Building engineering intelligent management and control method and system based on big data

Abstract

The embodiment of the invention relates to the technical field of information, in particular to a building engineering intelligent management and control method and system based on big data. The method comprises the following steps: reading a construction project set and construction resource description of a building; periodically receiving the current construction project, the obtained construction resource information, the weather information and the inspection video of the unmanned aerial vehicle; analyzing the inspection video, and respectively obtaining the construction progress and the construction defect according to the construction content and the detection item; correcting the construction resource description according to the obtained construction resource information, construction progress and construction defects; according to the corrected construction resource description, generating a progress description item and a quality inspection warning description item of the current construction project; reading an unstarted construction project, and generating a prompt item according to the corrected construction resource description and weather information; generating a plurality of backlogs according to the progress description item, the quality inspection warning description item and the prompt item; and displaying the backlog.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the field of information technology, in particular to a big data-based intelligent management and control method and system for construction projects. BACKGROUND

[0002] The management of large construction projects is of great significance to improving construction efficiency and ensuring construction quality. Especially in the middle and later stages of the project, after the main body of the high-rise building is capped, multiple professional projects such as foundation, structure, electromechanical, curtain wall, road, and greening are promoted in parallel, the construction process is frequently crossed, the resource allocation demand dynamically changes, and the management complexity significantly increases. At this time, it is difficult to fully grasp the site status by relying on the experience of the project manager, and it is easy to cause delay in the construction period, waste of resources, or quality problems. In recent years, unmanned aerial vehicle inspection, Internet of Things sensing, and big data technology have been gradually applied in the construction field, and data collection of the construction process has been realized. However, the existing systems mostly stay at the level of "data display" and lack deep analysis capabilities. Therefore, there is an urgent need for a management and control technology that can improve the fine and intelligent management of construction projects. SUMMARY

[0003] Embodiments of the present specification describe a big data-based intelligent management and control method and system for construction projects.

[0004] In a first aspect, the embodiments of the present specification provide a big data-based intelligent management and control method for construction projects, comprising the steps of:

[0005] reading a construction project set and a construction resource description, the construction project set recording the project name, construction content, pre-constraint, and quality inspection item of all construction projects, and the construction resource description recording the obtainable construction resources and resource description in natural language;

[0006] periodically receiving current construction projects, obtained construction resource information, weather information, and unmanned aerial vehicle inspection videos;

[0007] analyzing the inspection videos, and obtaining construction progress and construction defects according to the construction content and detection items, respectively;

[0008] correcting the construction resource description according to the obtained construction resource information, construction progress, and construction defects;

[0009] generating progress description items and quality inspection warning description items of the current ongoing construction projects according to the corrected construction resource description;

[0010] reading a non-started construction project, and generating a prompt item according to the corrected construction resource description and weather information;

[0011] According to the progress description item, the quality inspection warning description item and the prompt item, a plurality of affairs are generated, and the affairs record affair types, affair states and affair descriptions;

[0012] The affairs are displayed, and information of the progress description item, the quality inspection warning description item or the prompt item on which the affairs are based is displayed based on user interaction operations.

[0013] In a second aspect, the embodiments of the present specification provide a building engineering intelligent management and control system based on big data, comprising:

[0014] A reading module reads a construction project set and a construction resource description of a building, wherein the construction project set records project names, construction contents, preconditions and quality inspection items of all construction projects, and the construction resource description records obtainable construction resources and resource descriptions in natural language;

[0015] A receiving module periodically receives current construction projects, obtained construction resource information, weather information and inspection videos of unmanned aerial vehicles;

[0016] An analysis module analyzes the inspection videos, and obtains construction progress and construction defects according to the construction contents and the inspection items;

[0017] A correction module corrects the construction resource description according to the obtained construction resource information, the construction progress and the construction defects;

[0018] A first generation module generates progress description items and quality inspection warning description items of the current construction projects in progress according to the corrected construction resource description;

[0019] A second generation module reads unstarted construction projects, and generates prompt items according to the corrected construction resource description and the weather information;

[0020] An affair module generates a plurality of affairs according to the progress description items, the quality inspection warning description items and the prompt items, and the affairs record affair types, affair states and affair descriptions;

[0021] A display module displays the affairs, and displays information of the progress description items, the quality inspection warning description items or the prompt items on which the affairs are based based on user interaction operations.

[0022] In a third aspect, the embodiments of the present specification provide an electronic device, comprising a processor and a memory;

[0023] The processor is connected with the memory;

[0024] The memory is used for storing executable program codes;

[0025] The processor runs a program corresponding to executable program code stored in the memory by reading the executable program code, to execute the method of any of the preceding aspects.

[0026] In a fourth aspect, the embodiments of the present specification provide a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method of any of the preceding aspects.

[0027] The technical solutions provided by some embodiments of the present specification have at least the following beneficial effects:

[0028] In the embodiments of the present specification, the building engineering intelligent management and control method and system based on big data are provided, which realizes the identification of construction progress and quality defects by periodically receiving unmanned aerial vehicle inspection videos and combining automatic analysis of construction content and quality inspection items, improves the site supervision efficiency and accuracy, and reduces the risk of human misjudgment. According to the real-time acquisition of resource information, construction progress and defect data, the construction resources and resource descriptions described in natural language are dynamically corrected, so that the subsequent acquisition of construction resources has more accurate estimation, which helps to ensure the sufficiency of construction resources. The progress description items and quality inspection warning items are generated for the construction project, and the prompt items are generated for the non-started project in combination with the resource and weather information, the early warning information with decision support value is output, and the construction process and construction resource allocation are arranged for the on-duty management personnel.

[0029] Other features and advantages of the embodiments of the present specification will be further disclosed in the following specific embodiments and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present specification, the drawings required to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0031] Figure 1 The building engineering intelligent management and control schematic diagram provided by the embodiments of the present specification.

[0032] Figure 2 The building engineering intelligent management and control method flowchart provided by the embodiments of the present specification.

[0033] Figure 3 The progress description item generation schematic diagram provided by the embodiments of the present specification.

[0034] Figure 4 The business item display schematic diagram provided by the embodiments of the present specification.

[0035] Figure 5 The building engineering intelligent management and control system schematic diagram provided for the embodiment of the present specification.

[0036] Figure 6 The electronic device schematic diagram provided for the embodiment of the present specification. DETAILED DESCRIPTION

[0037] The technical solutions of the embodiments of the present specification are explained and described below in combination with the drawings of the embodiments of the present specification. The following embodiments are only preferred embodiments of the present specification, and not all. Based on the embodiments in the embodiments, other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present specification.

[0038] The terms "first", "second", "third" and the like in the specification and claims of the present specification and the above drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0039] In the following description, the appearance of terms such as "inner", "outer", "upper", "lower", "left", "right" and the like indicates the orientation or positional relationship only for the convenience of describing the embodiments and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present specification.

[0040] The data involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data comply with relevant national and regional laws, regulations and standards.

[0041] Before introducing the technical solutions recorded in the present specification, the application scenarios and related technologies of the technical solutions are introduced.

[0042] With the increasing scale of construction projects, the increasing complexity of structures, and the increasing requirements for construction period and quality, the current management mode has been difficult to meet the demand. Especially in large complexes, high-rise buildings or infrastructure projects, the construction process involves multi-party cooperation, multi-trade cross operation, a large number of resource scheduling and dynamic environmental changes, and the management complexity increases significantly. Unreasonable resource allocation, opaque progress monitoring, and untimely discovery of quality problems often occur, which can easily lead to delays, cost overruns, and even safety accidents. With the development of big data technology, intelligent management and control of construction engineering has emerged as the times require, and has become a new direction for promoting intelligent management and control of the construction industry. Intelligent management and control refers to the integration of Internet of Things, big data analysis, artificial intelligence, unmanned aerial vehicle inspection, BIM (Building Information Modeling) technology, to build a comprehensive system that integrates data collection, state perception, intelligent analysis, decision support and task execution.

[0043] The present specification provides a big data-based intelligent management and control method and system for construction engineering, please refer to the attached Figure 1 By automatically collecting site images through devices such as unmanned aerial vehicles and cameras, and combining AI algorithms to identify construction progress, the progress can be visualized and quantitatively managed, avoiding subjective judgment bias. Based on inspection videos 34 and quality inspection knowledge graphs, construction defects 36 such as cracks, misplacement and missing reinforcement can be automatically identified, quality problems can be discovered in advance, and the risk of rework can be reduced. By considering factors such as weather, pre-process, and resource availability, the system reads unstarted construction projects 21, generates prompt items 22 based on the corrected construction resource description 12 and weather information 31, and assists in scientific decision-making. This helps to shorten the construction period, reduce the overall cost, improve the quality and safety level of the project, and at the same time accumulate data assets for construction enterprises.

[0044] Specifically, the present specification first provides a big data-based intelligent management and control method for construction engineering, please refer to the attached Figure 2 , comprising the steps of:

[0045] Step S1) reading the construction project set 11 and the construction resource description 12 of the building, the construction project set 11 recording the project name, construction content, pre-constraint and quality inspection item of all construction projects, and the construction resource description 12 recording the available construction resources and resource description in natural language.

[0046] The construction project set 11 is the core structured data of project management, which contains the collection of all to-be-executed construction tasks in the construction project. The set records the static attributes of each construction project in a structured manner, and the project name is used to uniquely identify a construction task. The construction content describes the specific scope of work, process requirements and technical standards of the task in detail. The pre-requisite constraint is used to define other construction tasks that must be completed before the task starts, forming a logical dependency relationship between tasks and constituting the project schedule network. The quality inspection item lists the specific items, detection standards and acceptance basis that need to be checked after or during the completion of the construction task. These information collectively constitute the basic information of engineering schedule plan and quality management, providing comparison reference for subsequent progress tracking, construction defect 36 identification and early warning. For example, the project name of a construction project is foundation concrete pouring. The construction content is to pour C35 strength grade concrete in the foundation pit where the steel bar binding and formwork setting have been completed, with a pouring thickness of 1.2 meters and a need for vibration compaction. The pre-requisite constraint is that it must be started after “foundation pit support is completed” and “steel bar binding acceptance is passed”. The quality inspection item is concrete slump test, pouring compactness inspection, curing temperature record and 28-day compressive strength test.

[0047] The construction resource description 12 is used to record various types of resources and their dynamic characteristics relied on by project execution. The construction resource description 12 is recorded in natural language form, which has better expression ability for complex and non-standardized resource information. The construction resource description 12 covers all types of construction resources that can be obtained, mainly including human resources (such as the number of construction personnel, skill level, team configuration, etc.), material resources (such as the types, specifications, technical parameters of building materials and components), mechanical equipment, financial arrangements and other auxiliary resources. The resource description not only records the existence of resources, but also contains qualitative or semi-quantitative characterization of resource attributes, such as resource acquisition approach (purchase, lease, internal allocation, etc.), timeliness expectation, use efficiency evaluation, historical quality performance, etc. This rich contextual information carried in natural language enables the system to more flexibly understand the resource state in subsequent processing, and supports semantic-based reasoning and correction.

[0048] For example, the resource description of a concrete pouring team includes: "The reinforcement team consists of 15 workers, 6 of whom hold senior reinforcement worker certificates. The average daily completion of binding in the past three months is 8 tons, and the team leader has 5 years of high-rise construction experience. In recent days, 2 workers have taken leave due to holidays, and 1 new worker has been temporarily supplemented, requiring on-site training." Material description: "The maximum daily supply of C35 concrete is 300 cubic meters, and the transport fleet usually arrives within 2 hours after reservation. Due to the recent rise in raw material prices, the supplier has warned of the risk of short-term material shortage. The insulation board inventory is sufficient, but the new batch of products has not yet undergone fireproof re-inspection." Acquisition approach description: "The concrete pouring team is dispatched on-site through an annual labor cooperation agreement, and the team members are uniformly allocated by the company's human resources department. The team members are all company contract workers, and the daily management is jointly responsible by the project department and the labor company. If additional personnel are needed, a written application must be submitted to the labor company 3 days in advance, and 2-3 auxiliary workers with equivalent qualifications can usually be arranged within 48 hours." Timeliness description: "Reinforcement materials usually arrive half a day ahead of schedule, but there was a 36-hour delay last month due to traffic control. The concrete supply has a 92% on-time rate in the past two months." Efficiency description: "The concrete pouring team can complete an average of 40 cubic meters of pouring per hour under continuous operation conditions, but the efficiency decreases by about 15% at night." Quality description: "The reinforcement binding of this reinforcement team has a 96% pass rate in the past three projects, with the main problem being the omission of protection layer pads. The insulation board sticking process has not occurred again after rectification due to worker operation irregularities that caused local hollowing in the previous project."

[0049] Step S2) periodically receive current construction project 32, acquired construction resource information 33, weather information 31, and unmanned aerial vehicle inspection video 34.

[0050] The current construction project 32 information is provided by the project management system or the on-site dispatching record. The acquired construction resource information 33 includes the actual on-site construction personnel list and qualifications, the types and quantities of materials, the operation status of mechanical equipment, etc. The acquired construction resource information 33 reflects the deviation between the resource plan and the actual execution, which is the key basis for verifying and correcting the initial construction resource description 12.

[0051] Weather conditions (such as temperature, humidity, precipitation, wind, visibility, etc.) directly affect the feasibility of outdoor work, the selection of construction technology, material performance, and safety risks. By receiving weather information 31, potential interference of weather on current and future construction activities can be predicted, providing environmental basis for construction scheduling and risk warning. The reception of inspection video 34 of the unmanned aerial vehicle constitutes the system's non-contact, wide-area coverage perception of the physical state of the construction site. The video data collected by the regular flight of the unmanned aerial vehicle provides high spatio-temporal resolution visual information of the construction site, covering areas that are difficult to reach or inefficient for manual inspection. Inspection video 34 is the direct visual evidence source for subsequent analysis of construction progress 35 and identification of construction defects 36.

[0052] Step S3) Analyzing the inspection video 34, according to the construction content and detection items, respectively obtaining the construction progress 35 and the construction defects 36.

[0053] The method for analyzing the inspection video 34 to obtain the construction progress 35 according to the construction content includes:

[0054] Reading the sequence of frame images of the inspection video 34, identifying the construction area in the frame images, and generating an identified object description of the construction area according to the objects identified in the construction area and the state of the objects;

[0055] Comparing the identified description with the corresponding construction content to identify the current construction task and the construction task progress of the construction area;

[0056] According to the current construction task and the construction task progress, the construction progress 35 of the current construction project 32 is obtained;

[0057] According to the construction progress 35 obtained from the inspection video 34 obtained in the continuous multiple periods, the construction progress 35 trend is obtained, and the lag or lead state of the construction progress 35 is marked according to the construction progress 35 trend.

[0058] By analyzing the unmanned aerial vehicle inspection video 34, combined with the preset construction project information, the current construction progress 35 and construction defects 36 are automatically inferred. The continuous video stream is decomposed into a sequence of time-ordered image frames, and image segmentation or object detection technology is used to locate the part of the picture that belongs to the construction activity area (such as foundation pit, work surface, structural layer, etc.), excluding irrelevant background (such as road, vegetation, surrounding buildings, etc.). Through the target recognition algorithm, the key entity objects (such as reinforcement cage, formwork, concrete pouring surface, tower crane, construction machinery, etc.) existing in the construction area are detected, and the physical state of these objects (such as whether it exists, whether it is complete, whether it is in working state, spatial position relationship, etc.) is further analyzed. The identification results are structured or semi-structured as "identified object description" to digitally express the physical composition and working state of the current construction site.

[0059] When comparing the description of the identified object with the corresponding construction content, the current construction content of construction project 32 is used as a benchmark. Through semantic or logical matching, it is determined which preset construction task stage (e.g., rebar tying, formwork erection completed, concrete initial setting, etc.) the currently identified object and its state conform to. This determines the actual construction task node of the construction area and further quantifies the completion ratio of the task to form the construction task progress. For example, the inspection video 34 identifies the construction area as a three-story slab working surface. The identified object description is: rebar mesh has been laid, formwork erection is complete, concrete pump truck is operating, and approximately 25% of the area has been poured with concrete and initially smoothed. After comparing the construction content, it is determined that the current construction task is "concrete pouring," and the construction task progress is 25%. Through multi-period continuous analysis, the trend of construction progress 35 is obtained. The trend of construction progress 35 is analyzed to determine whether the current construction progress 35 is lagging, normal, or ahead of the planned progress, and is marked accordingly. Trend analysis overcomes the limitations of single-point observation and enhances the ability to predict construction efficiency and potential delay risks.

[0060] For example, the identification markers for the second day are described as follows: approximately 55% of the area has been poured, and concrete is being delivered to the remaining areas, with a construction progress of 55%. The identification markers for the third day are described as follows: approximately 70% of the area has been poured, with the pouring speed slowing down compared to the previous two days, and some areas suspended due to equipment failure, with a construction progress of 70%. Progress trend analysis: 60% should have been completed in the first three days, but 70% was actually completed, indicating that the progress is ahead of schedule.

[0061] Day 4: Item completion rate 80%, pouring progress continues to slow. Construction task progress 80%. Progress trend analysis: 80% should have been completed on day 4, actual completion is 80%, progress has changed from "ahead of schedule" to "normal". Day 5: Item completion rate 90%, construction in the remaining areas is suspended due to weather. Construction task progress 90%. Progress trend analysis: 100% should have been completed on day 5, actual completion is 90%, progress has fallen behind schedule.

[0062] The method for analyzing the inspection video 34 and obtaining the construction defect 36 based on the inspection items includes:

[0063] Based on the quality inspection items of all construction projects, a knowledge graph of 36 construction defects is constructed. The knowledge graph of 36 construction defects includes defect types, defect visual features, associated construction procedures, and severity level markings.

[0064] Read the sequence of frame images from inspection video 34, input the frame images into a pre-accessed target matching model, and the output of the target matching model is whether there are defect visual features that match the input.

[0065] According to the output of the target matching model, a candidate defect is generated;

[0066] The candidate defect is semantically compared with the quality inspection item of the current construction project, and the candidate defect that does not conform to the semantics is removed;

[0067] According to the remaining candidate defects, a construction defect 36 is generated, which records the defect type, the associated construction process and the severity level mark.

[0068] The construction defect 36 knowledge graph includes defect type, defect visual feature, associated construction process and severity level mark. Among them, the defect type (such as honeycomb, pitted surface, exposed steel bar, etc.), which is used for classification of defects; the defect visual feature (such as color abnormal area, texture discontinuity, geometric shape deviation, etc.), which expresses the typical image of each defect in the form of computer-recognizable visual description; the associated construction process, which establishes the mapping relationship between the defect and the specific construction task, ensures the context rationality of defect identification; and the severity level mark (such as slight, general, severe), which is used to quantify the impact of the defect.

[0069] The frame image sequence of the inspection video 34 is read and input into the pre-trained target matching model. The target matching model is usually based on a deep convolutional neural network architecture and is trained with a large number of labeled defect images, and has recognition ability. The model receives video frames as input, and the output is whether there is an image area matching the "defect visual feature" defined in the knowledge graph.

[0070] According to the output of the target matching model, a candidate defect is generated, that is, the system converts the matching results detected by the model into structured candidate entries. The semantic comparison of the candidate defect with the quality inspection item of the current construction project 32 is a key step to realize context filtering. According to the current construction project 32 and its corresponding quality inspection item, it is analyzed whether the construction process associated with the candidate defect is consistent with the current actual construction task. For example, if a "honeycomb" defect is detected in an area where concrete pouring has not been performed, the candidate defect is not semantically valid and should be removed. The final construction defect 36 record is generated according to the candidate defects that pass the semantic comparison.

[0071] For example, in the identification of concrete surface honeycomb defects, the construction of the knowledge graph is performed first. Specifically, in the construction defect 36 knowledge graph, "honeycomb" is defined as a concrete pouring defect, its defect type is "surface defect", its visual feature is "there are irregular and dense hole groups on the concrete surface, the color is lighter, and they are mostly distributed at the corners of the component", the associated construction process is "concrete pouring and vibration", and the severity level mark is "general" (if the area is small) or "severe" (if the depth is large and the area is wide).

[0072] Video analysis and model matching. The UAV inspection video 34 captures the concrete surface of the two-layer beam being maintained. The video frame is input into the target matching model, which identifies the region in the image that matches the visual feature of "dense hole group". Then a candidate defect is generated, "suspected honeycomb, located on the side of the two-layer beam, confidence 85%". Semantic comparison. The current construction project 32 is "two-layer beam concrete maintenance", and its quality inspection items include "no honeycomb, pitted surface and other defects on the concrete surface". The "honeycomb" type of the candidate defect matches the quality inspection item, and the associated process "concrete pouring" is the prerequisite for the current task, and the semantics are consistent. The construction defect 36 is generated, and the defect is confirmed to be valid, and the construction defect 36 record is generated. The construction defect 36 record includes defect type: honeycomb, associated construction process: concrete pouring, severity level: general, location: side of two-layer beam.

[0073] Step S4) Correct the construction resource description 12 according to the obtained construction resource information 33, construction progress 35 and construction defect 36.

[0074] The resource description includes construction personnel description, material description, acquisition path description, on-site timeliness description, efficiency description and quality description;

[0075] The method for correcting the construction resource description 12 according to the obtained construction resource information 33, construction progress 35 and construction defect 36 includes:

[0076] Read the construction personnel information, material information, acquisition path information and on-site timeliness information of the obtained construction resource information 33, and compare the construction personnel information, material information, acquisition path information and on-site timeliness information with the construction personnel description, material description, acquisition path description and on-site timeliness description, respectively;

[0077] When the matching degree of the comparison is lower than the preset threshold, the construction personnel description, material description, acquisition path description and on-site timeliness description are corrected according to the construction personnel information, acquisition path information and on-site timeliness information of the obtained construction resource information 33, respectively;

[0078] Obtain the reference construction duration of the construction project according to the construction content, obtain the estimated construction duration according to the construction progress 35, and correct the efficiency description according to the reference construction duration and the estimated construction duration;

[0079] Generate an estimated construction defect 36 description according to the construction content and the quality description, compare the construction defect 36 with the estimated construction defect 36 description, and if the matching degree of the construction defect 36 and the estimated construction defect 36 description is lower than the preset threshold, then the quality description is corrected according to the construction defect 36.

[0080] The multi-source data collected in the actual construction process, including the obtained construction resource information 33, the construction progress 35, and the construction defects 36, is used to continuously correct the construction resource description 12, thereby improving the accuracy and timeliness of the system's cognition of the resource state. The correction process covers the six dimensions of the construction resource description 12, which are the construction personnel description, the material description, the acquisition path description, the arrival and timeliness description, the efficiency description, and the quality description.

[0081] For the construction personnel, material, acquisition path, and arrival and timeliness descriptions, the correction is performed through a structured information comparison mechanism. The obtained construction resource information 33 actually collected is read, and the construction personnel configuration, material arrival situation, actual execution path of the resource acquisition channel, and actual arrival time of the resource are extracted, and a matching degree calculation is performed with the corresponding items in the initial resource description. The matching degree can be measured based on semantic similarity, numerical deviation rate, or logical consistency. When the matching degree is lower than a preset threshold, it indicates that the initial description cannot accurately reflect the reality, and the corresponding description will be automatically updated according to the actual data. For example, if the actual material supplier is different from the original description, or the resource arrival time is significantly delayed, the system will correct the material description and the arrival and timeliness description to ensure that the subsequent resource scheduling decisions are based on the latest facts.

[0082] The correction of the efficiency description is based on the time sequence performance analysis of the construction task. First, the reference construction time of the task is retrieved according to the construction content, i.e., the planned or historical average time required, and then the estimated construction time under the current resource input is calculated based on the construction progress 35 obtained in step S3, i.e., the time consumption of the actual completion is backtracked. By comparing the difference between the reference time and the estimated time, the deviation of the current construction efficiency is quantified. If the actual time consumption is significantly longer or shorter than the reference value, the efficiency description will be corrected accordingly, such as adjusting the evaluation of the speed of the work team, the efficiency of the equipment, etc. This realizes a closed loop of reverse optimization of resource capability cognition from actual operation performance. The correction of the quality description is based on defect feedback. According to the construction content and the current quality description, the estimated construction defects 36 description is generated, i.e., based on historical experience and resource capability, the types and distribution of possible defects are predicted. Then, the actual identified construction defects 36 are compared with the estimated value. If the actual defects significantly deviate from the estimate, such as the emergence of new types of defects not included in the estimate, or the defect frequency is much higher than expected, it indicates that the original quality description is no longer accurate, and the quality description will be corrected according to the actual defect data, such as updating the evaluation of the construction stability of a work team, the applicability of a material, or the risk level of a process.

[0083] For example, the initial construction resource description 12 is as follows:

[0084] Construction worker description: The concrete pouring team consists of 10 skilled workers with experience in high-rise building construction. Material description: The daily supply capacity of C35 concrete is 300 m³. Timeliness of arrival description: The average delay of concrete delivery is not more than 1 hour. Efficiency description: The pouring efficiency is 40 m³ per hour. Quality description: The concrete surface quality constructed by this team is good, with a low incidence of defects such as honeycomb and pitted surface.

[0085] The actual data acquisition of "obtained construction resource information 33" for 3 consecutive days shows that the concrete transport vehicle arrives with an average delay of 2.5 hours. By comparison, it is found that the actual arrival time deviates significantly from the initial "timeliness of arrival description" of "delay not more than 1 hour", and the matching degree is lower than the threshold. The revision result is to update the timeliness of arrival description to "concrete average arrival delay is about 2.5 hours, affected by traffic control". The material description is updated to "C35 concrete daily supply capacity is 200 m³, need to pay attention to supply stability".

[0086] Step S5) According to the revised construction resource description 12, generate the progress description item 37 and the quality inspection warning description item 38 of the current ongoing construction project.

[0087] The method of generating the progress description item 37 and the quality inspection warning description item 38 of the current ongoing construction project according to the revised construction resource description 12 includes:

[0088] According to the construction content and construction progress 35 of the construction project, obtain the construction workers and materials still needed for the current construction project 32;

[0089] Generate progress guarantee description 39 according to the construction workers and materials still needed for the current construction project 32;

[0090] Compare the progress guarantee description 39 with the acquisition approach description and the timeliness of arrival description, and generate the progress description item 37 according to the comparison result;

[0091] Obtain the quality inspection items still needed for the current construction project 32 and the construction defects 36 corresponding to the quality inspection items;

[0092] Calculate the matching degree of the construction defects 36 corresponding to the quality inspection items and the quality description, generate the occurrence probability of the construction defects 36 according to the matching degree, and generate the quality inspection warning description item 38 according to the occurrence probability and the corresponding construction defects 36.

[0093] Using the revised more accurate construction resource description 12, analyze the current ongoing construction project to generate the progress description item 37 and the quality inspection warning description item 38 for decision-making assistance.

[0094] According to the construction content of the construction project and the current confirmed construction progress 35, the types of key resources necessary to complete the remaining work quantity, especially manpower (such as specific types of work, quantity) and materials (such as material types, quantity) are derived. Then a future-oriented progress guarantee description 39 is generated, that is, the ideal state of the required resources for subsequent progress according to the plan. Then, the ideal state (i.e. progress guarantee description 39) is compared with the revised acquisition path description (where the resources come from, how to schedule) and the arrival timeliness description (whether the resources can arrive on time) in step S4. By analyzing the reliability, response period and historical punctuality rate of the resource supply path, the actual feasibility of resource guarantee is evaluated. If there are risks such as supply delay, unstable channel or difficulty in personnel supplement, the corresponding progress description item 37 is generated to reveal the potential progress constraints. For example, the label "uncertainty in key process manpower resource supplement" or "main material supply cycle extended, which may affect the connection of subsequent work".

[0095] Extract all quality inspection items that have not been completed for the current construction project 32, and combine the construction defects 36 related to the project identified in step S3 to identify the quality problems currently exposed. Each inspection item is analyzed in association with the updated quality description in step S4. The quality description includes a comprehensive evaluation of construction teams, material batches, and process stability. By calculating the matching degree between the historical or expected defect types corresponding to the inspection item and the current quality description, the probability of occurrence of the same defect in the future is inferred. For example, if a team's quality description is downgraded due to recent personnel changes, the probability of defects in the process it is responsible for increases accordingly. Combined with the probability of occurrence and the corresponding potential defect type, a quality inspection warning description item 38 is generated, prompting "reinforcing bar binding process protection layer thickness deviation risk increased, probability of occurrence about 70%".

[0096] Step S6) reads the unstarted construction project 21, and generates a prompt item 22 according to the revised construction resource description 12 and weather information 31.

[0097] The method for reading the unstarted construction project 21 and generating the prompt item 22 according to the revised construction resource description 12 and weather information 31 comprises:

[0098] Iterate through the unstarted construction project 21, extract the required construction personnel and materials, and generate a construction guarantee description;

[0099] According to the construction guarantee description, the acquisition path description and the arrival timeliness description, if there is a shortage of resources or the expected arrival time is later than the planned start time of the construction project, a resource preparation prompt item is generated;

[0100] Reading weather information 31, obtaining the construction content and planned start time of the unstarted construction project 21, when the weather affects the planned start time of the construction project, generating a start time prompt item;

[0101] Obtain the pre-requisite constraints of the unstarted construction project 21, and when the completion time of the pre-requisite constraints is later than the planned start time, generate a project start delay prompt item.

[0102] Through systematic traversal of all unstarted construction projects 21, and fusion of the corrected construction resource description 12 and real-time weather information 31, analysis is carried out from three dimensions of resource guarantee, environmental constraints and logical dependencies.

[0103] Extract the resource requirements such as the type and number of construction personnel, the type and amount of key materials, etc. required in the construction content, and form a construction guarantee description for each project. Then, compare and analyze this description with the dynamically corrected access description and on-site timeliness description in step S4. By simulating the resource scheduling path and timeline, it is determined whether the required resources can be fully available before the project plan starts. If the analysis result shows that there is a resource shortage (such as the team has been occupied by other tasks, the material inventory is insufficient) or the estimated arrival time is later than the planned start time, the system automatically generates a "resource preparation prompt item", such as "the senior reinforcement worker required for the second floor reinforcement binding of the main structure is expected to be delayed for 2 days, it is suggested to coordinate personnel in advance to supplement" or "A-level insulation board inventory is insufficient, it needs to be replenished within 3 days". Such prompts help to start the resource allocation process in advance and avoid delays due to insufficient preparation.

[0104] The generation of the start time prompt item depends on external environmental factors. Read the weather information 31 of the future period (such as precipitation probability, wind level, extreme temperature, visibility, etc.), and combine the construction content of the unstarted project (mainly the processes sensitive to weather such as open-air operation, high-altitude operation, concrete pouring, waterproof construction, etc.) and its planned start time to evaluate the impact of weather conditions on construction feasibility. For example, continuous rainfall may affect earthwork backfilling or external wall construction, and strong wind weather may prohibit tower crane operation. When it is judged that the future weather will cause the planned start time to fail to meet the safety or process requirements, a "start time prompt item" is generated, such as "the originally planned roof waterproof construction the next day is affected by the rain, it is suggested to be postponed to the day after the weather turns fine". Such prompt items improve the environmental adaptability of the construction plan, and help to avoid the confusion or safety risks caused by sudden weather changes on site.

[0105] The generation of the project start-up delay prompt item is derived from the dynamic verification of the project logical dependency relationship. Each unstarted construction project 21 usually has explicit preconditions (i.e., other construction tasks that must be completed before it). The current status of these preconditions is obtained, and in combination with the construction schedule 35 parsed in step S3, the estimated completion time of each precondition is calculated. When the estimated completion time is later than the planned start-up time of the current project, it means that the subsequent task cannot be carried out as planned. At this time, the "project start-up delay prompt item" is generated, such as "the preconditions of the external wall insulation construction, the main structure acceptance, are expected to be delayed for 1 day, and it is recommended to delay the start-up time of the insulation construction". This prompt item ensures the internal consistency of the construction plan and avoids the waste of resources caused by the blind start of subsequent processes due to the delay of preconditions.

[0106] Step S7) According to the progress description item 37, the quality inspection warning description item 38, and the prompt item, generate a number of affairs 23, which record the affair type, the affair state, and the affair description.

[0107] According to the progress description item 37, the quality inspection warning description item 38, and the prompt item, generate a number of affairs 23, which record the affair type, the affair state, and the affair description.

[0108] According to the progress description item 37, the quality inspection warning description item 38, and the prompt item, generate a number of affairs 23, which record the affair type, the affair state, and the affair description.

[0109] Set the affair state to the default initial value.

[0110] According to the progress description item 37, the quality inspection warning description item 38, and the prompt item, generate an affair description.

[0111] The determination of the affair type depends on the semantic analysis of the input item and the extraction of the decision action. For each progress description item 37, quality inspection warning description item 38, or prompt item, natural language understanding processing is performed to identify the decision intent or recommended action contained therein. For example, in the progress description item 37 "there is a delay risk in the reinforcement binding team personnel supplement", the core action that can be parsed is "coordinate personnel"; in the quality inspection warning description item 38 "the probability of concrete honeycomb defects increases", the actions that can be extracted are "strengthen inspection" or "organize rectification"; in the prompt item "roof waterproof construction needs to be delayed due to rainfall", the actions that can be identified are "adjust the plan" or "re-schedule". These verbs or verb phrases are "decision actions", which are classified into standardized affair types such as "resource coordination", "quality rectification", "schedule adjustment", "safety warning", and "technical briefing" according to the pre-set classification rules or action mapping table. This ensures the uniform classification and clear semantics of the affair item 23, facilitating subsequent task assignment and statistical analysis by type.

[0112] The status of the task is initialized to a preset default value, usually "Pending" or "Not Started", indicating that the task has just been generated and has not yet entered the execution process. This status serves as the starting point of the task's lifecycle and can be updated in the system to "Processing", "Completed", or "Rejected" based on the actual execution status.

[0113] The generation of the task description is a structured reconstruction and readability optimization of the original analysis results. Based on the corresponding progress description item 37, quality inspection warning description item 38, or prompt item, combined with the extracted task type, a complete, clear, and actionable text description is generated. This description typically includes: the problem background (such as the construction project involved and its location), the risks (such as insufficient resources, high probability of defects, and weather impact), the source of the basis (such as predictions of resource arrival delays), and the suggested action direction. For example, the task description generated from the "Resource Preparation Prompt Item" is: "Due to the current supplier's delay in concrete supply, the C35 concrete required for the basement sidewall pouring is expected to arrive two days later than planned. It is recommended to immediately contact the supplier to confirm the delivery time and assess whether an alternative supplier needs to be activated."

[0114] Step S8) Display the task 23 and display the progress description item 37, quality inspection warning description item 38 or prompt item information based on the user's interactive operation.

[0115] Item 23 is presented as a task list; please refer to the appendix. Figure 4 Each item (23) is labeled with its task type (e.g., "Resource Coordination," "Quality Rectification," "Schedule Adjustment," etc.), task status (e.g., "Pending," "Processing," "Completed"), and task description. Furthermore, the display interface supports sorting, filtering, and categorization by type, priority, urgency, or area of ​​responsibility. When a user clicks on or selects an item (23), they can view the original analysis information upon which that item (23) was generated. For example, if an item (23) originates from "Schedule Description Item 37," the user can view the specific content of that description item, such as "Concrete Supply Delay Risk," and the underlying data on the timeliness of resource availability, through the "View Details" operation.

[0116] On the other hand, this specification provides a big data-based intelligent management and control system for building engineering projects. Please refer to the appendix. Figure 5 ,include:

[0117] The reading module 100 reads the construction project set 11 and the construction resource description 12, the construction project set 11 records the project name, construction content, pre-requisite constraint and quality inspection item of all construction projects, and the construction resource description 12 records the available construction resource and resource description in natural language;

[0118] The receiving module 200 periodically receives the current construction project 32, the obtained construction resource information 33, the weather information 31 and the inspection video 34 of the unmanned aerial vehicle;

[0119] The analysis module 300 analyzes the inspection video 34, and obtains the construction progress 35 and the construction defect 36 according to the construction content and the detection item, respectively;

[0120] The correction module 400 corrects the construction resource description 12 according to the obtained construction resource information 33, the construction progress 35 and the construction defect 36;

[0121] The first generation module 500 generates the progress description item 37 and the quality inspection warning description item 38 of the current construction project according to the corrected construction resource description 12;

[0122] The second generation module 600 reads the unstarted construction project 21, and generates the prompt item according to the corrected construction resource description 12 and the weather information 31;

[0123] The affair module 700 generates a plurality of affair items 23 according to the progress description item 37, the quality inspection warning description item 38 and the prompt item, and the affair item 23 records the affair type, the affair state and the affair description;

[0124] The display module 800 displays the affair item 23, and displays the information of the progress description item 37, the quality inspection warning description item 38 or the prompt item according to which the affair item 23 is based on the interactive operation of the user.

[0125] Please refer to Figure 6 The structural schematic diagram of the electronic device provided by the embodiment of the present specification is shown.

[0126] As Figure 6As shown, the electronic device 1100 can include at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. The communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. The user interface 1103 can include a key, and the optional user interface can also include a standard wired interface, a wireless interface. The network interface 1104 can include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc. The processor 1101 can include one or more processing cores. The processor 1101 connects various parts in the entire electronic device 1100 through various interfaces and lines, executes various functions of the routing device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 can be realized by at least one of DSP, FPGA, and PLA. The processor 1101 can integrate CPU, GPU, and modem, etc. The CPU is mainly used to process operating systems, user interfaces, and application programs, etc. The GPU is used to render and draw the content to be displayed on the display screen. The modem is used to process wireless communication.

[0127] It can be understood that the above-mentioned modem can also not be integrated into the processor 1101, but be realized by a separate chip.

[0128] The memory 1105 can include RAM and ROM. Optionally, the memory 1105 includes a non-transitory computer readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 can include a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 1105 can also be at least one storage device located away from the above-mentioned processor 1101. The memory 1105 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program. The processor 1101 can be used to call the application program stored in the memory 1105 and execute the method in the above-mentioned multiple embodiments.

[0129] The embodiments of the present specification also provide a computer-readable storage medium, which stores instructions, when the instructions are executed on a computer or a processor, cause the computer or the processor to perform the steps of the above-mentioned embodiments. The constituent modules of the above-mentioned electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in the computer-readable storage medium.

[0130] The embodiments of the present specification also provide a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned embodiments.

[0131] In the case of no conflict, the technical features in the embodiments and the implementation forms can be combined arbitrarily.

[0132] In the above-mentioned embodiments, all or part of the embodiments can be realized by software, hardware, firmware or any combination thereof. When realized by software, all or part of the embodiments can be realized in the form of a computer program product. The computer program product comprises a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with a plurality of available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, digital versatile disc (DVD)) or a semiconductor medium (for example, solid state disk (SSD)) and the like.

[0133] When implemented by hardware or firmware, the foregoing method flow is programmed into a hardware circuit to obtain a corresponding hardware circuit structure, and the corresponding function is realized. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is an integrated circuit, and the logic function thereof is determined by the user programming the device. A digital system is "integrated" on a PLD by the designer programming it by himself / herself, and a chip manufacturer does not need to be invited to design and manufacture a special integrated circuit chip. Moreover, nowadays, instead of manually manufacturing an integrated circuit chip, this programming is mostly implemented by using a "logic compiler" software, which is similar to a software compiler used when a program is developed and written, and the original code before the compilation also needs to be written in a specific programming language, which is called a hardware description language (HDL), and there are many kinds of HDLs. It should be clear to those skilled in the art that the method flow only needs to be logically programmed in the above-mentioned several hardware description languages and programmed into an integrated circuit, and a hardware circuit that realizes the logical method flow can be easily obtained.

[0134] The above-described embodiments are merely preferred embodiments of the present specification, and do not limit the scope of the present specification. Various changes and modifications to the technical solutions of the present specification made by those skilled in the art without departing from the design spirit of the present specification shall fall within the protection scope of the claims of the present specification.

Claims

1. A method for intelligent management and control of construction projects based on big data, characterized in that, Including the following steps: Read the construction project set and construction resource description of the building. The construction project set records the project name, construction content, preconditions and quality inspection items of all construction projects. The construction resource description records the available construction resources and resource descriptions in natural language. Periodically receive information on current construction projects, acquired construction resources, weather information, and inspection videos from drones; By analyzing the inspection video, the construction progress and construction defects can be obtained according to the construction content and inspection items. The description of construction resources is revised based on the obtained construction resource information, construction progress, and construction defects. Based on the revised construction resource description, generate progress description items and quality inspection warning description items for the currently ongoing construction project; Read the construction projects that have not been started, and generate prompts based on the revised construction resource description and weather information; Based on the progress description, quality inspection warning description, and prompt items, several tasks are generated, and each task records the task type, task status, and task description. The system displays the task to be completed and, based on the user's interaction, displays information such as progress descriptions, quality inspection warnings, or prompts related to the task.

2. The intelligent management and control method for construction projects based on big data according to claim 1, characterized in that, The methods for analyzing the inspection video and obtaining the construction progress based on the construction content include: Read the sequence of frame images from the inspection video, identify the construction area in the frame image, and generate a description of the identified objects in the construction area based on the objects identified in the construction area and their state. By comparing the identification description with the corresponding construction content, the current construction tasks and progress of the construction area can be identified. Based on the current construction tasks and their progress, obtain the current construction progress of the project. Based on the construction progress obtained from inspection videos over multiple consecutive periods, a construction progress trend is obtained, and the lagging or leading state of the construction progress is marked according to the construction progress trend.

3. The intelligent management and control method for construction projects based on big data according to claim 2, characterized in that, The methods for analyzing the inspection video and obtaining construction defects based on the inspection items include: Based on the quality inspection items of all construction projects, a construction defect knowledge graph is constructed, which includes defect type, defect visual characteristics, associated construction procedures and severity level markings. The sequence of frame images from the inspection video is read, and the frame images are input into a pre-accessed target matching model. The output of the target matching model is whether there are defect visual features that match the input. Based on the output of the target matching model, candidate defects are generated; The candidate defects are semantically compared with the quality inspection items of the current construction project, and candidate defects that do not match the semantics are removed. Based on the remaining candidate defects, construction defects are generated, and the construction defects record the defect type, associated construction procedures, and severity level.

4. A method for intelligent management and control of construction projects based on big data according to any one of claims 1 to 3, characterized in that, The resource description includes descriptions of construction personnel, materials, acquisition methods, timeliness of arrival, efficiency, and quality. The methods for revising the construction resource description based on obtained construction resource information, construction progress, and construction defects include: Read the construction personnel information, material information, acquisition method information, and arrival timeliness information of the acquired construction resources, and compare the construction personnel information, material information, acquisition method information, and arrival timeliness information with the construction personnel description, material description, acquisition method description, and arrival timeliness description, respectively; When the matching degree of the comparison is lower than the preset threshold, the descriptions of construction personnel, materials, acquisition methods, and arrival timeliness are corrected according to the construction personnel information, acquisition method information, and arrival timeliness information of the obtained construction resource information. The reference construction time of the construction project is obtained based on the construction content, the estimated construction time is obtained based on the construction progress, and the efficiency description is corrected based on the reference construction time and the estimated construction time. Based on the construction content and quality description, an estimated construction defect description is generated. The construction defect is compared with the estimated construction defect description. If the matching degree between the construction defect and the estimated construction defect description is lower than a preset threshold, the quality description is corrected based on the construction defect.

5. The intelligent management and control method for construction projects based on big data according to claim 4, characterized in that, The method for generating progress description items and quality inspection warning description items for the currently ongoing construction project based on the revised construction resource description includes: Based on the construction content and progress of the construction project, obtain the construction personnel and materials still needed for the current construction project; Generate a progress guarantee description based on the construction personnel and materials still needed for the current construction project; The progress guarantee description is compared with the acquisition method description and the timeliness of arrival description, and a progress description item is generated based on the comparison result. Obtain the quality inspection items that still need to be carried out in the current construction project, as well as the construction defects corresponding to the quality inspection items; The matching degree between the construction defect corresponding to the quality inspection item and the quality description is calculated. The occurrence probability of the construction defect is generated based on the matching degree. The quality inspection warning description item is generated based on the occurrence probability and the corresponding construction defect.

6. A method for intelligent management and control of construction projects based on big data according to any one of claims 1 to 3, characterized in that, The method for reading inactive construction projects and generating prompts based on the revised construction resource description and weather information includes: Iterate through the construction projects that have not yet started, extract the construction personnel and materials required for them, and generate a construction support description; Based on the construction support description, the acquisition method description, and the timeliness description, if there is insufficient resources or the expected arrival time is later than the planned start time of the construction project, a resource preparation prompt item will be generated. Read weather information to obtain the construction content and planned start time of construction projects that have not yet started. When the weather affects the planned start time of construction projects, generate a start time reminder. Obtain the prerequisite constraints for construction projects that have not yet started. If the completion time of the prerequisite constraints is later than the planned start time, generate a project start postponement prompt.

7. The intelligent management and control method for construction projects based on big data according to claim 6, characterized in that, Based on the progress description, quality inspection warning description, and prompt items, several tasks are generated. The method for recording the task type, task status, and task description for each task includes: Semantic parsing is performed on the progress description items, quality inspection warning description items, and prompt items to extract decision actions, and the service type is determined based on the decision actions. Set the operation status to the default initial value; A service description is generated based on the progress description, quality inspection warning description, and prompts.

8. A big data-based intelligent management and control system for construction projects, characterized in that, include: The reading module reads the construction project set and construction resource description of the building. The construction project set records the project name, construction content, preconditions and quality inspection items of all construction projects. The construction resource description records the available construction resources and resource descriptions in natural language. The receiving module periodically receives information on the current construction project, acquired construction resources, weather information, and inspection videos from drones. The analysis module analyzes the inspection video and obtains the construction progress and construction defects according to the construction content and inspection items. The correction module corrects the construction resource description based on the obtained construction resource information, construction progress, and construction defects. The first generation module generates a progress description item and a quality inspection warning description item for the currently ongoing construction project based on the revised construction resource description. The second generation module reads the construction projects that have not been started and generates prompts based on the revised construction resource description and weather information. The service module generates several service items based on the progress description, quality inspection warning description, and prompt items. Each service item records the service type, service status, and service description. The display module shows the task to be completed and, based on the user's interactive operations, displays information such as progress descriptions, quality inspection warnings, or prompts related to the task.

9. An electronic device, characterized in that, Including the processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images