree to obtain an initial decision tree algorithm, and perform a pruning operation on the decision tree through a test sample with a label to obtain a trained decision tree algorithm. The second training sample may include sample construction site data of a first historical time, the test sample may include sample construction site data of a second historical time, and the label may include a progress estimate corresponding to the test sample. The second historical time is later than the first historical time.

[0111] The pruning operation refers to removing leaf nodes that are too subdivided and changing parent nodes or higher nodes to new leaf nodes.

[0112] In some embodiments, the second training sample and the test sample may be obtained based on historical data, and the label may be obtained based on manual annotation.

[0113] The upper and lower relationships between parent nodes and child nodes in the decision tree algorithm can be determined based on the weights of the data used to generate the decision tree algorithm. The greater the weight of the data, the higher the position of the corresponding node in the decision tree algorithm. For example, if the weight of the structural completion is greater than the weight of the process progress, then the node representing the structural completion is the parent node of the node representing the process progress.

[0114] In some embodiments, the weights of the structural completion degree, the process progress of each process, and the material availability rate and worker attendance rate corresponding to each process in the decision tree algorithm can be preset based on the corresponding relationship. The corresponding relationship can include that the weight of each data in the construction site data is positively correlated with the importance of each data to the overall construction progress, that is, the higher the importance of a data to the overall construction progress, the greater the weight of the data.

[0115] Step 230, based on the construction site conditions and the progress estimate, a construction log is generated according to a preset template.

[0116] The construction log refers to data that records the progress of different processes. In some embodiments, the construction log may include the date, the estimated progress value, and the process segmentation progress summary corresponding to the process, process progress, material availability rate, worker attendance rate, construction site conditions, and construction site data. The date refers to the date when the current construction log is generated.

[0117] The process segmentation progress summary refers to the content describing the process segmentation progress. For example, if the process segmentation progress is 55%, the process segmentation progress summary can be that the process is more than half completed. For another example, if the process segmentation progress is 85%, the process segmentation progress summary can be that the process is mostly completed.

[0118] In some embodiments, the processor may fill the date, estimated progress value, and process segmentation progress summary, process progress, material availability, and worker attendance rate into a preset template corresponding to the process to generate a construction log. The preset template may be pre-set.

[0119] In some embodiments, a process may correspond to a preset template, and a corresponding preset template corresponds to a process.

[0120] In some embodiments, after the processor generates the construction log, the user can check the accuracy of the construction log and make manual modifications or adjustments. In some embodiments, the user can attach other files (engineering drawings, construction site photos, etc.) to the construction log.

[0121] In some embodiments, the construction log may be displayed on the display module in the form of a chart or the like.

[0122] In some embodiments, the processor may store the generated construction log in a storage device so that it can be traced back at any time.

[0123] In some embodiments, in response to obtaining user input information, the processor may generate a construction log based on the user input information and the construction site data.

[0124] User input information refers to information input by workers related to the actual situation of the construction site. In some embodiments, the user input information may include process progress. In some embodiments, the user input information may be uploaded to the processor in the form of voice input or the like.

[0125] In some embodiments, the processor may compare the process progress in the user input information with the process progress determined by the construction site data based on the user input information and the construction site data, and in response to the difference between the two not exceeding the difference threshold, the processor may fill the process progress in the user input information into a preset template to generate a construction log. The difference threshold may be preset.

[0126] Exemplarily, the process progress in the user input information is 65%, and the process progress determined by the construction site data is 60%. The difference between the two does not exceed the difference threshold of 10%. The processor can fill in the process progress 65% in the user input information into the preset template to generate a construction log.

[0127] In some embodiments, in response to the difference between the process progress in the user input information and the process progress determined by the construction site data exceeding the difference threshold, the processor can send an alarm message to the manager. The alarm message is information that reminds the manager that the user input information is inaccurate. For instructions on managers, see Figure 1 and its related description.

[0128] In some embodiments, workers can also use terminal devices to split the process to be performed into multiple sub-processes that can be used for phased acceptance, and upload the multiple sub-processes to the sensor module through the terminal device to update the latest process nodes. The process nodes can be used to characterize the progress of the process.

[0129] In some embodiments of the present specification, since the process progress reported by the workers at the construction site is more accurate, the process progress reported by the workers at the construction site is taken into consideration when generating the construction log, so that the construction log can reflect a more realistic process progress.

[0130] In some embodiments, the processor may send a construction log and a summary of the process segmentation progress to project-related users.

[0131] Project-related users refer to users associated with the construction project. In some embodiments, project-related users may include owners, project managers, and the like.

[0132] In some embodiments of the present specification, the construction log and the process segmentation progress summary are sent to project-related users, so that the project-related users can obtain the progress of the process in a timely manner, thereby guiding subsequent operations.

[0133] In some embodiments of the present specification, a progress estimate is determined based on the construction site conditions, and a progress estimate that accurately reflects the overall construction progress can be obtained; based on the construction site conditions and the progress estimate, a construction log is generated according to a preset template, and the progress of the construction process can be continuously monitored in a timely manner.

[0134] It should be noted that the above description of process 200 is only for illustration and description, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process hand-eye calibration under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0135] In some embodiments, the processor can determine whether there is an abnormal situation in the construction log based on the construction log; in response to the existence of an abnormal situation in the construction log, generate and send an early warning message to the supervisor.

[0136] In some embodiments, abnormal situations may include construction progress delays, dangerous events, abnormal attendance, equipment abnormalities, and unqualified quality.

[0137] Construction progress delay means that the overall construction progress lags behind the planned progress. The planned progress refers to the progress that the project is planned to complete within the working day. In some embodiments, the planned progress can be pre-set, including multiple working days and the planned completion progress corresponding to each working day. The working day refers to the number of days required to complete the process. For example, 5 days.

[0138] In some embodiments, the processor may extract the date and the progress estimate in the construction log, query the working day in the planned progress corresponding to the date in the construction log, and determine the progress of the planned completion corresponding to the aforementioned working day; in response to the difference between the planned completion progress corresponding to the working day and the progress estimate exceeding the progress threshold, the processor may determine that there is a construction progress delay in the construction log. The progress threshold may be preset.

[0139] Exemplarily, the date in the construction log is October 1st, the working day corresponding to the date in the construction log is the third day, the planned completion progress corresponding to the working day is 65%, and the estimated progress value is 50%. The difference between the two exceeds the progress threshold of 10%. The processor can determine that there is a construction progress delay in the construction log.

[0140] The occurrence of a dangerous event refers to the occurrence of a dangerous event at the construction site. For an explanation of the dangerous event, please refer to step 210 and its related description.

[0141] In some embodiments, in response to the presence of hazard indicators and event reports in the construction site data in the construction log, the processor may determine that a hazard event has occurred in the construction log.

[0142] Abnormal attendance refers to abnormal attendance of workers. In some embodiments, abnormal attendance may include low attendance rate of workers and / or absence of workers in important positions. Important positions may be obtained by user input.

[0143] In some embodiments, the processor may extract the attendance rate in the construction log, and in response to the attendance rate being lower than the attendance threshold, the processor may determine that there is an attendance anomaly in the construction log, wherein the attendance threshold may be preset.

[0144] In some embodiments, the processor may extract worker attendance data from the construction site data, traverse the attendance records of workers in important positions in the worker attendance data, and in response to not finding attendance records of workers in important positions in the worker attendance data, the processor may determine that there is an attendance anomaly in the construction log. The attendance record includes the time point when the worker enters the construction site and the time point when the worker leaves the construction site.

[0145] Equipment abnormality refers to a failure in the operation of the equipment. In some embodiments, equipment abnormality may include equipment failure, equipment stopping operation, and equipment not operating during the planned working time. The planned working time refers to the time when the equipment needs to work. In some embodiments, the planned working time can be preset.

[0146] In some embodiments, the processor can extract the equipment operating status in the construction site data. In response to the working time in the equipment operating status not being consistent with the planned working time, the processor can determine in the construction log that the equipment is not operating during the planned working time; in response to the operating speed in the equipment operating status being 0, the processor can determine in the construction log that the equipment has stopped operating; in response to the abnormal state in the equipment operating status being abnormal vibration of the equipment, the processor can determine that there is an equipment failure in the construction log.

[0147] Unqualified quality means that there are quality problems in the construction project, for example, the building structure does not meet safety standards, the construction quality is lower than the requirements, etc.

[0148] In some embodiments, since workers can monitor the quality of the construction project in real time, the user input information may also include quality problems existing in the construction project.

[0149] In some embodiments, in response to the construction log including quality issues existing in the construction project, the processor may determine that quality failure exists in the construction log.

[0150] In some embodiments, in response to an abnormality in the construction log, the processor may generate and send an early warning message to a supervisor.

[0151] The early warning information refers to information that notifies supervisors to handle abnormal situations in the construction log. In some embodiments, the early warning information may include abnormal situations and supervisors corresponding to the abnormal situations.

[0152] Supervisors refer to personnel who handle abnormal situations in the construction log. In some embodiments, supervisors may include project managers, equipment maintenance personnel, etc. In some embodiments, different abnormal situations have different supervisors corresponding to different abnormal situations. For example, the abnormal situation is a delay in the construction schedule, and the supervisor corresponding to the abnormal situation is the project manager. For another example, the abnormal situation is an equipment abnormality, and the supervisor corresponding to the abnormal situation is the equipment maintenance personnel. For another example, the abnormal situation is a dangerous incident, and the supervisor corresponding to the abnormal situation is the safety supervisor and / or the project manager. For another example, the abnormal situation is attendance abnormality, and the supervisor corresponding to the abnormal situation is the project manager and / or the human resources department. For another example, the abnormal situation is unqualified quality, and the supervisor corresponding to the abnormal situation is the quality manager and / or the project manager.

[0153] In some embodiments of the present specification, in response to abnormal situations in the construction log, an early warning message is generated and sent to the supervisor, so that the supervisor can be notified in time to deal with the abnormal situation in the construction log to avoid the negative impact of the abnormal situation on the construction project.

[0154] Figure 3 It is a schematic diagram of an exemplary process of determining and adjusting a task allocation scheme according to some embodiments of this specification.

[0155] In some embodiments, the processor can determine a task allocation plan 340 based on the worker's comprehensive score 310, team collaboration 320, and task decomposition rules 330; in response to the completion status of the subdivided task item not meeting the preset conditions, adjust the task priority corresponding to the subdivided task item, and adjust the workers corresponding to the subdivided task item based on the preset rules.

[0156] The comprehensive score 310 can reflect the worker's working ability. In some embodiments, the comprehensive score can be expressed by a numerical value or the like.

[0157] In some embodiments, the processor can determine the comprehensive score of the worker in a variety of ways. For example, the processor can extract multiple sets of working hours and efficiency of workers in historical data, calculate the average of the multiple sets of working hours and efficiency, and based on the average of the multiple sets of working hours and efficiency, query the reference score corresponding to the average of the multiple sets of working hours and efficiency in the score table, and determine the reference score as the comprehensive score of the worker. For more information about the working hours and efficiency of workers, please refer to Figure 2 and its related description.

[0158] In some embodiments, the scoring table may be pre-set, including multiple groups of working hours and efficiencies and reference scores corresponding to each group of working hours and efficiencies. The reference scores may be obtained by user input.

[0159] In some embodiments, the processor can determine the worker's comprehensive score through a score prediction model based on skill matching, historical performance, teamwork, health and safety scores, and experience level. Figure 4 and its related description.

[0160] Teamwork 320 can reflect the ability of a worker to cooperate with his coworkers. In some embodiments, teamwork can be expressed by a grade or the like, where the higher the grade, the higher the teamwork.

[0161] In some embodiments, the processor may obtain the teamwork of the workers from a storage device. The teamwork in the storage device may be obtained by input from a manager.

[0162] The task decomposition rule 330 refers to a rule for guiding the decomposition of work tasks. The work tasks refer to the tasks of the entire construction project.

[0163] In some embodiments, the task decomposition rules 330 may include task subdivision rules, worker allocation rules, and priority division rules.

[0164] The subdivision rules of the task can be used to guide the subdivision of the work task into multiple subdivision task items. Subdivision task items refer to subtasks obtained after subdividing the work task. For example, if the work task is to build a room, the subdivision task item can be concrete configuration. In some embodiments, the subdivision rules can be pre-set based on historical experience.

[0165] The worker allocation rules may be used to guide the determination of workers corresponding to the subdivided task items. In some embodiments, the worker allocation rules may be pre-set based on historical experience.

[0166] Prioritization rules can be used to guide the determination of task priorities for sub-task items. Task priority refers to the priority of executing a sub-task item. The higher the task priority, the higher the priority of executing the sub-task item. It is understandable that different sub-task items have different orders of precedence, so the task priorities of sub-task items are different.

[0167] In some embodiments, the task decomposition rules can be pre-set based on factors such as the type of work task, duration, technical difficulty, etc. For example, if the work task is to build a house, the task subdivision rule can be to subdivide the work task into multiple subdivided task items based on the standard steps of building a house, and the priority division rule can be that the subdivided task items corresponding to the steps that must be completed first in the construction steps have a higher task priority and / or the subdivided task items with shorter duration and higher technical difficulty have a higher task priority.

[0168] The worker allocation rule may be to allocate workers with higher comprehensive scores and team collaboration to sub-task items with higher priorities, and to allocate workers with lower comprehensive scores and team collaboration to sub-task items with lower priorities.

[0169] The task allocation scheme 340 refers to a scheme for dividing the subdivided task items into corresponding workers. In some embodiments, the task allocation scheme may include at least one subdivided task item and workers and task priorities corresponding to the subdivided task item. For example, the task allocation scheme may include subdivided task items 341-1, ..., subdivided task items 341-n, and workers and task priorities corresponding to each subdivided task item.

[0170] In some embodiments, the processor may decompose the work task into a plurality of sub-task items based on the comprehensive score 310 and team collaboration 320 of the workers and in accordance with the task decomposition rules, and determine the workers and task priorities corresponding to the sub-task items.

[0171] In some embodiments of the present specification, based on the comprehensive scores and team collaboration of the workers, the work tasks are decomposed into multiple sub-task items according to the task decomposition rules, and workers who are good at different fields are assigned to different sub-task items, which can improve the overall coordination efficiency of the work tasks.

[0172] In some embodiments, the processor may also determine the task priority corresponding to the subdivided task item based on the classification characteristics, time characteristics and material availability of the subdivided task item. For an explanation of the material availability, see Figure 2 and its related description.

[0173] Classification features can be used to characterize the process to which the subdivided task items belong.

[0174] The time feature can be used to characterize the time-related data of the subdivided task item. In some embodiments, the time feature may include the delivery time and the estimated completion time. The delivery time refers to the time point when the subdivided task item is delivered. The estimated completion time refers to the estimated time required to complete the subdivided task item.

[0175] In some embodiments, the processor may query the reference classification feature and reference time feature corresponding to the subdivided task item in the task feature table based on the subdivided task item, and determine the obtained reference classification feature and reference time feature as the classification feature and time feature of the subdivided task item. The task feature table may be pre-set, including multiple subdivided task items and corresponding reference classification features and reference time features. The reference classification feature and reference time feature may be determined by user input.

[0176] In some embodiments, the processor may determine the correspondence between the classification characteristics, time characteristics and material availability of the subdivided task items and the task priority, and determine the task priority of the subdivided task items based on the correspondence between the above three characteristics and the task priority. The correspondence may be preset, including the process sequence, time sequence and material availability sequence.

[0177] The process sequence refers to the order of different processes. The priority of multiple sub-task items corresponding to the earlier processes in the process sequence is greater than the priority of multiple sub-task items corresponding to the later processes in the process sequence. It is understandable that in the actual construction process, different processes have a fixed order of priority. For example, the foundation must be completed before construction can continue.

[0178] Time sequence refers to the order of different sub-task items in the same process based on time characteristics. The closer the current time point is to the delivery time and the shorter the estimated completion time is, the earlier the sub-task item is in the time sequence. The priority of the sub-task item at the front of the time sequence is higher than the priority of the sub-task item at the back of the time sequence.

[0179] The order of materials in place refers to the order of different sub-task items determined based on the material in place situation in the same process. The sub-task items with more materials in place and the shorter the time it takes for the materials to arrive at the corresponding construction area are ranked higher in the order of materials in place. The priority of the sub-task items at the front of the order of materials in place is higher than the priority of the sub-task items at the back of the order of time.

[0180] It is understandable that the more materials that arrive at the construction area, the shorter the time it takes for the materials to arrive at the corresponding construction area, and the less likely it is that the sub-task item cannot be carried out due to lack of materials. After the sub-task item is completed first, the material transportation resources can be allocated to the remaining sub-task items. Material transportation resources can include personnel and tools for transporting materials.

[0181] In some embodiments, the task priority can be expressed in the form of a sequence, etc. For example, the task priority can be expressed as [(preparation work for pouring concrete, October 1), ..., (concrete curing, October 20)], where preparation work for pouring concrete and concrete curing are subdivided task items, preparation work for pouring concrete is the subdivided task item with the highest task priority in the concrete pouring process, October 1 indicates the delivery time of preparation work for pouring concrete, concrete curing is the subdivided task item with the lowest task priority in the concrete pouring process, and October 20 indicates the delivery time of concrete curing.

[0182] In some embodiments of the present specification, based on the classification characteristics, time characteristics and material availability of the subdivided task items, a task priority that is more in line with the actual situation at the construction site can be determined to avoid delays in the construction period due to a disordered sequence of subdivided task items.

[0183] In some embodiments, in response to the completion status of the subdivided task item not satisfying a preset condition, the processor may adjust the task priority corresponding to the subdivided task item, and adjust the worker corresponding to the subdivided task item based on a preset rule.

[0184] Among them, the completion status of the subdivided task item may include the current progress of the subdivided task item and the time left to the delivery time. The preset condition means that the current progress of the subdivided task item is not less than the completion threshold and the time left to the delivery time is not less than the time threshold. Among them, the completion threshold and the time threshold can be preset. In some embodiments, the completion threshold and the time threshold corresponding to different subdivided task items may be different.

[0185] In some embodiments, in response to the completion status of the subdivided task item not satisfying a preset condition, the processor may adjust the task priority corresponding to the subdivided task item based on the current progress, delivery time, material supply status, and corresponding task priority of the subdivided task item.

[0186] The current progress refers to the degree to which the subdivided task item has been completed. In some embodiments, the process of determining the current progress of the subdivided task item is similar to the process of determining the process progress, and its implementation method can refer to the implementation method of the process progress determination process.

[0187] In some embodiments, the processor may determine the task priority of the subdivided task item through a preset adjustment rule based on the current progress, delivery time, material supply and corresponding task priority of the subdivided task item. The preset adjustment rule may be pre-set, including that the smaller the current progress of the subdivided task item, the closer the current time point is to the delivery time and the smaller the number of materials in place, the higher the task priority of the subdivided task item should be.

[0188] In some embodiments of the present specification, when adjusting the task priority of a subdivided task item, the current progress, delivery time, and material supply situation of the subdivided task item are taken into consideration, and the task priority of the subdivided task item can be adjusted in a timely manner to meet actual construction needs, and the task priority of more urgent subdivided task items can be increased.

[0189] In some embodiments, the processor can adjust the workers corresponding to the subdivided task items in a variety of ways. For example, the processor can adjust the workers corresponding to the subdivided task items through preset rules based on the workers' length of service and type of work. The preset rules can be pre-set, including selecting workers whose types of work are the same as those required for the subdivided task items, and assigning workers to subdivided task items with different task priorities according to their length of service. The longer the length of service, the higher the task priority of the assigned subdivided task items. The length of service and type of work of the workers can be obtained from the storage device.

[0190] In some embodiments, the processor may confirm the candidate workers based on the worker's skill matching and the current progress of the subdivided task item; and adjust the workers corresponding to the subdivided task item based on the candidate worker's comprehensive score 310 and team collaboration 320. For more information about the comprehensive score, team collaboration and the current progress of the subdivided task item, please refer to the above related description.

[0191] The skill matching degree can be used to characterize the evaluation result of the degree to which the worker has mastered the skills required for the process. In some embodiments, the evaluation result can include interview scores, training scores, etc.

[0192] In some embodiments, the skill matching degree of a worker may be represented by a feature matrix, where each row of the feature matrix represents a worker and each column represents an evaluation result of the degree to which the worker has mastered the skills required for a process.

[0193] In some embodiments, the processor may obtain the skill matching degree of the worker through a storage device.

[0194] Candidate workers are workers to be assigned subdivided task items.

[0195] In some embodiments, the processor may calculate the average of multiple evaluation results corresponding to each worker based on the worker's skill matching degree and the current progress of the subdivided task item, sort the aforementioned average values ​​to obtain a sorting result, and determine a preset number of workers in the sorting result that match the current progress of the subdivided task item as candidate workers according to a preset matching rule. The sorting result may include the ranking of the workers and the corresponding average values ​​of the multiple evaluation results. The preset number may be preset. For example, 10.

[0196] In some embodiments, the preset matching rules can be pre-set, including that the smaller the current progress of the subdivided task item, the higher the ranking of the preset number of workers matching the current progress of the subdivided task item in the sorting result. Exemplarily, if the current progress of the subdivided task item is 20% and the preset number is 10, the processor can select the 10 workers from the 1st to the 10th in the sorting result as candidate workers; if the current progress of the subdivided task item is 40% and the preset number is 10, the processor can select the 10 workers from the 10th to the 20th in the sorting result as candidate workers; if the current progress of the subdivided task item is 60% and the preset number is 10, the processor can select the 10 workers from the 20th to the 30th in the sorting result as candidate workers. It can be understood that the slower the progress of the subdivided task item, the more workers with higher skill matching are needed to complete it to avoid delaying the construction progress.

[0197] In some embodiments, the processor may determine the worker with the highest comprehensive score and / or the highest teamwork ability as the new worker corresponding to the subdivided task item based on the comprehensive scores and teamwork ability of the candidate workers.

[0198] In some embodiments of the present specification, candidate workers suitable for performing the subdivided task items can be determined based on the worker's skill matching and the current progress of the subdivided task items. Based on the comprehensive scores and team collaboration of the candidate workers, workers who perform the subdivided task items can be quickly determined to avoid delays in the construction period.

[0199] In some embodiments, in response to the completion status of the subdivided task item satisfying a preset condition, the task order of the worker corresponding to the subdivided task item is adjusted.

[0200] A task order is a record of the detailed task items that a worker needs to perform.

[0201] In some embodiments, in response to the completion of the subdivided task item meeting the preset conditions, the processor may adjust the task list of the worker corresponding to the subdivided task item, assign the remaining subdivided task items to the workers corresponding to the aforementioned subdivided task items based on the worker assignment rule, or add the workers corresponding to the aforementioned subdivided task items to the standby list. The standby list refers to a list of workers who have no tasks temporarily. It is understandable that the workers added to the standby list can wait to handle other sudden and urgent tasks.

[0202] In some embodiments of the present specification, in response to the completion status of a subdivided task item meeting a preset condition, the task list of the worker corresponding to the subdivided task item is adjusted, and the remaining tasks are assigned to the worker to avoid the worker having nothing to do and resulting in reduced income, or the worker is arranged to wait for processing other sudden emergency tasks to avoid the impact of unattended emergencies on construction.

[0203] In some embodiments of the present specification, based on the workers' comprehensive scores, team collaboration, and task decomposition rules, a suitable task allocation plan can be quickly determined. In response to the completion status of a subdivided task item not meeting preset conditions, the task priority corresponding to the subdivided task item can be adjusted in a timely manner, and workers who are more suitable to complete the subdivided task item can be determined based on preset rules.

[0204] Figure 4 is an exemplary schematic diagram of a score prediction model according to some embodiments of the present specification.

[0205] In some embodiments, the processor can determine the worker's comprehensive score 310 through a score prediction model 450 based on skill matching 410, historical performance 420, teamwork 320, health and safety score 430, and experience level 440. For more information about skill matching and teamwork, see Figure 3 and its related description.

[0206] Historical performance 420 refers to the performance indicators of the worker in historical time. In some embodiments, the performance indicators may include quality scores, speed scores, etc. Among them, the quality score can be used to characterize the quality of the subdivided task items completed by the worker. The higher the quality score, the higher the quality of the subdivided task items completed. The speed score can be used to characterize the working speed of the worker. The higher the speed score, the faster the working speed of the worker.

[0207] In some embodiments, historical performance may be represented by a feature matrix, where each row of the feature matrix represents a worker and each column represents a performance indicator.

[0208] In some embodiments, the processor may obtain the worker's historical performance through a storage device.

[0209] The health and safety score 430 may be used to characterize the health status of workers.

[0210] In some embodiments, the processor may obtain the health and safety score of the worker through a storage device.

[0211] The experience level 440 may be used to characterize how much work experience a worker has.

[0212] In some embodiments, the processor may obtain the worker's experience level from a storage device.

[0213] The rating prediction model 450 refers to a model used to determine a comprehensive rating of a worker.

[0214] In some embodiments, the score prediction model 450 may include a linear regression model. The linear regression model may reflect the linear relationship between skill matching, historical performance, teamwork, health and safety score, and experience level and the comprehensive score, including independent variables, target variables, and parameters of the independent variables. The independent variables may include skill matching, historical performance, teamwork, health and safety score, and experience level, and the target variable may include the comprehensive score.

[0215] In some embodiments, the processor may use the third training sample with the third label as an independent variable and the third label as a target variable, obtain the parameters of the respective variables in the initial linear regression model by linear fitting or the like, and update the parameters of the independent variables in the initial linear regression model based on the test set, evaluate the initial linear regression model by indicators such as the root mean square error, and complete the training of the score prediction model when the root mean square error meets the preset conditions. The preset conditions may include that the root mean square error is less than an error threshold. The error threshold may be preset.

[0216] The third training sample may include the sample worker's sample skill matching, sample historical performance, sample teamwork, sample health and safety score, and sample experience level, and the third label of the third training sample may be the actual comprehensive score of the sample worker. In some embodiments, the third training sample may be obtained based on historical data, and the third label may be determined based on manual annotation. The feature matrix representing the sample skill matching may be connected to the matrix representing the sample historical performance into a new matrix, and then the new matrix is ​​used to train the linear regression model.

[0217] In some embodiments, the processor may calculate the actual comprehensive score of the sample worker through a preset scoring algorithm based on the sample skill matching, sample historical performance, sample teamwork, sample health and safety score, and sample experience level of the sample worker. The preset scoring algorithm may be preset, including weighted integration of skill matching, historical performance, teamwork, health and safety score, and experience level to obtain a comprehensive score.

[0218] In some embodiments, in the process of weighted integration of skill matching, historical performance, teamwork, health and safety score, and experience level, the weights of the five factors may be related to the degree of influence of the five factors on the comprehensive score. The higher the degree of influence, the greater the weight. For example, the skill matching of a worker has the greatest influence on the comprehensive score, so the skill matching has the greatest weight.

[0219] The test set may include the skill matching, historical performance, teamwork, health and safety score, and experience level of the worker to be tested. In some embodiments, the processor may divide the historical data into a training set and a test set based on a preset ratio. The training set includes a plurality of third training samples with a third label. The preset ratio may be pre-set. For example, 70% of the historical data is used as a training set and 30% of the historical data is used as a test set.

[0220] In some embodiments of the present specification, the score prediction model includes a linear regression model, which can obtain an intuitive and clear relationship between skill matching, historical performance, teamwork, health and safety score, and experience level and the comprehensive score, thereby determining a more accurate comprehensive score.

[0221] In some embodiments, the score prediction model 450 may include a machine learning model. For example, the score prediction model may include any one or combination of a convolutional neural network (CNN) model, a neural network (NN) model, or other custom model structures.

[0222] In some embodiments, the inputs to the score prediction model may include skill matching, historical performance, teamwork, health and safety score, and experience level, and the output may include a comprehensive score 310 .

[0223] In some embodiments, the processor may input multiple third training samples with third labels into the initial rating prediction model, construct a loss function through the third labels and the prediction results of the initial rating prediction model, iteratively update the initial rating prediction model based on the loss function through methods such as gradient descent, and complete the rating prediction model training when the loss function of the initial rating prediction model meets preset conditions, wherein the preset conditions may be that the loss function converges, the number of iterations reaches a set value, etc.

[0224] In some embodiments of the present specification, the scoring prediction model includes a machine learning model, which processes skill matching, historical performance, teamwork, health and safety scores, and experience levels through the machine learning model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of data, obtain the correlation between skill matching, historical performance, teamwork, health and safety scores, and experience levels and the comprehensive score, and improve the accuracy and efficiency of determining the comprehensive score.

[0225] In some embodiments, the processor may update the rating prediction model 450 based on the skill match 410 and the recent performance 460 .

[0226] Recent performance 460 refers to the worker's recent performance indicators. In some embodiments, the processor can obtain the worker's recent performance through a storage device. The recent time range can be preset. For example, within 1 month.

[0227] In some embodiments, the processor may replace the historical performance in the third training sample with the third label with the recent performance, and calculate the new comprehensive score of the sample worker as the new third label through a preset scoring algorithm; use the third training sample with the new third label as the independent variable, and the new third label as the target variable, re-determine the parameters of the respective variables in the linear regression model through linear fitting and other methods, and update the parameters of the independent variables in the linear regression model based on the test set, evaluate the initial linear regression model through indicators such as the root mean square error, and complete the training of the scoring prediction model when the root mean square error meets the preset conditions. In the process of updating the parameters of the independent variables in the linear regression model based on the test set, the processor may replace the historical performance of the worker used for testing in the test set with the recent performance of the worker.

[0228] In some embodiments of the present specification, by updating the rating prediction model based on skill matching and recent performance, a more realistic rating prediction model can be obtained, thereby obtaining a comprehensive rating of the worker more quickly.

[0229] In some embodiments, the processor may update the worker's comprehensive score 310 based on a preset period, wherein the preset period may be preset, for example, 1 week.

[0230] In some embodiments, the processor may transmit the worker's updated comprehensive score to a storage device to replace the original comprehensive score, so as to update the worker's comprehensive score.

[0231] In some embodiments of the present specification, by updating the comprehensive scores of workers based on a preset period, a more accurate comprehensive score can be obtained, which is in turn conducive to determining a more appropriate task allocation plan.

[0232] In some embodiments of the present specification, a comprehensive score of a worker is determined through a scoring prediction model based on skill matching, historical performance, teamwork, health and safety score, and experience level, which can save the process of scoring the workers and avoid inaccurate comprehensive scores due to the subjectivity of manual scoring.

[0233] Some embodiments of the present specification also provide a progress and quality implementation monitoring device for a construction site, comprising at least one processor and at least one memory, the memory being used to store computer instructions, and the processor being used to execute at least part of the computer instructions to implement any of the progress and quality implementation monitoring methods for a construction site described in the above embodiments.

[0234] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes any of the above-mentioned embodiments for the method of monitoring the progress and quality of the construction site.

[0235] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0236] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0237] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A method for monitoring the progress and quality of a construction site, characterized in that: The method is executed by a processor, and the method includes: Determine the construction site conditions based on the construction site data, wherein the construction site conditions include at least one of a degree of structural completion, a process progress, a material availability rate, and a worker attendance rate; Based on the structural completion degree, the process progress, the material availability rate and the worker attendance rate, a progress estimate is determined by a decision tree algorithm, and the progress estimate is used to reflect the overall progress of the construction project; wherein, The decision tree algorithm includes a parent node, a child node, a leaf node, and a reference progress estimation value corresponding to the leaf node. The parent node is the parent node of the child node, the leaf node is the child node at the bottom of the decision tree, and each leaf node corresponds to a reference progress estimation value. Based on the construction site conditions and the progress estimate, a construction log is generated according to a preset template, wherein the preset template includes a process segmentation progress summary, wherein the process segmentation progress summary is used to reflect the process segmentation progress, wherein the process segmentation progress refers to the process progress after the process is segmented according to a segmentation standard, wherein the segmentation standard refers to the standard for dividing the progress of the process into different intervals.

2. The method according to claim 1, characterized in that The construction site data includes sensor data and image data of the construction site, and the method further includes: Acquiring the sensing data through a sensing module; The image data is obtained through drone inspection.

3. The method according to claim 2, characterized in that The method further comprises: Based on the image data, the structural completion is determined by a structural prediction model, and the structural prediction model is a machine learning model.

4. The method according to claim 1, characterized in that The construction site conditions also include at least one of environmental parameters, hazard indicators and event reports.

5. The method according to claim 1, characterized in that The method further comprises: Determine a task allocation plan based on the comprehensive scores of the workers, team collaboration, and task decomposition rules, wherein the task allocation plan includes at least one subdivided task item and the workers and task priorities corresponding to the subdivided task item; In response to the completion status of the subdivided task item not satisfying a preset condition, the task priority corresponding to the subdivided task item is adjusted, and the worker corresponding to the subdivided task item is adjusted based on a preset rule.

6. The method according to claim 5, characterized in that The method further comprises: The worker's comprehensive score is determined by a score prediction model based on skill matching, historical performance, teamwork, health and safety scores, and experience level.

7. The method according to claim 6, characterized in that The method further comprises: The rating prediction model is updated based on the skill matching and recent performance.

8. The method according to claim 1, characterized in that The method further comprises: In response to obtaining user input information, the construction log is generated based on the user input information and the construction site data.

9. The method according to claim 1, characterized in that The method further comprises: Based on the construction log, determining whether there is an abnormality in the construction log; In response to an abnormality in the construction log, an early warning message is generated and sent to a supervisor.

10. A progress and quality monitoring system for a construction site, characterized in that: The system includes a processing module, a sensor module, and a display module. The sensor module is arranged at a construction site, and the processing module is configured as follows: Determine the construction site conditions based on the construction site data, wherein the construction site conditions include at least one of a degree of structural completion, a process progress, a material availability rate, and a worker attendance rate; Based on the structural completion degree, the process progress, the material availability rate and the worker attendance rate, a progress estimate is determined by a decision tree algorithm, and the progress estimate is used to reflect the overall progress of the construction project; wherein, The decision tree algorithm includes a parent node, a child node, a leaf node, and a reference progress estimation value corresponding to the leaf node. The parent node is the parent node of the child node, the leaf node is the child node at the bottom of the decision tree, and each leaf node corresponds to a reference progress estimation value. Based on the construction site conditions and the progress estimate, a construction log is generated according to a preset template, wherein the preset template includes a process segmentation progress summary, wherein the process segmentation progress summary is used to reflect the process segmentation progress, wherein the process segmentation progress refers to the process progress after the process is segmented according to a segmentation standard, wherein the segmentation standard refers to the standard for dividing the progress of the process into different intervals.

11. A progress and quality monitoring device for a construction site, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the progress and quality implementation monitoring method for a construction site as described in any one of claims 1 to 9.

12. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the progress and quality implementation monitoring method for a construction site as described in any one of claims 1 to 9.

Images