Intelligent construction equipment recommendation method for extracting and recommending optimal equipment suitable for delayed processes based on efficiency index of construction equipment
The intelligent construction equipment recommendation method addresses inefficiencies in conventional selection methods by calculating an efficiency index from workload, failure data, and weather data, enhancing process stability and reducing costs through data-driven decision-making.
Patent Information
- Application Number
- KR1020260045898
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2026-03-13
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2046-03-13
AI Technical Summary
Conventional construction equipment selection methods rely on empirical judgment, fail to integrate equipment operational efficiency data, and do not adequately consider external environmental factors, leading to inefficiencies and increased costs due to unsuitable equipment deployment and delayed processes.
An intelligent construction equipment recommendation method that calculates an efficiency index based on workload, failure characteristics, and operating costs, integrates weather forecast data, and uses real-time sensor data to predict equipment lifespan, enabling data-driven decision-making for optimal equipment selection.
This method improves process stability by systematically selecting suitable equipment, reduces the risk of cascading delays, and lowers unexpected maintenance costs by anticipating equipment failures and environmental risks, resulting in reduced construction time and costs.
Smart Images

Figure 112026031046545-PAT00005_ABST
Abstract
Description
Technology Field
[0001] The present invention relates to an intelligent construction equipment recommendation method that extracts and recommends optimal equipment suitable for a delayed process based on the efficiency index of construction equipment. Background Technology
[0002] Generally, the construction process is a complex system in which various complex processes proceed in parallel, and the order of processes and the appropriateness of resource allocation directly affect the overall construction period and cost. However, conventional process management methods have often relied primarily on empirical judgment or simple comparisons of progress rates to determine whether delays have occurred. This approach makes it difficult to quantitatively analyze the root causes of delays and entails the problem of failing to reallocate corresponding equipment in a timely manner. In particular, despite the significant impact that equipment operational efficiency has on process productivity, equipment selection was often made based on conventional criteria.
[0003] Despite construction equipment being a core asset requiring massive investment, instances of systematically integrated analysis of data—such as average breakdown intervals, operating costs, and actual workload—have been limited. At most construction sites, equipment failure histories and maintenance records were utilized merely for simple management purposes, lacking a system to incorporate this information into process-related decision-making. Consequently, problems arose where equipment unsuitable for delayed processes was deployed, leading to additional time losses or increased costs.
[0004] Relying solely on progress rates or work reports to determine process delays can lead to a discrepancy with actual production activities. For instance, although material consumption rates are an indicator reflecting the actual activity of process execution, systems for assessing delays by comparing them to standard consumption rates have not been sufficiently generalized. Therefore, there is a need for technical means to precisely assess process status by combining material input patterns with equipment operation data.
[0005] Construction processes are significantly affected by external environmental variables such as weather conditions. In particular, for outdoor work, factors such as precipitation, strong winds, and extreme heat affect not only work efficiency but also the probability of equipment failure. However, conventional technologies have limitations in that they utilize weather forecast data only as a simple reference or fail to directly link it to the adjustment of the process sequence. Consequently, there is an increasing need for technology that comprehensively reflects external risks in equipment recommendation and process-related decision-making processes.
[0006] With recent advancements in IoT sensors and machine learning, technologies for predicting remaining equipment lifespan based on vibration, temperature, and current data are being introduced. However, integrated structures that dynamically adjust equipment selection by directly incorporating these prediction results into process recommendation algorithms are still being implemented only to a limited extent. In other words, there is a structural limitation where equipment status prediction and process optimization operate separately. The problem to be solved
[0007] According to the present invention, by integrating the workload, failure characteristics, and operating costs of construction equipment and quantifying them into an efficiency index, equipment suitable for delayed processes can be systematically selected. Accordingly, the equipment selection process, which previously relied on empirical judgment, is transformed into a data-driven decision-making structure, thereby improving process stability.
[0008] According to the present invention, by determining a delay state by comparing the material consumption rate with a standard consumption rate, a more substantial decline in productivity can be detected early than with a simple progress rate analysis. This provides the effect of preventing cascading delays by introducing suitable equipment before the process exceeds a critical point.
[0009] According to the present invention, by considering weather forecast data and process attribute information together, hazardous dates for outdoor work can be identified in advance and alternative processes can be proposed. This enables realistic and stable process operation that reflects external environmental risks, rather than simple schedule optimization.
[0010] According to the present invention, by predicting the remaining usable time of equipment based on real-time sensor data and reflecting this in the efficiency index, the introduction of equipment with a high probability of failure can be suppressed in advance. This provides the effect of reducing the risk of process interruption and lowering unexpected maintenance costs.
[0011] According to the present invention, by continuously analyzing the equipment status through a machine learning model and calculating a correction efficiency index, a structure can be implemented in which recommendation accuracy improves over time. Accordingly, a self-learning equipment recommendation system that adapts to site characteristics, equipment usage patterns, and environmental conditions is established, allowing for the expectation of reduced construction time and cost savings in the long term.
[0012] The technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. means of solving the problem
[0013] An intelligent construction equipment recommendation method for extracting and recommending optimal equipment suitable for a delayed process based on an efficiency index of construction equipment, performed by an electronic device including a processor according to an embodiment of the present invention, comprises the following operations: the processor acquiring field operation data including the progress of each process of a target building under construction, material status data, a list of construction equipment available for each process, an average failure interval for each construction equipment, and an operating cost for each construction equipment; the processor checking, based on the field operation data, whether there exists a target process among a plurality of processes currently in progress on the target building that corresponds to a delayed state and is simultaneously set to be capable of parallel progress with other processes; the processor checking, if the target process is confirmed, a standard efficiency index and a standard cost limit set for the target process; the processor confirming at least one target equipment corresponding to the target process through the construction equipment list, and checking the efficiency index of each of the at least one target equipment based on the work volume per unit time for the target process for each of the at least one target equipment, the average failure interval, and the operating cost; and the processor, wherein the efficiency index is greater than or equal to the standard efficiency index and simultaneously the operating cost is the standard The method may include identifying final equipment that is below a cost limit as recommended equipment for the target process and providing recommendation information to a user terminal, including the expected time of completion of the target process when the target process is performed using the final equipment.
[0014] According to one embodiment, the operation of checking whether the target process exists may include the operation of the processor calculating the material consumption rate per unit time of the target material corresponding to the target process from the material status data during the progress of the target process, and the operation of the processor confirming that the target process is in the delayed state if the material consumption rate per unit time of the target material is less than 70% compared to the standard material consumption rate set corresponding to the type of the target process.
[0015] According to one embodiment, the operation of checking the efficiency index of each of the target equipment may include the operation of the processor calculating a first efficiency factor by normalizing the work amount per unit time of the target equipment to a set reference work amount; the operation of the processor calculating a second efficiency factor by normalizing the average failure interval of the target equipment to a set reference failure interval; the operation of the processor calculating a cost correction factor by normalizing the operating cost of the target equipment to a set reference cost; and the operation of the processor calculating the efficiency index by applying a weighting coefficient set to the first efficiency factor and the second efficiency factor, respectively, and subtracting the cost correction factor.
[0016] According to one embodiment, the operation of providing the recommendation information may include: the operation of the processor collecting weather forecast data of the area where the target building exists from an external server and determining whether the target process is an outdoor operation from the attribute information of the target process; the operation of the processor, if it is confirmed that the target process is an outdoor operation, determining from the weather forecast data a risk date on which the probability of precipitation during the execution of the target process until the expected completion time of the target process is expected to be greater than a threshold probability; and the operation of the processor providing alternative recommendation information to the user terminal, suggesting that, if the risk date is greater than or equal to a threshold number of days, the process capable of performing indoor work should be prioritized among the remaining processes excluding the target process.
[0017] According to one embodiment, the intelligent construction equipment recommendation method may include the following operations: when the target process is identified, the processor obtains real-time status data regarding the target equipment from at least one of a vibration sensor, a temperature sensor, and a current sensor attached to the target equipment; the processor predicts the remaining usable time of the target equipment through a machine learning model based on the real-time status data; the processor calculates a failure risk correction coefficient by comparing the remaining usable time with the average failure interval; and the processor recalculates a corrected efficiency index by reflecting the failure risk correction coefficient in the efficiency index and re-selects the recommended equipment based on the corrected efficiency index.
[0018] The above intelligent construction equipment recommendation method is,
[0019] The above processor further includes an operation of calculating an efficiency index for each of the above target equipment through the following [Mathematical Formula 1], and
[0020] [Mathematical Formula 1]
[0021]
[0022] EI is the efficiency index of the target equipment, W_act is the work volume per unit time of the target equipment, W_std is the reference work volume of the target process, M_act is the average failure interval of the target equipment, M_std is the reference failure interval of the target equipment, C_act is the operating cost of the target equipment, C_std is the set reference cost, p is the set cost sensitivity coefficient, and k is the set cost penalty index.
[0023] The above intelligent construction equipment recommendation method is,
[0024] The above processor acquires a ground image of a point where the target process is to be performed, and identifies the distribution of moisture content of the ground included in the ground image through image segmentation;
[0025] The above processor calculates the maximum ground pressure per unit area applied to the ground surface based on the self-weight and working load during the operation of the above-mentioned final equipment; and
[0026] The above processor includes an operation of calculating the minimum area of an outrigger pad to be placed at the bottom of the final equipment and providing it along with the recommendation information when the ground allowable bearing capacity estimated according to the moisture content distribution is less than the maximum ground pressure.
[0027] The operation of providing the above recommendation information is,
[0028] The above processor performs the operation of checking the current inventory amount of essential consumables that are pre-set as essential for the operation of the above final equipment from the field material management database;
[0029] The operation of the processor to calculate an estimated required amount of consumables by multiplying the required consumable consumption rate per unit time set for the end equipment by the remaining time required for the target process; and
[0030] The processor includes an operation of including a notification in the recommendation information instructing the transfer of insufficient materials from an adjacent material warehouse of the target building that is previously registered, if the current inventory of the essential consumables is less than the estimated required amount of consumables.
[0031] The operation of providing the above recommendation information is,
[0032] The operation of the processor to calculate a real-time wet-bulb black globe temperature (WBGT) index from temperature and humidity sensors in the field area where the target process is performed;
[0033] The above processor acquires heart rate and body temperature data from a wearable device of personnel introduced into the target process; and
[0034] When the above WBGT index is above the set risk level and at the same time the body temperature of the personnel exceeds the critical temperature, the operation includes switching the smart turnsteel gate placed at the entrance of the site area to a locked state and providing a forced rest notification.
[0035] The operation of providing the above recommendation information is,
[0036] The above processor, when the type of the end equipment is mobile lighting equipment, performs the operation of generating a real-time illuminance plan from a plurality of point-specific illuminance sensors placed inside the target process;
[0037] The operation of the processor identifying a dark spot area below a reference illuminance set on the real-time illuminance plane; and
[0038] The above processor includes the operation of transmitting a control signal to the end equipment in response to receiving a request to start a process through the end equipment from the user terminal, moving the end equipment to a point corresponding to the dark area and automatically adjusting the lamp module angle of the end equipment toward the center point of the dark area. Effects of the invention
[0039] The effects of the intelligent construction equipment recommendation method according to the embodiments of the present invention are described as follows.
[0040] According to the present invention, by integrating the workload, failure characteristics, and operating costs of construction equipment and quantifying them into an efficiency index, equipment suitable for delayed processes can be systematically selected. Accordingly, the equipment selection process, which previously relied on empirical judgment, is transformed into a data-driven decision-making structure, thereby improving process stability.
[0041] According to the present invention, by determining a delay state by comparing the material consumption rate with a standard consumption rate, a more substantial decline in productivity can be detected early than with a simple progress rate analysis. This provides the effect of preventing cascading delays by introducing suitable equipment before the process exceeds a critical point.
[0042] According to the present invention, by considering weather forecast data and process attribute information together, hazardous dates for outdoor work can be identified in advance and alternative processes can be proposed. This enables realistic and stable process operation that reflects external environmental risks, rather than simple schedule optimization.
[0043] According to the present invention, by predicting the remaining usable time of equipment based on real-time sensor data and reflecting this in the efficiency index, the introduction of equipment with a high probability of failure can be suppressed in advance. This provides the effect of reducing the risk of process interruption and lowering unexpected maintenance costs.
[0044] According to the present invention, by continuously analyzing the equipment status through a machine learning model and calculating a correction efficiency index, a structure can be implemented in which recommendation accuracy improves over time. Accordingly, a self-learning equipment recommendation system that adapts to site characteristics, equipment usage patterns, and environmental conditions is established, allowing for the expectation of reduced construction time and cost savings in the long term.
[0045] In addition, various effects that can be identified directly or indirectly through this document may be provided. Brief explanation of the drawing
[0046] FIG. 1 is a block diagram showing the components of an electronic device according to an embodiment of the present invention. FIG. 2 is a block diagram showing the components of an intelligent construction equipment recommendation system according to one embodiment of the present invention. FIG. 3 is a flowchart of the operation of an intelligent construction equipment recommendation method according to one embodiment of the present invention. FIG. 4 is a flowchart of the operation of an intelligent construction equipment recommendation method according to one embodiment of the present invention. In relation to the description of the drawings, the same or similar reference numerals may be used for the same or similar components. Specific details for implementing the invention
[0047] Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the embodiments of the present invention, if it is determined that a detailed description of related known components or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted.
[0048] In describing the components of the embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by these terms. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.
[0049] Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 4.
[0051] FIG. 1 is a block diagram showing the components of an electronic device according to one embodiment of the present invention.
[0052] According to one embodiment, the electronic device (100) may include a memory (110), a processor (120), a communication interface (130), and / or a display device (140). The configuration of the electronic device (100) shown in FIG. 1 is exemplary and the embodiments of the present invention are not limited thereto. For example, the electronic device (100) may further include components not shown in FIG. 1 (e.g., a web crawler, a user interface, an input device, a notification unit, a sensor unit, or at least one of any combination thereof).
[0053] According to one embodiment, the memory (110) may store instructions or data. For example, the memory (110) may store one or more instructions that cause the electronic device (100) to perform various operations when executed by the processor (120).
[0054] For example, the memory (110) may be implemented as a single chipset with the processor (120). The processor (120) may include at least one of a communication processor or a modem.
[0055] For example, the memory (110) can store various information related to the electronic device (100). For example, the memory (110) can store information regarding the operation history of the processor (120). For example, the memory (110) can store input data acquired by the electronic device (100), output data output by the electronic device (100), data acquired from an external server, a wearable device, a plurality of cameras and / or user terminals, etc.
[0056] For example, the memory (110) may include multiple storage devices of different types. For example, the memory (110) may include volatile and / or non-volatile storage media. For example, the memory (110) may include at least one of RAM (random-access memory), ROM (read only memory), eMMC (Embedded Multi-Media Card), or any combination thereof.
[0057] The steps of the method or algorithm described in connection with the embodiments disclosed in this specification may be directly implemented in hardware, software modules, or a combination of both, executed by the processor (120). The software modules may reside in a storage medium (i.e., memory (110)) such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, or a CD-ROM.
[0058] For example, the memory (110) is coupled to a processor (120), and the processor (120) can read information from a storage medium and write information to a storage medium. Alternatively, the memory (110) may be integrated with the processor (120). The memory (110) and the processor (120) may reside within an application-specific integrated circuit (ASIC). The ASIC may reside within a user terminal. Alternatively, the memory (110) and the processor (120) may reside as separate components within the user terminal.
[0059] According to one embodiment, the processor (120) may be operatively connected to the memory (110), the communication interface (130), and / or the display device (140). For example, the processor (120) may control the operation of the memory (110), the communication interface (130), and / or the display device (140).
[0060] According to one embodiment, the communication interface (130) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (100) and an external device (e.g., user terminal (210) of FIG. 2, external server (220), etc.), and the performance of communication through the established communication channel. The communication interface (130) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication interface (130) may include a wireless communication module (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device through a first network (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a long-range communication network such as a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module can identify or authenticate the electronic device (100) within a communication network, such as the first network or the second network, using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in a subscriber identification module.
[0061] According to one embodiment, the display device (140) may include at least one output device that provides various information and a user interface to the user.
[0062] For example, the display device (140) may include a display device, an audio output device, a virtual reality output device, etc.
[0063] For example, the display device (140) can provide the administrator with various types of user interfaces described in the present disclosure visually and / or audibly.
[0064] The components of the electronic device (100) illustrated in FIG. 1 are exemplary, and the embodiments of the present disclosure are not limited thereto.
[0065] At least some of the embodiments of the present disclosure may be implemented as artificial intelligence (AI) through the processor (120) and memory (110) of the electronic device (100). The processor (120) may be composed of one or more processors, and the one or more processors may be general-purpose processors such as a CPU, AP, DSP (digital signal processor), etc., graphics-dedicated processors such as a GPU, VPU (vision processing unit), or artificial intelligence-dedicated processors such as an NPU. The one or more processors may be controlled to process input data according to predefined operation rules or artificial intelligence models stored in memory (110). Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.
[0066] The predefined operating rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined operating rules or artificial intelligence models are created by a basic artificial intelligence model being trained using multiple learning data by a learning algorithm, thereby enabling the performance of a desired characteristic (or purpose). Such learning may be performed within the electronic device (100) itself where the artificial intelligence according to the present disclosure is performed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.
[0067] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values and can perform neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights can be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include, but are not limited to, deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), restricted Boltzmann machines (RBM), deep belief networks (DBN), bidirectional recurrent deep neural networks (BRDNN), or deep Q-networks.
[0068] According to one embodiment, an electronic device (100) may collect real-time status data at regular intervals from a vibration sensor, a temperature sensor, and a current sensor attached to a target device, and input this data into a supervised learning-based regression model by combining it with a pre-established training dataset. The training dataset may be configured to include past equipment operation history, failure time, maintenance records, and sensor time series data.
[0069] For example, a supervised learning-based regression model may include at least one of a multilayer perceptron (MLP), a random forest regression model, or a gradient boosting-based model, through which the remaining useful life (RUL) of the target equipment can be predicted as a continuous value.
[0070] The remaining usable time predicted in this way can be utilized as an “individual equipment-specific predicted life value” distinct from the simple average interval between failures.
[0071] According to another embodiment, the electronic device (100) may form time-series data of vibration signals, temperature rise trends, and current fluctuation patterns over time of the equipment and input this into a Recurrent Neural Network (RNN)-based model.
[0072] In particular, since equipment degradation is characterized by "temporal change patterns" rather than numerical values at a single point in time, it is possible to learn long-term state changes by utilizing a Long Short-Term Memory (LSTM) structure.
[0073] The LSTM model detects minute degradation trends in equipment early to predict the remaining usable time, and this prediction can be reflected as a failure risk correction factor in the process of calculating the efficiency index.
[0074] According to another embodiment, the electronic device (100) can define process type, work environment, equipment characteristics, and past process execution result data as a state, and define the act of placing specific equipment in the process as an action to configure a reinforcement learning-based recommendation model.
[0075] For example, a reinforcement learning-based recommendation model performs learning by setting the process completion time, failure occurrence, and cost efficiency after deploying specific equipment to a specific process as rewards.
[0076] Through this, as iterative learning is performed, equipment selection strategies optimized for process types are automatically derived, enabling the implementation of an adaptive recommendation structure that goes beyond simple condition filtering.
[0077] According to one embodiment, the electronic device (100) can train an unsupervised learning model based on the distribution of sensor data collected in a normal operating state. For example, after training to reproduce a normal state pattern by applying an autoencoder-based anomaly detection model, if the reconstruction error exceeds a certain threshold, it can be determined as an anomaly.
[0078] Such anomaly detection results are reflected in the process of calculating the failure risk correction factor, so that the efficiency index can be configured to be lowered if an abnormal pattern is detected, even if there is sufficient average failure interval remaining.
[0079] According to another embodiment, the electronic device (100) can periodically retrain the model by collecting performance data after the actual process is completed and adding it to the training data of the artificial intelligence model.
[0080] For example, after introducing recommended equipment, the prediction error can be calculated by comparing the actual process completion time with the predicted completion time, and this can be reflected in the loss function to adjust the model weights.
[0081] In this way, through iterative learning, a self-learning equipment recommendation system that adapts to various environmental variables such as site characteristics, weather conditions, and material characteristics can be implemented.
[0082] In another embodiment, instead of a single artificial intelligence model, multiple prediction models are operated in parallel, and the final remaining usable time can be calculated by weighting the prediction results of each model.
[0083] For example, by combining the prediction results of a regression-based model, an LSTM-based model, and an anomaly detection model, the bias of a single model can be reduced and the reliability of the prediction can be improved.
[0084] This ensemble structure enhances the stability of equipment recommendations and contributes to ensuring consistent performance in various process environments.
[0086] FIG. 2 is a block diagram showing the components of an intelligent construction equipment recommendation system according to one embodiment of the present invention.
[0087] According to one embodiment, the intelligent construction equipment recommendation system may include an electronic device (100), a user terminal (210), and an external server (220).
[0088] According to one embodiment, the electronic device (100) may be implemented as a central processing unit that performs decision-making and integrates various operational data collected at a construction site, serving as the core computing entity of the present invention. The electronic device (100) may be implemented in the form of a field server, a cloud-based computing device, or an edge computing device, and performs real-time data processing functions in conjunction with a process management system. In particular, it may include a high-performance processor and memory structure to simultaneously process multiple processes and multiple equipment data.
[0089] The electronic device (100) is connected via communication with construction equipment, a material management system, a weather information system, etc., to collect various source data. The collected data is not merely stored but is converted into an analyzable form through preprocessing steps such as processing missing values, removing outliers, and normalization. These preprocessing steps serve as a basis for calculating efficiency indices and improving the reliability of the input data for the artificial intelligence model.
[0090] The electronic device (100) may include a computation module that calculates an efficiency index by synthesizing the workload, failure characteristics, and cost information of the equipment. Additionally, when real-time sensor data is input, it performs a correction operation that predicts the remaining usable time using a machine learning model and reflects this in the existing efficiency index. This structure has technical significance in that it implements a dynamic decision-making system rather than simple static analysis.
[0091] The electronic device (100) may include a prediction engine that predicts the expected time of process completion, the probability of failure, the possibility of cost overrun, etc. by utilizing past process execution results and equipment operation history as learning data. This prediction engine may be configured by applying various artificial intelligence techniques such as supervised learning, reinforcement learning, or ensemble models, and may be designed to continuously improve recommendation accuracy.
[0092] The electronic device (100) performs bidirectional communication with a user terminal (210) and an external server (220) and may include data encryption and access control functions. In particular, since operational data at a construction site includes costs, schedules, and equipment asset information, it is desirable to apply a communication protocol that ensures security. This prevents external intrusion or data tampering and enables the provision of a stable process recommendation service.
[0093] According to one embodiment, the user terminal (210) may be implemented as an interface device through which a field manager or process manager checks the recommended results of the present invention and makes decisions. This may be implemented in the form of a smartphone, tablet, laptop, or dedicated industrial terminal, and visually provides recommended equipment, estimated completion time, and alternative process information through an intuitive user interface (UI).
[0094] The user terminal (210) can provide visualization of the process status in the form of a graph, heatmap, or timeline. For example, delayed processes are indicated by color highlighting, and the efficiency score of recommended equipment can be expressed in the form of a comparison chart. This visualization function supports intuitive understanding of complex data, thereby providing the effect of reducing decision-making time.
[0095] The user terminal (210) is not merely a simple information receiving device, but may include an interaction function capable of inputting approval, modification requests, or manual relocation commands regarding the recommendation results. The user's selection results can be transmitted back to the electronic device (100) and used as training data, thereby continuously improving the recommendation algorithm.
[0096] The user terminal (210) can display a notification message when certain threshold conditions are met, such as an increased risk of equipment failure, a prediction of worsening weather, or a risk of cost overrun. This notification can be provided in the form of vibration or voice guidance as well as a visual display, enabling a rapid response to emergency situations.
[0097] When multiple managers participate in the same project, the user terminal (210) can set access rights by role through a permission-based account system. For example, the site manager can check overall process information, and the equipment manager can focus on equipment status information. Through this, an organized and systematic process management environment is created.
[0098] According to one embodiment, an external server (220) performs the role of collecting external information, such as weather information, local environmental data, and maintenance data provided by the equipment manufacturer, and providing it to the electronic device (100). This enables decision-making that comprehensively considers not only internal field data but also external environmental factors.
[0099] The external server (220) can provide data such as the probability of precipitation, wind speed, and temperature through a public weather API or a private weather forecasting service. This information is used to determine the risk of an outdoor process and to decide whether to recommend an alternative process.
[0100] The external server (220) can be linked with the equipment manufacturer or a specialized maintenance organization to provide standard failure patterns, recommended maintenance cycles, and consumable part life information for each piece of equipment. This can be used to set a reference value for the average failure interval.
[0101] The external server (220) can provide a cloud-based learning environment for processing large volume data. By integrating and learning equipment operation data collected from multiple sites, the prediction accuracy of the artificial intelligence model can be improved, and the learned model can be distributed to the electronic device (100).
[0102] The external server (220) performs software updates, security patch distribution, model version management, etc., to ensure the scalability and maintainability of the system. This allows the system to be flexibly expanded even when new equipment types are added or new prediction models are developed.
[0103] In the present disclosure, “target building” may refer to a single project site where construction is in progress or a project unit consisting of multiple buildings.
[0104] In the present disclosure, “process” may refer to work units managed on-site (e.g., work units classified by WBS / process codes), such as earthwork, rebar / formwork, concrete pouring, waterproofing, exterior finishing, equipment installation, interior finishing, etc., and “process corresponding to a delayed state” may refer to a process whose performance lags behind the standard plan.
[0105] In the present disclosure, “construction equipment” may include machinery and / or equipment used in the execution of a process, such as excavators, cranes, concrete pump trucks, aerial work platforms, generators, and compressors.
[0106] In the present disclosure, the “efficiency index” may be defined as a score calculated by normalizing and / or weighting productivity factors (e.g., workload per unit time), stability factors (e.g., interval between breakdowns), and cost factors (e.g., operating costs) that contribute to process execution for each piece of equipment, and the “reference efficiency index” and “reference cost limit” may be defined as threshold standards set in advance according to process type, project constraints (e.g., budget, schedule, quality), site policies, etc.
[0107] In the present disclosure, “recommendation information” may consist of information in the form of packets including recommended equipment (or a list of equipment candidates), reasons for recommendation (e.g., efficiency summary information), expected completion time, cost impact, risks (e.g., failure, weather, etc.).
[0109] FIG. 3 is a flowchart of the operation of an intelligent construction equipment recommendation method according to one embodiment of the present invention.
[0110] According to one embodiment, the components of an intelligent construction equipment recommendation system can perform the operations disclosed in FIG. 3. For example, at least some of the components included in the electronic device (100) among the components of the intelligent construction equipment recommendation system (e.g., memory (110), processor (120), communication interface (130), and display device (140) of FIG. 1) may be configured to perform the operations of FIG. 3.
[0111] In the following embodiments, the operations S310 to S350 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel. Additionally, content corresponding to or overlapping with the aforementioned details in relation to FIG. 3 may be briefly explained or omitted.
[0112] According to one embodiment, the processor (120) can obtain field operation data including the progress of each process of the target building under construction, material status data, a list of construction equipment that can be input for each process, the average breakdown interval for each construction equipment, and the operating cost for each construction equipment (S310).
[0113] The electronic device (100) obtains “field operation data” including the progress of each process of the target building under construction, material status data, a list of construction equipment available for each process, the average failure interval for each piece of equipment, and the operating cost for each piece of equipment.
[0114] For example, "progress by process" can be obtained from a process management system (e.g., schedule management tool, site schedule, WBS management DB, daily work log system) and can be expressed in various formats, such as the ratio of actual work to plan, cumulative work volume by process (e.g., pouring volume, installation quantity), work completion rate (%), or schedule deviation (days / hour).
[0115] For example, "material status data" can be aggregated from material outbound and inbound records, inventory systems, supplier delivery data, on-site weighing / scan records, etc., and may include real-time or near-real-time remaining quantities, scheduled deliveries for the day, and delivery risks of materials critically consumed in specific processes (e.g., rebar, formwork materials, waterproofing materials, piping, finishing materials, etc.).
[0116] For example, the “list of equipment available for input by process” may be configured to include not only equipment already brought into the site but also equipment available for rental, equipment owned by partner companies, and equipment that can be converted to nearby sites, and “available for input” may mean conditions that satisfy physical feasibility of entry (e.g., transport / access routes / installation space), regulatory / permit restrictions (e.g., equipment usage permits, night work restrictions), work compatibility (e.g., process-equipment matching basis), and safety requirements (e.g., rated load, working radius).
[0117] For example, the average time between failures (e.g., MTBF, etc.) can be calculated based on equipment maintenance history or manufacturer's recommended data, rental company operation data, and field inspection records, and "operating costs per equipment" can be calculated as costs per unit period (e.g., hourly or daily) including fuel costs, electricity costs, rental fees, depreciation, operator labor costs, maintenance costs, etc.
[0118] As an example, information may be collected indicating that the progress of “concrete pouring (process code C-120)” at Site A is delayed by 2 days compared to the plan, and that while ready-mix concrete can be supplied normally in the material status, the placement of pump trucks required for pouring is unstable. In this case, the equipment list may include two pump trucks (pump truck-1, pump truck-2) and one replaceable small boom pump (boom pump-3), and the data may be organized such that pump truck-1 has a short average breakdown interval and low operating costs due to a recent history of frequent breakdowns, whereas pump truck-2 has a long average breakdown interval but somewhat higher operating costs. To integrate this data into a single format, the electronic device (100) [organizes] the time unit (minute / hour / day) and quantity unit (m²) of the data coming from different systems. 3Preprocessing can be performed to standardize cost units (won / hour, won / day) and correct missing values with recent observations or conservative estimates. Additionally, to ensure data reliability, if the discrepancy between sensor data and work log reports exceeds a threshold range, a “validation needed flag” can be applied to lower the weight in subsequent decisions or require user confirmation.
[0119] According to one embodiment, the processor (120) can determine, based on field operation data, whether there is a target process among a plurality of processes in progress on a target building that is in a delayed state and is set to be able to proceed in parallel with another process (S320).
[0120] The electronic device (100) checks, based on field operation data, whether there is a target process among multiple ongoing processes that is in a “delayed state” and is “set to be able to proceed in parallel with other processes simultaneously.”
[0121] For example, a "delayed state" can be determined by synthesizing multiple signals, going beyond simply meaning a low progress rate, such as (i) deviations from the actual schedule compared to the planned schedule, (ii) reduced productivity based on material consumption rates, (iii) reduced equipment utilization (increased equipment idle time), and (iv) constraints on available working time. Whether parallel execution is possible can be determined by "process attribute information" established by considering the sequential relationships between processes (e.g., network schedule, CPM relationships), the possibility of interference within the same work area (e.g., movement path conflicts, overlapping equipment working radii), and safety regulations (e.g., processes prohibited from simultaneous operation). For instance, the exterior scaffolding installation process and some internal equipment piping processes can be performed in parallel if they are separated by building or area, but the parallel execution of concrete pouring and rebar placement on the same floor may be restricted due to the process sequence.
[0122] From a scenario perspective, even if “external waterproofing (process W-210)” at site B appears to be delayed, if “external wall finishing (process F-310)” in the same area already requires the introduction of equipment and the installation of work platforms, parallel work may be restricted for safety or spatial interference. In this case, the electronic device (100) may classify it as unsuitable for parallel work based on process attribute information and exclude it from the recommended processes. Conversely, if “drainage facilities (process M-410)” in the underground parking area is delayed, the work area may be separated from “internal temporary construction (process T-110)” on the ground level and classified as suitable for parallel work. Additionally, to increase the reliability of the delay judgment, if the core material consumption rate of the corresponding process in the material status data is below a certain percentage of the standard (e.g., less than 70%), it may be considered as “activity degradation” and distinguished from a simple reporting delay (e.g., input delay). This determination of whether parallelization is possible or not can be automated by combining pre-established process relationship tables (e.g., inter-process dependency mapping tables) and site zone mapping information (e.g., Zone / Floor / Tool), and an interface may also be provided that allows users to manually adjust the parallelization status according to site policies.
[0123] According to one embodiment, when a target process is identified, the processor (120) can check the standard efficiency index and standard cost limit set for the target process (S330).
[0124] When the target process is identified, the electronic device (100) checks the standard efficiency index and standard cost limit set for the process. The standard efficiency index can be set to reflect the balance of productivity and stability required depending on the nature of the process. For example, for processes that cause significant cascading delays when the process is interrupted, such as pouring and lifting, a standard can be set with a higher weighting for “failure stability (i.e., average interval between failures),” and for processes that require pushing volume within a short period, a standard can be set with a higher weighting for “work volume per unit time.” The standard cost limit can be calculated by reflecting the project budget, current month execution plan, equipment rental contract conditions, fuel unit price fluctuations, whether night work is performed (or additional costs), etc., and even for the same process, the limit may vary depending on the urgency (or degree of delay) and whether an alternative process exists.
[0125] As an example, if a delay occurs in “earthwork (Process E-100)” and the site intends to recover the volume by increasing the deployment of excavators but finds it difficult to rent additional expensive equipment due to budget constraints, the standard cost limit can be set relatively low. On the other hand, if the waiting cost for subsequent processes, such as structural casting, is very high, the standard cost limit can be set high, but the policy can be designed to require a high standard efficiency index for equipment with a low risk of breakdown.
[0126] For example, the electronic device (100) may include a rule-based module that stores basic criteria (or templates) for each process type and adjusts the criteria values according to site conditions (e.g., delay days, material supply stability, weather risk, equipment availability). Additionally, when a site manager or public affairs officer selects an operation mode such as “cost priority / time priority / safety priority” on the user terminal (210), the weighting structure of the standard efficiency index and the standard cost limit can be configured to switch dynamically.
[0127] According to one embodiment, the processor (120) can identify at least one target equipment corresponding to a target process through a construction equipment list and can determine the efficiency index of each of the at least one target equipment based on the work volume per unit time, average breakdown interval, and operating cost for each of the target equipment's target process (S340).
[0128] The electronic device (100) identifies at least one target equipment corresponding to the target process through a construction equipment list and checks the efficiency index for each target equipment from the perspective of process execution.
[0129] Here, “identifying target equipment” goes beyond simply verifying the correct equipment type and may include a filtering process that considers (i) the type of equipment technically suitable for the relevant process (e.g., crane for lifting, pump truck for pouring), (ii) site physical conditions (e.g., access width, working radius, floor height, ground bearing capacity), (iii) safety limitations (e.g., rated load, presence of safety devices), (iv) available operating hours (e.g., noise regulation time zones, night work restrictions), and (v) availability of personnel / operators. In other words, equipment that cannot actually be deployed, even if it exists on the list, may be excluded or processed with a lower priority.
[0130] In the efficiency index verification step, three factors such as the amount of work per unit of time per piece of equipment (e.g., excavator excavation volume per hour, pump truck pouring volume per hour, crane lifting cycles per hour), average breakdown interval (e.g., frequency of breakdowns per operation period), and operating costs (e.g., including fuel, rental, maintenance, and operator costs) may be reflected to a minimum. For example, when there are equipment A and B that can be deployed in the same process, if A has a high amount of work but a short breakdown interval, and B has a somewhat lower amount of work but a long breakdown interval and high costs, the electronic device (100) can calculate the relative efficiency index of the two pieces of equipment differently depending on the urgency of the process and the reference value.
[0131] For example, the electronic device (100) can calculate a comprehensive score by normalizing the units of each element by standardizing them with a standard workload, standard failure interval, and standard cost, and applying a weighting factor set for each process type. Additionally, since the data may not be up to date, realism can be enhanced by giving higher weight to operation records from a recently set period (e.g., the last month) or by correcting the stability factor by reflecting the condition grade of each equipment (e.g., immediately after maintenance, imminent maintenance, etc.).
[0132] According to one embodiment, the processor (120) identifies a final equipment having an efficiency index greater than or equal to a reference efficiency index and an operating cost less than or equal to a reference cost limit as recommended equipment for a target process, and can provide recommendation information to a user terminal including an expected time of completion of the target process when the target process is performed through the final equipment (S350).
[0133] The electronic device (100) identifies equipment whose calculated efficiency index is greater than or equal to the standard efficiency index and whose operating cost is less than or equal to the standard cost limit as “final equipment,” confirms it as recommended equipment for the target process, and provides recommendation information including “expected completion time of the target process” when the final equipment is introduced to the user terminal (210).
[0134] Here, "recommendation information" is not merely a short message such as "Equipment A recommended," but can be configured to enable field managers to make immediately actionable decisions. For example, the recommendation information may include (i) the recommended equipment identifier (equipment ID / model / rental company), (ii) a summary of the reason for the recommendation (balance of workload, failure reliability, and cost suitability), (iii) the estimated completion time (date / time), (iv) cost impact (increase / decrease from baseline), (v) a risk summary (results of adjustment for weather risk and failure risk), and (vi) alternative candidates (next-best equipment).
[0135] The calculation of the estimated completion time can be performed based on the remaining workload of the process and the workload of the equipment (i.e., throughput per unit time), and can additionally reflect realistic variables such as material supply speed, available working hours (e.g., day / night, noise-sensitive time), weather risks (e.g., inability to work during precipitation), and equipment setup time (e.g., delivery, installation, test run, etc.).
[0136] For example, the remaining volume of the pouring process is 120m 3 The recommended pump truck has an hourly pouring capacity of 30m 3 If so, it takes 4 hours by simple calculation, but in reality, time for ready-mix concrete arrival intervals, waiting for quality inspection, worker shifts, curing and safety inspections is included, so the electronic device (100) can calculate the estimated completion time by reflecting the average delay coefficient of similar past processes (e.g., 1.2 times) or buffer time according to site policy. Before the recommended equipment is finalized, an interactive UI such as “Approve / Hold / Select Replacement Candidate” may be provided to the user terminal (210), and when the user selects a specific piece of equipment, the electronic device (100) can save the selection result as a log and use it as training data to improve the quality of future recommendations. In addition, if there is no equipment that meets the criteria in the recommendation results, guidance is provided to naturally transition to a “criteria relaxation option” (e.g., a candidate possible when the cost limit is increased) or “perform an alternative process,” thereby enabling the implementation to maintain the decision-making flow without interrupting operations.
[0138] FIG. 4 is a flowchart of the operation of an intelligent construction equipment recommendation method according to one embodiment of the present invention.
[0139] According to one embodiment, the components of an intelligent construction equipment recommendation system can perform the operations disclosed in FIG. 4. For example, at least some of the components included in the electronic device (100) among the components of the intelligent construction equipment recommendation system (e.g., memory (110), processor (120), communication interface (130), and display device (140) of FIG. 1) may be configured to perform the operations of FIG. 4.
[0140] In the following embodiments, the operations S410 to S420 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel. Additionally, content corresponding to or overlapping with the previously described content in relation to FIG. 4 may be briefly explained or omitted.
[0141] According to one embodiment, the processor (120) can calculate the material consumption rate per unit time of the target material corresponding to the target process from the material status data during the progress of the target process (S410).
[0142] The electronic device (100) calculates the material consumption rate per unit time input during the progress of the “target material” corresponding to the target process from the material status data.
[0143] Here, “material status data” does not refer merely to simple inventory quantities, but may consist of comprehensive data including (i) records of material receipt and shipment (or inflow and outflow), (ii) records of on-site input (or use), (iii) supplier delivery slips / transaction details, (iv) warehouse (or storage area) scan / weighing records (e.g., barcode, RFID, QR, weighing device, etc.), and (v) records of material requests and distribution by process.
[0144] Here, “target materials” can be defined as core consumables pre-mapped according to the process type, for example, ready-mix concrete and admixtures for the concrete pouring process, rebar / binding wire for the rebar placement process, waterproofing sheets / coating materials for the waterproofing process, and piping materials / valves for the equipment piping process. The electronic device (100) can automatically identify target materials corresponding to a specific process through a mapping table linking the process code (WBS) and the material code (or material master), and the site manager can also set the target materials for each process to be added and / or excluded.
[0145] The electronic device (100) sets an observation period (e.g., the last 1 hour, 4 hours, 1 day, or work shift time) to calculate the consumption rate, and then estimates or determines the “actual input amount (or, consumption amount)” of the target material within that period. At this time, the actual input amount can be calculated in various ways, for example, (a) a method of considering the warehouse output amount as the input amount, (b) a method of considering the work area inflow amount (movement amount by floor / zone) as the input amount, (c) a method of calculating inversely from equipment measurement (e.g., ready-mix concrete weighing records, pump truck pouring logs, mixing equipment weighing) or work reports (e.g., pouring amount, installation quantity). Additionally, considering the case where the material is “outgoing but not actually used and is stored,” the electronic device (100) may be implemented to conservatively estimate the consumption amount or assign a “verification needed” flag if the discrepancy between the outgoing amount and the work result (e.g., actual installation quantity, pouring volume) exceeds a specific threshold. For example, if rebar is shipped out but work in the area is stopped and only stacked, the consumption rate based on the simple shipment amount may be overestimated, so the electronic device (100) can correct the “actual usage” by reflecting the estimated stacking amount based on field reports or photo records.
[0146] As an example, if 120 m of PVC pipe material is shipped out in the last 4 hours during the basement drainage facility process and the actual construction completion report is tallied at 100 m, the electronic device (100) may set the actual usage to a range of 100 to 120 m, taking into account the possibility of omission / disposal / stacking, or apply a correction rule (e.g., prioritize the report basis, and the shipment basis is the upper limit). Subsequently, the material consumption rate per unit time is calculated by dividing the consumption amount by the observation time, and the time unit can be standardized to minutes / hours / days according to the site policy. In addition, for sites where working hours are limited (e.g., noise-sensitive time zones, no night work, lunch break, etc.), the electronic device (100) may calculate the consumption rate by reflecting the "effective working time (working window)" instead of the simple elapsed time. For example, even if 8 hours have elapsed, if the actual working time is 6 hours, the process activity can be more accurately reflected by applying 6 hours as the denominator for the consumption rate calculation.
[0147] According to one embodiment, the processor (120) can determine that the target process is in a delayed state if the material consumption rate per unit time of the target material is less than 70% of the standard material consumption rate set corresponding to the type of the target process (S420).
[0148] The electronic device (100) checks the target process in a delayed state when the material consumption rate per unit time of the calculated target material is less than 70% compared to the standard material consumption rate set in correspondence with the type of target process.
[0149] Here, “standard material consumption rate” refers to the expected speed of material input when a specific process is performed normally, and can be defined as a reference value set in advance based on process type (e.g., rebar placement, formwork installation, pouring, waterproofing, pipe installation, etc.), work environment (e.g., indoor / outdoor), work area conditions (e.g., narrowness, number of floors, delivery flow), equipment input level (e.g., 1 / 2 pieces of equipment), manpower level (e.g., size of work crew).
[0150] Here, the "standard material consumption rate" may be extracted from past performance data of similar projects, or an initial value may be set based on specifications, standard cost estimates, and supplier productivity standards, and then adjusted according to site conditions. The electronic device (100) may include a standard table storing standard consumption rates by process type, and may apply site-specific correction coefficients to reflect special conditions of a specific site (e.g., narrow urban area, import restrictions, weather risks, etc.).
[0151] Here, the critical condition of “less than 70%” can be utilized not merely as an abstract indicator of low progress, but as a standard to quantitatively capture a state where actual production activities have slowed down. For example, the standard consumption rate of the waterproofing process is 10 rolls per hour (or, m 2(Converted value) If the actual observed consumption rate is 6 rolls per hour (or 60%), the electronic device (100) can determine that the process activity has significantly deteriorated compared to the standard and confirm it as a delayed state. At this point, it is important to note that the decrease in the material consumption rate may differ depending on whether it is due to a “material shortage,” “equipment / personnel problem,” or “inability to work (weather / complaints / safety).” Therefore, the electronic device (100) can be further implemented by classifying candidates for the cause of the delay by checking, along with the determination of the delayed state, whether there is an inventory shortage (e.g., whether the inventory is below the critical inventory level), a delivery delay flag (e.g., possibility of failure to receive on the same day), and constraints on available working hours (e.g., weather risk date). For example, if the material consumption rate is low but the inventory is sufficient and the available working hours are normal, the possibility of an equipment efficiency problem (breakdown / idle) increases, and if the inventory is below the critical level, it can be classified as a material supply problem.
[0152] Additionally, since delay determination based on consumption rate can be falsely detected by accidental fluctuations at a single point in time (e.g., brief waiting, safety inspection, material sorting time), the electronic device (100) may apply “continuous observation” or “cumulative observation” rules. For example, it may be configured so that a delay is not immediately confirmed even if the consumption rate in 30-minute intervals is less than 70% once, but is confirmed only when it is less than 70% in two or more consecutive intervals or when the cumulative consumption rate over the last 4 hours is less than 70%. Furthermore, thresholds may be set differently depending on the process type; for short-duration intensive processes like pouring, the threshold rule may be adjusted so as not to react sensitively to short observation intervals because instantaneous fluctuations are large, while for relatively continuous work processes like pipe installation, the threshold rule may be adjusted to quickly detect continuous degradation. This threshold determination structure increases the reliability of identifying delayed processes and has the effect of suppressing the subsequent equipment recommendation logic from being unnecessarily triggered.
[0154] According to one embodiment, the operation of checking the efficiency index of each target equipment may include the operation of calculating a first efficiency factor by normalizing the work volume per unit time of the target equipment to a set reference work volume, the operation of calculating a second efficiency factor by normalizing the average failure interval of the target equipment to a set reference failure interval, the operation of calculating a cost correction factor by normalizing the operating cost of the target equipment to a set reference cost, and the operation of calculating an efficiency index by applying a weighting coefficient set for each of the first efficiency factor and the second efficiency factor and subtracting the cost correction factor.
[0155] The electronic device (100) calculates a first efficiency factor by normalizing the work amount per unit time of the target equipment to a “set standard work amount.”
[0156] Here, "work volume per unit of time" can be defined in different forms depending on the process type. For example, an excavator has an excavation load per hour (m²). 3 / h), concrete pump truck pouring rate per hour (m²) 3 / h), for cranes, lifting cycles per hour (cycles / h) or lifting weight per unit time (ton / h), for aerial work platforms, working area per hour (m² 2 It can be defined as / h) or the number of completed work items (EA / h), etc. The electronic device (100) can select a meaningful work volume indicator in each process through “measurement unit mapping information” linked to the process code and equipment type, and convert it into a work volume of the same process standard so that comparison between different equipment is possible.
[0157] The standard workload can be set by including (i) the average productivity of the same process in the past, (ii) the performance specifications of the manufacturer / rental company, (iii) standard cost estimates or internal standards, and (iv) a correction value that reflects site conditions (e.g., delivery route, work radius, ground condition, number of floors, etc.). For example, even with the same pump car, the actual pouring speed may decrease due to pipe installation, vehicle waiting, etc., at a narrow urban site, so the electronic device (100) can apply a “site condition coefficient” to adjust the standard workload to suit the site. Normalization can generally be performed by dividing the target equipment workload by the standard workload, and this value can be interpreted as meaning above-average productivity if it is 1.0 or higher, and below-average productivity if it is lower.
[0158] As a specific example, in the pouring process, the standard work volume is 25m 3 It is set to / h, and the workload based on the recent performance of Equipment A is 30m 3 If it is / h, the first efficiency factor can be calculated as 1.2. On the other hand, equipment B is 20m 3 If the rate is / h, it can be calculated as 0.8. Here, the “work volume based on recent performance” can be estimated as the average of the last n operations (e.g., the last 5 pours) or the moving average of the last 2 weeks to ensure it is not influenced by fluctuations in a single date. Furthermore, in environments where equipment work volume data is not directly collected, the work volume can be calculated by inversely combining process performance (e.g., pour volume) and equipment operating time (e.g., start-up time, operator log). This normalization structure enables performance comparisons between equipment without unit differences and provides a foundation for stable summation in the subsequent weighted combination stage.
[0159] The electronic device (100) calculates a second efficiency factor by normalizing the average failure interval of the target equipment to a “set reference failure interval.”
[0160] Here, the "average interval between failures" is an indicator representing the reliability and continuous operation of the equipment, and can serve as a very important variable in situations where process delays need to be recovered. For example, even if the equipment has high productivity, if work is interrupted due to a failure, the completion time of the process may actually be delayed; therefore, the electronic device (100) configures the efficiency by reflecting not only the workload factor but also the failure stability factor.
[0161] The standard failure interval can be set by equipment type and / or model, and can be calculated based on reliability data provided by the manufacturer, maintenance history from the rental company, on-site operational logs, or statistics from similar sites. Additionally, since the definition of a failure itself may become ambiguous, in this embodiment, operationally significant events such as “failures causing work stoppage (e.g., inability to start, major drive system malfunction, stoppage due to hydraulic leakage)” are defined as failures, while simple consumable replacements or minor warning alarms are distinguished so as not to be counted as failures. This definition contributes to improving the quality of equipment history data and ensuring fairness in comparisons between equipment.
[0162] The normalization method can be implemented as a value obtained by dividing the average failure interval by the reference failure interval, and if it is 1.0 or higher, it may mean that it is more stable than the average, and if it is less than 1.0, it may mean that the risk of failure is relatively high. For example, if the reference failure interval is 200 hours and the average failure interval of equipment A is 240 hours, the second efficiency factor becomes 1.2, and if equipment B is 150 hours, it becomes 0.75. Here, since the average failure interval may miss recent deterioration of condition if only the long-term average of the past is reflected, the electronic device (100) may give a higher weight to the failure interval in the period after recent maintenance, or may transform it into a failure stability factor that strengthens the “recent condition” by reflecting the result of the remaining lifespan prediction of the equipment as a correction factor.
[0163] In addition, for new equipment or equipment with missing history for which failure interval data is insufficient, the electronic device (100) can apply the group average value of equipment of the same model / same class as a substitute value, while applying an “uncertainty penalty” indicating low data reliability to prevent excessive recommendations. This method contributes to maintaining the stability of the recommendation system while absorbing the problem of missing data that commonly occurs in practice.
[0164] The electronic device (100) calculates a cost correction factor by normalizing the operating cost of the target equipment to a “set standard cost.”
[0165] Here, "operating costs" are a key factor in ensuring that equipment recommendations do not conflict with on-site budget constraints, and can be calculated in terms of the total cost required to operate the equipment in the actual field, rather than just the rental fee.
[0166] For example, operating costs may include rental fees (hourly / daily), fuel or electricity costs, labor costs for operators or equipment operators, costs for consumables (lubricants / filters), and the expected value of maintenance and / or inspection costs (e.g., monthly maintenance costs converted to an hourly rate). Additionally, if night work or holiday work is included, additional costs (e.g., surcharge labor costs, lighting / safety management costs, etc.) may be included in operating costs.
[0167] The standard cost can be set according to the “standard cost of typically input equipment” for each process type or the site budget plan (or equipment cost execution plan). For example, the site may have an internal standard requiring that equipment costs for a specific process be kept below 2 million won per day; in this case, the standard cost can be set on a daily basis for comparison. Normalization can be identified by the value obtained by dividing operating costs by the standard cost; a value greater than 1.0 indicates that the equipment is expensive compared to the standard, while a value less than 1.0 indicates that the equipment is advantageous in terms of cost. However, since the cost correction factor in the present invention may be applied in a “direction that lowers efficiency,” the design may be such that the penalty in the final efficiency index increases as the cost normalization value increases.
[0168] As an example, if the standard cost is 300,000 won per hour and the operating cost of equipment A is 270,000 won, the cost correction factor becomes 0.9. If equipment B is 360,000 won, it becomes 1.2. Since consistency of units is important here, the electronic device (100) can convert the operating cost into the same unit based on the expected work time or expected operating time of the recommended target process. For example, even for daily rental equipment, if the process is performed for only 4 hours, the hourly converted unit price can be viewed differently, so contract conditions such as “conversion based on actual operating time” or “reflection of minimum contract billing unit (e.g., half day / 1 day)” can be reflected in the cost calculation. This implementation increases field applicability by ensuring that the recommendation results do not deviate from actual contracts and execution.
[0169] The electronic device (100) applies a weighting factor set for each of the calculated first efficiency element (i.e., productivity element) and second efficiency element (i.e., stability element), and subtracts a cost correction factor to calculate the efficiency index of the target equipment.
[0170] The technical significance of this step lies in moving beyond simple equipment selection based solely on productivity or cost, and enabling decision-making by integrating multiple factors critical to process operations (e.g., productivity, failure stability, and cost) into a single metric. Particularly in situations involving the recovery of delayed processes, even if equipment with high short-term productivity appears advantageous, it is necessary to evaluate stability factors with greater weight; a high risk of downtime due to failure can delay the overall completion time. Conversely, in projects under significant cost pressure, the influence of cost deduction items can be relatively increased to ensure that recommended equipment is operated within the budget limits.
[0171] Weighting factors can be set according to process type or field operation mode. For example, the system can be configured such that the productivity weight (a) is increased in "Condition-first mode," the stability weight (b) is increased in "Safety / Stability-first mode," and the cost reduction factor (c) is increased in "Budget-first mode." Additionally, weights can be automatically adjusted based on the characteristics of the process itself (e.g., risk of cascading delays, tolerance of work stoppages). For instance, since the stoppage cost is high for a pouring process, the stability weight can be relatively increased, while for a simple transport process, the productivity weight can be increased. In this case, various numerical designs can be implemented, such as normalizing the sum of the weights to 1 (e.g., a+b=1) or setting the cost reduction factor on a separate scale.
[0172] As an example, it can be assumed that in a delayed rebar placement process, equipment A (e.g., small crane assist) has a first efficiency factor of 1.1, a second efficiency factor of 0.9, and a cost correction factor of 0.8, while equipment B (e.g., large crane conversion) has a first efficiency factor of 1.3, a second efficiency factor of 1.1, and a cost correction factor of 1.4. In the schedule-first mode, B's productivity advantage is significantly reflected, but in the budget-first mode, the cost reduction is large, so A may have the advantage in the final efficiency index. In other words, even with the same data, recommendations can vary depending on operational goals, which aligns with the reality of on-site decision-making.
[0173] For example, the electronic device (100) can sort the equipment in descending order after calculating the efficiency index and determine the equipment that satisfies the standard efficiency and standard cost limits as recommended candidates. In addition, if the difference in efficiency index is small (e.g., the difference between the top two pieces of equipment is less than a threshold), it can be treated as a “tie candidate” and presented to the user terminal (210) two or three candidates along with scores for each item (productivity / stability / cost), thereby inducing the user to make a final selection by considering the field situation (e.g., feasibility of entry, operator supply, etc.).
[0175] According to one embodiment, the operation of providing recommendation information may include: collecting weather forecast data of an area where a target building exists from an external server and checking whether the target process is an outdoor operation from the attribute information of the target process; if it is confirmed that the target process is an outdoor operation, checking from the weather forecast data a risk date on which the probability of precipitation during the execution of the target process until the expected completion time of the target process is expected to be greater than a threshold probability; and if the risk date is greater than or equal to a threshold number of days, providing alternative recommendation information to a user terminal that suggests prioritizing the execution of an indoor workable process among the remaining processes excluding the target process.
[0176] The electronic device (100) collects weather forecast data for the area where the target building is located from an external server (220) and checks whether the process is an outdoor operation by referring to attribute information of the target process.
[0177] Here, the "external server (220)" can be linked with a public weather API or a private weather service to provide variables that affect the performance of the process, such as the probability of precipitation, amount of precipitation, wind speed, perceived temperature, possibility of snowfall, risk of lightning strike, fine dust / yellow dust, etc.
[0178] The electronic device (100) maps the forecast area based on the address (or administrative district) or site coordinates (GPS) of the target building and can request data for the required range by considering the time resolution of the forecast (e.g., 1 hour unit / 3 hour unit / day unit) and the validity period (e.g., 48 hours / 7 days).
[0179] Here, "process attribute information" is metadata pre-set for each process code and may include not only "outdoor / indoor distinction," but also weather sensitivity (e.g., sensitivity to precipitation / wind speed / temperature), workability conditions (e.g., suspension when wind speed exceeds 10 m / s), equipment usage restriction conditions (e.g., crane operation prohibited when there is a risk of lightning), and safety and quality constraints (e.g., waterproof coating processes are sensitive to humidity / precipitation), even for outdoor processes.
[0180] For example, “exterior wall painting / waterproofing” can be set to be outdoors and highly sensitive to precipitation and humidity, and “steel lifting” can be set to be outdoors and highly sensitive to wind speed. The electronic device (100) can be implemented to enter a weather risk assessment stage when the target process is identified as outdoors, and to skip the weather risk assessment or reflect it with a low weight when it is identified as indoors.
[0181] In a scenario where the exterior wall waterproofing process is delayed and equipment recommendation is performed, the electronic device (100) collects the probability of precipitation and hourly precipitation forecast for the next 72 hours from an external server and confirms that the process is registered in the attribute information as “an outdoor process and a precipitation-sensitive process.” On the other hand, since the underground floor piping installation process is an indoor process, weather data for the same period may be maintained only at a reference level or excluded from the risk date determination.
[0182] The electronic device (100) defines the period for performing the target process from weather forecast data until the expected completion time of the target process, and identifies a date (or time period) within that period where the probability of precipitation is scheduled to be greater than or equal to a threshold probability as a “risk date.”
[0183] Here, “expected completion time” may refer to the expected completion time of the process calculated when the recommended equipment is introduced, and the electronic device (100) may be configured to re-calculate the risk date when the expected completion time is updated due to changes in the recommended equipment or efficiency correction. That is, the weather risk assessment may be implemented not as a fixed, single judgment, but as a dynamically updated method based on changes in the recommended results.
[0184] In the present disclosure, the “critical probability” may be set differently depending on the type of process. For example, processes that are very sensitive to precipitation, such as waterproofing and painting, may be judged conservatively by setting the critical probability low (e.g., 30–40%), while processes such as earthwork and rebar may be set the critical probability somewhat high (e.g., 60–70%). In addition, it may be extended to consider not only simple precipitation probability but also complex conditions such as precipitation amount (e.g., 1 mm / h or more), continuous precipitation duration (e.g., lasting for 2 hours or more), humidity threshold, and whether wind speed is present. Consequently, the electronic device (100) may use the precipitation probability as a minimum requirement and consider other indicators together if necessary.
[0185] In a scenario, when the target process is an exterior work and the expected completion time is calculated as “18:00 the day after tomorrow,” the electronic device (100) checks the forecast for the range “today to 18:00 the day after tomorrow” and if the forecast predicts an 80% probability of precipitation between 9:00 AM and 12:00 PM tomorrow, it registers that time period as a risk date (or, risk time period). At this time, the risk date is not simply lumped together as “tomorrow,” but if the forecast is in hourly units, it can be managed as a time-based risk section such as “tomorrow 09:00 to 12:00.”
[0186] In addition, since working hours are limited in actual field conditions (e.g., 08:00 to 17:00), the electronic device (100) may be implemented by referring to process attribute information or field settings (e.g., valid working hours) to count only the dangerous time zones within the working time zone. For example, in a field where night work is prohibited, even if the late-night precipitation forecast is calculated as a dangerous date, the actual impact on work is low, so it may be separately indicated or a low weight may be applied.
[0187] The electronic device (100) provides alternative recommendation information to the user terminal (210) to “prioritize performing an indoor workable process among the remaining processes excluding the target process” instead of a strategy of pushing forward with the target process as is when the number of confirmed risk dates (or, accumulation of risk time zones) is greater than or equal to a threshold number of days.
[0188] Here, the critical days can be set in advance according to on-site management policies (e.g., weather sensitivity, construction time margin, risk of contractual liquidated damages) and may also be set differently depending on the type of process. For example, for waterproofing processes where quality defects are critical during precipitation, the critical days can be set to 1 day so that replacement is recommended even if the risk is only one day, and for simple stockpiling / transporting processes, the critical days can be set to 2 to 3 days.
[0189] The alternative recommendation information can be configured in a form that can be immediately executed at the actual site, rather than as an abstract instruction such as “perform an indoor process.” For example, an electronic device (100) can generate a list of 1 to N alternative processes by searching for process candidates classified as possible for indoor work that can run parallel with the target process in the process table data, and then sorting them by priority based on (i) processes with a significant effect on shortening the lead time upon switching, (ii) processes for which preconditions are already met (e.g., material procurement and approval completion), and (iii) processes for which input resources do not overlap (e.g., processes with minimal equipment and personnel conflict). Additionally, to make it easy for the user to understand, it can provide “expected effects of performing the alternative process (e.g., workload available today, expected range of delay recovery)” and “preparations required for switching (e.g., material delivery, work area cleanup, safety measures).” Through this, the site manager can prevent causing quality and safety issues by forcing outdoor processes on days with high weather risks and can operate in a way that maintains productivity through indoor processes.
[0190] As an example, if the exterior painting process is delayed and recommended equipment is selected, but it is confirmed that one of the next two days is at risk of precipitation (e.g., above a critical probability), the electronic device (100) may first suggest candidate processes that can be performed indoors, such as “interior electrical wiring arrangement process,” “interior gypsum board installation process,” and “machine room piping prefabricated assembly process.” In this case, the alternative recommendation may not simply be “switch to an indoor process,” but may include a mixed schedule (or switching) strategy in the form of “performing an indoor process during the time of risk of precipitation, and resuming the exterior process when the risk is resolved.” For example, if the risk date is above a critical number of days, an alternative recommendation notification is displayed on the user terminal (210), and if the user selects an alternative process, the electronic device (100) may be configured to present a simulation result in which a short-term schedule (e.g., 1-3 days Look-ahead) on the process table is automatically rearranged. In addition, if no alternative indoor process exists, alternative guidance such as “accept risk and proceed” or “recalculate estimated completion time” can be provided to minimize decision gaps.
[0192] According to one embodiment, an intelligent construction equipment recommendation method may include, when a target process is identified, acquiring real-time status data regarding the target equipment from at least one of a vibration sensor, a temperature sensor, and a current sensor attached to the target equipment; predicting the remaining usable time of the target equipment through a machine learning model based on the real-time status data; calculating a failure risk correction coefficient by comparing the remaining usable time with the average failure interval; recalculating a corrected efficiency index by reflecting the failure risk correction coefficient in the efficiency index; and re-selecting recommended equipment based on the corrected efficiency index.
[0193] The electronic device (100) obtains real-time status data of the equipment from at least one of a vibration sensor, a temperature sensor, and a current sensor attached to the target equipment at the time when the target process is identified (e.g., when the equipment recommendation procedure is initiated by identifying it as a delayed process).
[0194] Here, “real-time” may mean continuous or periodic sampling in seconds / minutes, and may be set to intervals of 1 to 10 seconds or 1 minute, etc., depending on the field communication environment (e.g., cellular / Wi-Fi / LPWAN) and equipment characteristics.
[0195] In the present disclosure, the "sensor" may be implemented as a CAN / OBD measuring device embedded in the equipment itself, telematics data provided by an engine controller (ECU), or a rear-mounted sensor module, and the sensor data may be transmitted to an electronic device (100) through a wired / wireless gateway, or configured to transmit only summary features after primary preprocessing at the equipment terminal.
[0196] Vibration sensor data is useful for early detection of abnormalities in the equipment's drive system (motor / hydraulic pump / gear), and temperature sensor data can reflect deterioration conditions such as engine overheating, hydraulic oil temperature rise, and bearing overheating. Current sensor data can be used as an indicator of overload, insulation degradation, abnormal power consumption, etc. in electric or hybrid equipment. The electronic device (100) can generate not only raw sensor data but also derived indicators such as RMS, peak value, energy in a specific frequency band, temperature rise rate, and frequency of current spike occurrence. In particular, since there is a lot of noise in the field, the electronic device (100) can increase the reliability of the status data by performing basic noise suppression preprocessing such as moving average, median filter, and interval averaging.
[0197] From a scenario perspective, if excavator equipment A is selected as a candidate for delayed process input, the electronic device (100) can check the vibration RMS and temperature rise trends over the past 30 minutes to 2 hours. If the engine temperature rises rapidly from the beginning of the operation and the vibration RMS appears higher than the usual standard, there is room to conclude that the equipment is likely to soon fail or experience performance degradation. Conversely, if the sensor signal is stable and the temperature is maintained within the normal range, the condition of the equipment can be interpreted as good.
[0198] For example, for equipment without sensors, the procedure can be maintained by treating alternative data such as (i) recent maintenance records, (ii) operator inspection checklists, and (iii) condition ratings provided by the rental company as condition data, and in this case, the safety of the recommendation can be ensured by assigning an uncertainty flag.
[0199] The electronic device (100) predicts the remaining useful life (RUL) of the target equipment through a machine learning model using acquired real-time status data as input.
[0200] Remaining usable time (RUL) can be defined as “the estimated time of operation from the present until the equipment fails to continue operation” and can be output in time units (e.g., hours, days).
[0201] Machine learning models can be configured to learn historical data obtained from the field operating environment (e.g., sensor time series, failure timing, maintenance history, operating patterns, environmental conditions) to estimate the probability that a specific state pattern will lead to a future failure or the time remaining until failure.
[0202] For example, the form of the model can be implemented in various ways. For instance, an electronic device (100) can directly predict RUL using a regression model (e.g., random forest regression, gradient boosting, neural network regression, etc.) with sensor feature values (e.g., vibration RMS, specific frequency band energy, temperature rise rate, current variability, etc.) as input. Additionally, for equipment where time series patterns of vibration / temperature / current are important, a time series model such as LSTM / GRU can be used to be configured to reflect both “trends” and “abrupt changes.” Considering field applicability, the electronic device (100) can be implemented to calculate a confidence interval (or, error range) or confidence score for the RUL value output by the model, and to conservatively adjust the recommendation when the prediction is uncertain.
[0203] From a scenario perspective, when pump truck equipment B is a candidate for a delayed pouring process, the electronic device (100) can detect an increase in abnormal high-frequency components in the temperature rise pattern and vibration spectrum over the past hour. Based on the learning result that these patterns have repeatedly appeared just before hydraulic pump failure in the past, the learning model can predict the RUL of equipment B as “about 6 hours.” On the other hand, if equipment C has a sensor pattern within the normal range and has a low history of failures, the RUL can be predicted as “about 60 hours or more.” As such, since the RUL reflects the “current state” more strongly than the simple mean interval between failures (MTBF), the recommendation ranking may differ depending on the state, even for equipment of the same model.
[0204] Additionally, or generally, the electronic device (100) may be configured to perform only inference by receiving a periodically trained model from an external server (220) without performing the model training itself on-site. Alternatively, if on-site communication is unstable, the electronic device (100) may operate by performing basic inference as an edge device and synchronizing training updates with the server during nighttime / idle periods. Furthermore, since training data bias may occur due to differences in equipment models, years of manufacture, and maintenance policies at each site, the electronic device (100) may have an “Out-of-Distribution” detection logic to conservatively process predictions or request user confirmation if the input pattern significantly deviates from the training range.
[0205] Additionally, or generally, the training dataset of the machine learning model may be configured to include historical operational data by equipment, records of failure times, maintenance records, sensor time-series data, and process execution result data. The sensor time-series data may be defined as data arranged along a time axis, such as vibration magnitude and frequency distribution, temperature rise patterns, and current consumption fluctuation characteristics, and may be collected at a fixed sampling interval (e.g., in seconds or minutes). Furthermore, the failure time data may be configured to include failure type, failure location, and repair time, and may be utilized to learn the correlation between equipment degradation patterns and failure results.
[0206] According to one embodiment, the input features of a machine learning model may include not only simple raw sensor values but also derived variables processed into statistical feature values. For example, mean values, variance, kurtosis, and frequency spectrum peak values can be extracted from vibration data, and the slope of rise per unit time, maximum value, and moving average value can be calculated from temperature data. Additionally, load fluctuation range, frequency of abnormal peak occurrence, and deviation from normal patterns can be defined as feature values from current data. Furthermore, non-sensor information such as accumulated equipment usage time, elapsed time since last maintenance, and process type codes may also be included as input features. Such multidimensional feature vectors serve to improve prediction accuracy by representing the equipment status more precisely.
[0207] According to one embodiment, the output of the machine learning model may be defined as the remaining usable time of the target equipment, which may be composed of a regression problem calculated in the form of a continuous value. The remaining usable time refers to the length of time during which normal operation is predicted to be possible based on the current point in time, and the unit of time may be defined as hours, days, or the number of process cycles. In addition, in another embodiment, the output may not be a single continuous value, but may be defined in the form of a probability value classified into multiple risk grades such as "Normal," "Caution," and "Danger." In this case, it may be configured to calculate a failure risk correction coefficient based on the probability value for each grade.
[0208] According to one embodiment, a machine learning model can be retrained by periodically incorporating actual process execution result data even after initial training. For example, the error between the predicted remaining usable time and the actual time of failure is calculated and reflected in the loss function, and the model parameters are updated to continuously improve prediction accuracy. This iterative learning structure enables the implementation of a self-correcting prediction system that adapts to changes in site characteristics, environmental conditions, and equipment aging.
[0210] The above intelligent construction equipment recommendation method is,
[0211] The above processor further includes an operation of calculating an efficiency index for each of the above target equipment through the following [Mathematical Formula 1], and
[0212]
[0213] EI is the efficiency index of the target equipment, W_act is the work volume per unit time of the target equipment, W_std is the reference work volume of the target process, M_act is the average failure interval of the target equipment, M_std is the reference failure interval of the target equipment, C_act is the operating cost of the target equipment, C_std is the set reference cost, p is the set cost sensitivity coefficient, and k is the set cost penalty index.
[0214] According to one embodiment, the electronic device (100) may obtain a plurality of parameters representing the productivity, reliability, and economic efficiency of the target equipment and input them into Equation 1 in order to calculate the efficiency index of the target equipment.
[0215] In the present disclosure, the “efficiency index” may be defined as a value that integrates productivity based on work volume per unit time, equipment stability based on average interval between failures, and economic efficiency based on operating costs into a single indicator.
[0216] The electronic device (100) can provide a quantitative basis for process-specific equipment recommendations by extracting each parameter from field operation data (e.g., progress by process, material status, equipment list, breakdown interval, cost information) and equipment status data (e.g., sensor-based status data or maintenance history).
[0217] According to one embodiment, “work volume per unit time” refers to the amount of work that the target equipment can process per unit time in a specific process. For example, this may include the excavation / loading volume per hour for an excavator, the pouring volume per hour for a concrete pump truck, and the number of lifting cycles or lifting weight per hour for a crane. The electronic device (100) can calculate the work volume per unit time by collecting actual work volume and operating time from equipment telematics or operation logs, and if work volume data is not collected directly, it can be calculated by combining process performance (e.g., pouring volume, installation quantity) and equipment operating time (e.g., start-up time, work section log). In addition, to mitigate temporary fluctuations, an average or moving average of a recent period (e.g., the last week or the last n operations) may be applied, and if the equipment has different units, it can be converted to the same process standard using “measurement unit mapping information” corresponding to the process code and equipment type.
[0218] According to one embodiment, “standard workload” refers to the average workload normally expected in a target process and can be used as a reference value to determine at what level the workload per unit time is normal for process execution. The electronic device (100) can obtain the standard workload from average performance data of similar past processes, standard cost estimates, or a pre-established standard table by process type. Additionally, since the standard workload may vary depending on site conditions (e.g., constraints on the delivery path, work radius, number of floors, narrowness, restrictions on night work, etc.), the electronic device (100) can adjust the standard workload by applying a correction factor that reflects the site conditions. Accordingly, even for the same process, a reference value adapted to the difficulty of the site can be applied, thereby improving the realism of the efficiency index.
[0219] According to one embodiment, the “average failure interval” refers to the average time during which the target equipment can be continuously operated until it causes a work stoppage due to a failure, and can be used as an indicator of the reliability or stability of the equipment. The electronic device (100) can calculate the average failure interval based on equipment maintenance history data, failure occurrence logs, rental company operation data, or manufacturer reliability data. Furthermore, in this specification, failure may be defined not as a simple warning alarm or minor consumable replacement, but as a failure event at a level that stops the execution of the process (e.g., inability to start, major drive system malfunction, stoppage due to hydraulic leakage, etc.), thereby ensuring that the comparison criteria for the average failure interval are consistently maintained. Furthermore, if the remaining usable time is predicted based on real-time sensor data, the electronic device (100) may apply a correction value to the average failure interval or stability-related parameters to reflect recent deterioration in condition.
[0220] According to one embodiment, the “reference failure interval” refers to the average reliability reference value that the equipment type or model has in a normal state. The electronic device (100) may obtain the reference failure interval from group statistics of equipment of the same model or class (e.g., fleet average), standard reliability information provided by the manufacturer, or type-specific reference values stored in an internal database. In the case of new equipment or equipment with insufficient failure history, the electronic device (100) may apply the reference failure interval as a substitute value, but may prevent excessive recommendations by applying an uncertainty flag or conservative penalty indicating low data reliability.
[0221] According to one embodiment, “operating costs” refer to the total costs incurred when the target equipment is put into a process and operated, and may include rental fees, fuel or electricity costs, labor costs for operators, expected values of maintenance and inspection costs, consumable costs, and surcharge costs for night / holiday work. The electronic device (100) can calculate operating costs by linking rental contract information, fuel usage data, personnel deployment information, and past maintenance cost statistics, and can convert the costs by reflecting the expected working time of the process and the minimum contract billing unit (e.g., half-day / 1 day) to standardize the cost calculation unit to an hourly or daily rate. By structuring operating costs from the perspective of total costs in this way, the discrepancy with actual execution costs can be reduced compared to a simple comparison of rental fees.
[0222] According to one embodiment, “base cost” refers to a standard value of an acceptable cost for a target process and can be set according to the equipment cost allocation per process, project budget plan, or on-site cost control policy. The electronic device (100) stores the base cost as a template for each process type (e.g., standard equipment cost per process type) and can dynamically adjust the base cost according to the degree of delay, operating modes such as schedule priority / budget priority, or monthly execution status. This enables recommendations that reflect the “acceptable cost at this point in time” even for the same process.
[0223] According to one embodiment, the “cost sensitivity coefficient” is a setting value for adjusting the intensity of the influence of operating costs on the efficiency index. The electronic device (100) can set the cost sensitivity coefficient differently depending on the field operation mode; for example, when budget control is important, the cost sensitivity coefficient can be set high so that equipment with costs exceeding the standard is disadvantaged in the recommendation ranking. Conversely, when shortening the construction period is the top priority, the cost sensitivity coefficient can be set relatively low so that the contribution of productivity and stability factors is reflected more significantly. Additionally, the cost sensitivity coefficient may be entered by a field manager at a user terminal (210) or may be automatically calculated based on rules according to the project stage (e.g., initial stage or final stage, etc.) and the cost execution rate.
[0224] According to one embodiment, the “cost penalty index” is a setting value that determines the rate at which the penalty increases when operating costs exceed the standard cost. The electronic device (100) can store the cost penalty index as a pre-set policy value, and for projects where control over cost overruns is strict, the cost penalty index can be set higher so that the efficiency index decreases rapidly when costs exceeding the standard occur. Conversely, in environments where cost variability is high or equipment supply is limited, the cost penalty index can be set lower to apply the penalty for cost overruns gradually. This structure reduces recommendation distortions that may occur when processing cost elements as “linear deductions” and enables flexible control tailored to field policies.
[0225] According to one embodiment, Equation 1 has technical significance in that it combines productivity, reliability, and cost terms into different non-linear function forms. Specifically, productivity is reflected in the form of a logarithmic function so that even if the workload per unit time increases, the increase in the efficiency index can be gradually mitigated. Accordingly, the problem of equipment with extremely high workload figures being overestimated while ignoring cost and risk factors can be suppressed, and the "over-input of high-performance equipment" that commonly occurs in the field can be structurally prevented.
[0226] According to one embodiment, the logarithmic function term included in Equation 1 may be structured to take the natural logarithm of the value obtained by adding 1 to the ratio of the work volume per unit time to the reference work volume. In this case, considering the mathematical characteristic that the domain of the logarithmic function must be greater than 0, the work volume per unit time may be limited to a real value greater than or equal to 0, and the reference work volume may also be pre-set to a value greater than 0. Furthermore, to prevent the logarithmic value from diverging to negative infinity even when the work volume per unit time approaches 0, the system may be configured to set a minimum work volume threshold or perform clipping processing to limit extreme values. Through this, the efficiency index is calculated within a mathematically stable range, and distortion caused by abnormal data can be prevented.
[0227] According to one embodiment, a structure that applies an exponential function to a value obtained by subtracting 1 from the ratio of the average failure interval to the reference failure interval can be understood as a technical means to non-linearly amplify and reflect the difference in failure stability. That is, when the average failure interval is equal to the reference failure interval, the exponential function value is designed to converge to 1, and as the average failure interval increases above the reference, the contribution of efficiency to the index can be configured to increase acceleratingly. Conversely, when the average failure interval is lower than the reference, the exponential function value decreases to less than 1, which may negatively affect the efficiency index. This non-linear amplification structure is intended to reflect field characteristics where the impact of failure risk on process interruption increases rapidly based on a critical point rather than a simple linear relationship, and provides a technical effect of reflecting equipment stability more sensitively than a simple average value comparison.
[0228] According to one embodiment, the cost sensitivity factor can be set by comprehensively considering the project's budget constraint level, the need to shorten the construction period, contract conditions, and client requirements. For example, in a project with limited budget leeway, the cost sensitivity factor can be set relatively high to strengthen penalties for cost overruns, whereas in an urgent process where shortening the construction period is the top priority, the cost sensitivity factor can be lowered to ensure that the influence of productivity factors is reflected relatively significantly.
[0229] In addition, the cost penalty index can be set as an exponential parameter to linearly or non-linearly adjust the impact of cost increases on the efficiency index. When the cost penalty index is close to 1, cost increases are reflected linearly, whereas when set to a value greater than 1, the penalty resulting from cost increases can be reflected by accelerating expansion. This structure provides a technical effect of curbing the selection of excessively high-cost equipment by designing the efficiency index to decrease sharply when costs exceed a certain level.
[0230] Furthermore, reliability is reflected in the form of an exponential function, allowing the efficiency index to be designed to decrease sensitively when the average interval between failures falls below the reference interval. This reflects the fact that work stoppages caused by equipment failure have a significant impact on the entire process during the recovery of delayed processes, thereby implementing a recommendation structure that prioritizes process stability over recommendations focused solely on productivity. In particular, since the system can be designed so that a meaningful penalty to the efficiency index occurs even when the average interval falls only slightly below the reference, it reduces the likelihood of high-risk equipment remaining in top recommendations.
[0231] Meanwhile, the cost term is reflected through a structure that applies a power-law penalty to the ratio of operating costs to base costs and subtracts it. Accordingly, while a relatively gradual deduction occurs when operating costs approach the base costs, the efficiency index can be configured to decrease sharply when operating costs significantly exceed the base costs. This embeds a "cost excess suppression mechanism" into the mathematical formula itself, which is difficult to implement using a simple cost-weighted summation method, and can be defined as a technical design that reflects the characteristics of construction sites where cost management is critical.
[0232] According to one embodiment, the calculation of the efficiency index based on Equation 1 provides a differentiated effect that simultaneously improves the stability of the recommendation results and field suitability compared to a simple linear weighted summation method. For example, even if the equipment has a very high workload per unit time, if the average failure interval is lower than the standard or the operating cost significantly exceeds the standard, the efficiency index can be adjusted to below an appropriate level by Equation 1. Accordingly, a situation in which “high-production, high-risk equipment” is introduced into a delayed process and thereby increases the risk of shutdown can be suppressed in advance.
[0233] Furthermore, since equipment with excellent average interval between failures may receive relatively high evaluations in efficiency indices due to the influence of reliability factors, there may be a tendency to prioritize recommendations for "equipment that pushes through uninterruptedly to the end" during the recovery process of delayed processes. This can lead to improved reliability of the estimated time of process completion and reduce cascading delays and additional waiting costs.
[0234] Furthermore, since the cost sensitivity coefficient and cost penalty index can be adjusted according to the field operation mode, recommendation results tailored to various field policies, such as budget priority, schedule priority, and stability priority, can be provided within the same mathematical formula structure. Consequently, this mathematical formula 1 is differentiated in that it implements an intelligent equipment recommendation structure that can be dynamically tuned according to field policies while reflecting productivity, stability, and economic efficiency in a balanced manner.
[0236] The above intelligent construction equipment recommendation method is,
[0237] The above processor acquires a ground image of a point where the target process is to be performed, and identifies the distribution of moisture content of the ground included in the ground image through image segmentation;
[0238] The above processor calculates the maximum ground pressure per unit area applied to the ground surface based on the self-weight and working load during the operation of the above-mentioned final equipment; and
[0239] The above processor includes an operation of calculating the minimum area of an outrigger pad to be placed at the bottom of the final equipment and providing it along with the recommendation information when the ground allowable bearing capacity estimated according to the moisture content distribution is less than the maximum ground pressure.
[0240] The electronic device (100) can additionally generate information to assist in safe equipment operation by reflecting the ground conditions at the point where the final equipment will actually be operated.
[0241] Specifically, the electronic device (100) can acquire an image of the ground at the point where the target process is to be performed, and the ground image can be acquired from a fixed camera at the site, a mobile terminal camera (e.g., a user terminal (210)), or drone photography equipment.
[0242] The ground image may include the surface condition of the location where the equipment is to be placed (e.g., soil, gravel, concrete slab, traces of subsidence, pools of water, muddy sections, etc.), and the electronic device (100) can identify which work area the image corresponds to by linking it with coordinate information of the shooting location or process area information.
[0243] According to one embodiment, the electronic device (100) can identify the spatial distribution of ground conditions by performing image segmentation on the acquired ground image.
[0244] For example, the electronic device (100) can compartmentalize dry areas, wet areas, water pooling areas, paved areas, etc. in a ground image and estimate the distribution of moisture content of the ground for each compartment.
[0245] Here, "moisture content distribution" can be defined as information indicating "how the relative moisture content of the ground surface or upper layer varies depending on the location," and the electronic device (100) can classify moisture-related classes (e.g., dry / normal / wet / saturated) in pixel units or grid units through a learned segmentation model, and can generate the classification results by converting them into a continuous value distribution or mapping them into interval values. Additionally, considering cases where the shooting environment has a significant impact, such as changes in illumination or shadows, the electronic device (100) can be configured to perform preprocessing such as color correction, noise removal, and cropping of the region of interest (e.g., expected area of equipment grounding).
[0246] According to one embodiment, the electronic device (100) can calculate the maximum ground pressure per unit area applied to the ground surface based on the self-weight and working load of the final equipment. Here, the self-weight can be obtained from equipment specifications (e.g., model-specific specification DB, rental company equipment specifications, manufacturer data), and the working load can be calculated from load conditions expected in the process (e.g., lifting weight of a crane, bucket load of an excavator, working conditions of a pump truck, etc.).
[0247] The electronic device (100) can calculate the “maximum ground pressure” by reflecting the ground structure (e.g., wheels, tracks, outriggers, etc.) and ground area and load distribution conditions of the equipment, and in particular, for equipment using outriggers, it can conservatively calculate the maximum ground pressure by considering that the load deviation per outrigger (e.g., working direction, boom angle) may cause the maximum ground pressure to be concentrated at a specific point.
[0248] According to one embodiment, the electronic device (100) can calculate the minimum area of an outrigger pad to be placed under the final equipment and provide it along with recommendation information when the ground allowable bearing capacity estimated according to the moisture content distribution is less than the maximum ground pressure.
[0249] Here, "allowable ground bearing capacity" can be estimated using a reference table for allowable bearing capacity by moisture class or an empirical model, reflecting the general trend that bearing capacity decreases as moisture content increases.
[0250] The electronic device (100) can estimate the allowable support force for each work location (e.g., each expected outrigger placement point) and calculate the minimum reinforcement plate area based on the most unfavorable point among them (e.g., the point with the lowest allowable support force). The minimum reinforcement plate area can be defined as “the ground area required so that the maximum ground pressure is less than or equal to the allowable support force,” and the electronic device (100) can be configured to provide the reinforcement plate area, as well as the reinforcement plate specifications (e.g., width × height), number of placements, and placement location (e.g., left front / left rear / right front / right rear), to the user terminal (210) in the form of a guide.
[0251] According to the present embodiment, the results of equipment recommendations can be extended beyond merely considering "performance, cost, and failure risk" to also take into account "ground stability," which is important in actual field operations. Accordingly, the risk of equipment overturning or subsiding in areas where the ground is wet or saturated can be suppressed in advance, and by proactively inducing preparatory work such as installing reinforcement plates before operating the equipment, it provides the effect of reducing work stoppages, safety accidents, and secondary damage. In addition, by identifying moisture distribution based on images, it reduces judgment errors that may occur in point-based measurements (e.g., checking only some locations) and enables conservative design by distinguishing hazardous locations even within the same work area, thereby increasing the reliability of equipment placement and field acceptance.
[0253] The operation of providing the above recommendation information is,
[0254] The above processor performs the operation of checking the current inventory amount of essential consumables that are pre-set as essential for the operation of the above final equipment from the field material management database;
[0255] The operation of the processor to calculate an estimated required amount of consumables by multiplying the required consumable consumption rate per unit time set for the end equipment by the remaining time required for the target process; and
[0256] The processor includes an operation of including a notification in the recommendation information instructing the transfer of insufficient materials from an adjacent material warehouse of the target building that is previously registered, if the current inventory of the essential consumables is less than the estimated required amount of consumables.
[0257] The electronic device (100) can enhance the “feasibility of recommendation” by checking the supply of consumables essential for operating the equipment together during the process of confirming recommended equipment and providing recommendation information.
[0258] Specifically, the electronic device (100) can check the current inventory of essential consumables that are pre-set as necessary for the operation of the final equipment from the field material management database. Here, essential consumables may be defined differently depending on the type of equipment; for example, for diesel equipment, they may include fuel, urea solution, hydraulic fluid, engine oil, filters, etc., and for electric equipment, they may include battery packs, charging cables, spare fuses, etc. The electronic device (100) may have a table mapping the “list of essential consumables” according to the equipment ID or equipment type, and the table may be configured so that an administrator can add and / or change it according to field policies.
[0259] According to one embodiment, the electronic device (100) can calculate the estimated required amount of consumables by multiplying the required consumable consumption rate per unit time set for the end equipment by the remaining time required for the target process. Here, the consumption rate per unit time may be set based on past operation logs, the average consumption rate provided by the manufacturer, or the field average value, and may be corrected according to work intensity (e.g., load level, equipment utilization rate, idle rate).
[0260] Additionally, "remaining time required" may be defined as a value calculated by reflecting the remaining work volume of the process, the work volume of the final equipment, available work time slots, setup time, etc. (or time calculated backward from the expected time of completion). The electronic device (100) may be configured to calculate conservatively by adding a safety margin (e.g., 10-20% buffer) to prevent work interruption when calculating the estimated required amount of consumables.
[0261] According to one embodiment, the electronic device (100) may include in its recommendation information a notification instructing the transfer of insufficient materials from an adjacent material warehouse of a previously registered target building when the current stock of essential consumables is less than the expected required amount of consumables.
[0262] Here, "adjacent material warehouse" may include other area warehouses within the same site, a shared warehouse at a nearby site, a partner company warehouse, or a logistics hub, and the electronic device (100) may select the optimal source of movement by considering the location of each warehouse, inventory held, time required for movement, availability of means of transport (e.g., forklift and / or truck).
[0263] For example, the "movement instruction notification" may include the quantity of shortages, the outbound warehouse, the inbound location, the time of the request, the person in charge, and the recommended means of transport, and may be provided so that the user terminal (210) can approve / reject or select an alternative warehouse. Additionally, the electronic device (100) may be configured to separately indicate cases where the recommended equipment is suitable but the procurement of consumables is impossible, thereby processing equipment recommendations and material logistics decisions in a single flow.
[0264] According to this embodiment, the problem of "shortage of essential consumables," which is one of the primary reasons equipment recommendations cannot be immediately applied to the site, can be proactively resolved at the recommendation stage. Consequently, it is possible to prevent situations where process delays recur due to equipment becoming idle after the recommended equipment has been finalized, caused by shortages of fuel, urea solution, hydraulic fluid, etc., and to implement an actionable recommendation system that links equipment deployment with material logistics. Furthermore, by including notifications for moving to adjacent warehouses in the recommendation information, site managers can be encouraged to procure shortages immediately without separate verification procedures. As a result, this provides benefits such as reduced process downtime, lower emergency purchasing costs, and improved efficiency in material operations.
[0266] The operation of providing the above recommendation information is,
[0267] The operation of the processor to calculate a real-time wet-bulb black globe temperature (WBGT) index from temperature and humidity sensors in the field area where the target process is performed;
[0268] The above processor acquires heart rate and body temperature data from a wearable device of personnel introduced into the target process; and
[0269] When the above WBGT index is above the set risk level and at the same time the body temperature of the personnel exceeds the critical temperature, the operation includes switching the smart turnsteel gate placed at the entrance of the site area to a locked state and providing a forced rest notification.
[0270] The electronic device (100) can be configured to monitor the thermal environment and the physiological condition of personnel in real time in the site area where the target process is performed, determine whether work can be continued, and perform access control when necessary.
[0271] Specifically, the electronic device (100) can collect real-time environmental data from temperature sensors and humidity sensors installed in the field area and calculate the Wet Bulb Globe Temperature (WBGT) index based on this.
[0272] Here, the WBGT index can be defined as a heat stress indicator that comprehensively reflects temperature, humidity, radiant heat, airflow, etc., rather than just temperature, and the electronic device (100) can calculate the WBGT value at regular intervals (e.g., every minute) using sensor data and a pre-stored calculation formula or conversion table.
[0273] According to one embodiment, an electronic device (100) can acquire heart rate and body temperature data from a wearable device of personnel deployed to a target process. The wearable device can be implemented in various forms, such as a smart band, smart helmet, or smart vest, and can communicate with the electronic device (100) via Bluetooth, low-power wireless communication, or a dedicated field network. The electronic device (100) can determine the heat stress state of personnel by analyzing a rapid increase in heart rate, a continuous increase in body temperature, or deviations from individual standards. Additionally, individual thresholds may be applied differentially to each personnel by considering factors such as age, work intensity, and whether protective equipment is worn.
[0274] According to one embodiment, the electronic device (100) can switch a smart turnsteel gate placed at the entrance of the site area to a locked state when the WBGT index is above a set risk level and at the same time the body temperature of the personnel exceeds a critical temperature. Here, the risk level may be divided into stages such as “caution,” “warning,” “danger,” etc., and may be configured to perform physical access control only when additional abnormal biological signals are detected at a risk level or higher.
[0275] Here, the "smart turnsteel gate" includes an electronic locking device and a control module, and can be automatically switched to a locked or unlocked state according to a control signal received from the electronic device (100).
[0276] Additionally, the electronic device (100) can provide a forced rest notification to the user terminal (210) and the wearable device simultaneously. The forced rest notification may include a recommended rest time, a recommendation for hydration intake, guidance on cooling zones, and a function to call an administrator. Furthermore, the electronic device (100) may be configured to track whether the rest is being performed, reconfirm whether the body temperature has returned to a normal range after a certain period of time, and release the turnstill gate only when safety conditions are met.
[0277] According to the present embodiment, physical access control is performed only when the WBGT-based environmental risk level and real-time physiological data of personnel simultaneously satisfy critical conditions, without relying on either simple environmental criteria or simple biological criteria; thus, the risk of heatstroke and heat-related illnesses can be substantially reduced while preventing excessive work interruptions. Accordingly, this improves worker safety while providing the effect of reducing the burden on site managers through the objectivity and automation of safety measures.
[0279] In paragraph 1,
[0280] The operation of providing the above recommendation information is,
[0281] The above processor, when the type of the end equipment is mobile lighting equipment, performs the operation of generating a real-time illuminance plan from a plurality of point-by-point illuminance sensors placed inside the target process;
[0282] The operation of the processor identifying a dark spot area below a reference illuminance set on the real-time illuminance plane; and
[0283] The above processor includes the operation of transmitting a control signal to the end equipment in response to receiving a request to start a process through the end equipment from the user terminal, moving the end equipment to a point corresponding to the dark area and automatically adjusting the lamp module angle of the end equipment toward the center point of the dark area.
[0284] The electronic device (100) can perform automatic lighting correction control by analyzing the illumination status inside the target process in real time when the type of the final equipment is a mobile lighting device.
[0285] Specifically, multiple point-specific illuminance sensors may be placed inside the target process, and the electronic device (100) may collect real-time illuminance values from these sensors to generate spatial distribution data. The electronic device (100) may map the collected illuminance data to a two-dimensional grid or planar coordinate system to generate a “real-time illuminance plan”.
[0286] According to one embodiment, the electronic device (100) can identify dark areas that are below a reference illuminance set on an illuminance plane.
[0287] Here, the "reference illuminance" may be set differently depending on the type of process (e.g., finishing work, electrical wiring work, inspection work, etc.) and may be stored in advance based on industrial safety standards or internal quality standards. The electronic device (100) may cluster areas below the reference value on an illuminance plane or define a continuous low illuminance area as a single dark area and calculate the center point coordinates.
[0288] According to one embodiment, when the electronic device (100) receives a request to start a process via a mobile lighting device from a user terminal (210), it can transmit a control signal to move the final equipment to a point corresponding to a dark area. The mobile lighting device may include an autonomous movement module or a remote control module, and the electronic device (100) can move the equipment to a target point by calculating a movement path based on the coordinates of the dark area center point and applying a collision avoidance algorithm.
[0289] Additionally, the electronic device (100) can transmit a control signal to automatically adjust the angle of the lamp module of the equipment toward the center point of the dark area. At this time, the lamp module may be implemented with a structure capable of rotation and tilting, and the electronic device (100) can calculate the optimal irradiation direction and angle by considering the lighting angle, irradiation distance, luminous flux, etc. If necessary, the individual angles of multiple lamp modules can be adjusted differently to uniformly compensate for the dark area.
[0290] According to the present embodiment, instead of simply installing lighting in a fixed manner, the uniformity of illumination in a work area can be improved by automatically identifying dark areas through real-time illumination plane analysis and automatically positioning and aligning mobile lighting equipment. Accordingly, this improves the quality of precision work requiring visibility, provides the effect of preventing safety accidents that may occur in dark areas, and enables the implementation of an intelligent field lighting control system capable of actively relocating lighting according to changes in the work environment.
[0292] The above description is merely an illustrative explanation of the technical concept of the present invention, and those skilled in the art to which the present invention pertains will be able to make various modifications and variations within the scope of the essential characteristics of the present invention.
[0293] Accordingly, the embodiments disclosed in this invention are intended to illustrate, not limit, the technical concept of the invention, and the scope of the technical concept of the invention is not limited by these embodiments. The scope of protection of this invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this invention.
Claims
Claim 1 An intelligent construction equipment recommendation method for extracting and recommending optimal equipment suitable for a delayed process based on an efficiency index of construction equipment, performed by an electronic device including a processor, wherein the processor performs the operation of acquiring site operation data including the progress of each process of a target building under construction, material status data, a list of construction equipment available for each process, an average failure interval for each construction equipment, and an operating cost for each construction equipment; the processor performs the operation of identifying, based on the site operation data, a target process among a plurality of processes in progress on the target building that corresponds to a delayed state and is set to be capable of parallel progress with other processes; the processor performs the operation of identifying a standard efficiency index and a standard cost limit set for the target process; and the processor performs the operation of identifying at least one target equipment corresponding to the target process through the construction equipment list, and identifying the efficiency index of each of the at least one target equipment based on the work volume per unit time for the target process for each of the at least one target equipment, the average failure interval, and the operating cost. An intelligent construction equipment recommendation method comprising the operation of the processor identifying a final equipment as recommended equipment for the target process, wherein the efficiency index is greater than or equal to the reference efficiency index and the operating cost is less than or equal to the reference cost limit, and providing recommendation information to a user terminal including an expected time of completion of the target process when the target process is performed through the final equipment. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete
Citation Information
Patent Citations
Method, device and system for automating quotation proposal and order processing of industrial machinery equipment based on analysis of process specification information of facility
KR102806684B1
