Project progress optimization method and system based on data analysis

Abstract

The invention discloses a project progress optimization method and system based on data analysis, and relates to the technical field of project progress optimization, and the method comprises the steps: obtaining the plan information of a target building project, and constructing a first workload prediction model based on historical project data; and based on the activity and position data collected by the wearable device, monitoring the task execution state of each worker in real time, and constructing a second progress assessment. When it is detected that the overall progress deviates from the target threshold value, the task scheduling sequence and the distribution strategy of the remaining workload are dynamically adjusted, and closed-loop optimization control over the construction period is achieved. According to the project progress optimization method based on data analysis provided by the invention, the workload and progress can be evaluated more comprehensively by combining multi-dimensional information such as historical data, environmental factors and staff efficiency, the limitation of depending on a single data source or simple average is avoided, and the adaptability of a project is remarkably improved. And a multi-objective optimization algorithm and reinforcement learning are adopted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering progress optimization, in particular to an engineering progress optimization method and system based on data analysis. BACKGROUND

[0002] With the continuous development of the construction industry and engineering project management, the traditional engineering progress management method gradually exposes many shortcomings, especially in complex engineering projects. In recent years, with the rise of information technology and data analysis technology, the research direction of engineering progress optimization has gradually shifted to intelligent methods based on data analysis. Many scholars and engineering practitioners have begun to use big data analysis, artificial intelligence, Internet of Things technology and other tools to collect and analyze real-time data during the engineering process, optimize engineering progress plans, predict engineering progress delays in advance, and thus optimize resource allocation and task scheduling. Data analysis methods can provide scientific workload estimates and progress predictions based on historical project data, real-time work data, and environmental changes, thereby effectively improving the construction efficiency and the likelihood of timely delivery of engineering projects. This data analysis-based engineering progress optimization method has become an important research direction in the field of engineering management.

[0003] Although many research and practical applications have applied data analysis-based progress optimization methods in recent years, there are still many shortcomings in existing technologies, especially when dealing with the many variable factors in actual complex engineering projects, it is still difficult to achieve ideal results. First, most existing engineering progress optimization methods rely on historical data and static models, ignoring the impact of real-time site data (such as the immediate workload of workers, environmental changes, etc.) on progress prediction. For example, traditional progress prediction models often use historical project average working hours and other data for calculation, lacking a real-time dynamic response mechanism, so in complex and variable engineering environments, there is a large deviation in progress, and even leading to engineering delays.

[0004] Secondly, existing methods often fail to fully integrate and utilize real-time data collected by Internet of Things (IoT) sensors and other advanced technologies, resulting in lagging progress information and workload data, which in turn affects the accurate adjustment of progress and resource optimization. Traditional methods usually rely only on manual records or manual adjustments based on pre-set plans, lacking effective automation mechanisms and real-time feedback systems. In addition, although some methods use machine learning and data mining techniques for prediction, they are still limited to analysis of a single data source, failing to fully consider the multiple effects of environmental factors (such as weather, equipment failure, etc.) on engineering progress. In particular, for dynamic projects, existing methods fail to provide flexible duration adjustment and task priority optimization, resulting in complex and ineffective adjustment processes when engineering progress deviations occur.

[0005] Furthermore, current project progress management systems are mostly independent subsystems, lacking global coordination mechanisms. In the case of multi-project collaboration and resource sharing, cross-project progress integration and optimization cannot be efficiently performed. Traditional systems often use single objective optimization, without considering how to share resources and prioritize between multiple sub-projects and tasks, making it difficult to adjust the overall project progress. SUMMARY

[0006] In view of the above problems, the present application is proposed.

[0007] Therefore, the technical problem solved by the present application is that the existing engineering progress optimization method based on historical data has the problems of slow response to real-time work data, insufficient consideration of the influence of environmental factors on progress, insufficient multi-project collaboration and resource sharing, and how to dynamically adjust engineering progress and optimize task allocation through real-time data flow and intelligent algorithms.

[0008] To solve the above technical problems, the present application provides the following technical solutions: a project progress optimization method based on data analysis, comprising obtaining plan information of a target construction project, and constructing a first workload prediction model based on historical engineering data; real-time monitoring of the task execution status of each worker based on activity and location data collected by a wearable device, and constructing a second progress evaluation. When the overall progress deviates from the target threshold, dynamically adjusting the task scheduling order and the allocation strategy of the remaining workload to realize closed-loop optimization control of the construction period.

[0009] As a preferred scheme of the project progress optimization method based on data analysis, the plan information of the target construction project comprises engineering information for constructing an engineering plan.

[0010] The engineering information includes the work data of each worker and historical project data, and the historical data is feature extracted, and a prediction model is established based on the features.

[0011] As a preferred scheme of the project progress optimization method based on data analysis, the first workload prediction model comprises task workload and work efficiency prediction, weighted accumulation of work time and efficiency of each type of work, and dynamic correction based on actual values of environmental factors and their influence coefficients to obtain the expected task load of the workers.

[0012] As a preferred scheme of the project progress optimization method based on data analysis, the real-time monitoring of the task execution status of each worker comprises each worker wearing a detection bracelet, the bracelet being built-in with an accelerometer and a GPS, and real-time monitoring of the activity data and work status of the workers.

[0013] The system detects real-time workloads using Apache Kafka real-time data stream processing framework for data transmission.

[0014] As a preferred scheme of the engineering progress optimization method based on data analysis, the real-time monitoring of the task execution state of each worker further comprises dividing the engineering time into multiple time periods according to nodes, each time period being a sub-project, and each sub-project being composed of multiple workers.

[0015] When multiple sub-projects are executed in parallel, the progress of the multiple sub-projects is processed through a distributed computing architecture.

[0016] As a preferred scheme of the engineering progress optimization method based on data analysis, the construction of the second progress evaluation comprises calculating a standardized progress value by a current time point plan and an actual completion ratio when the target engineering progress deviates from a predetermined target, further introducing a work type importance and a resource consumption factor to construct a priority index, dynamically adjusting a construction period and a task arrangement, calculating a progress difference of the engineering plan, and automatically adjusting a remaining workload.

[0017] As a preferred scheme of the engineering progress optimization method based on data analysis, the dynamic adjustment of the task scheduling sequence and the allocation strategy of the remaining workload comprises determining a task scheduling sequence and an allocation strategy of a remaining workload based on the priority index and a progress deviation residual amount output by the second model during the progress adjustment process.

[0018] Another object of the present application is to provide an engineering progress optimization system based on data analysis, which can realize real-time collection and analysis of construction site data through one of the schemes, and solve the technical problems of lack of real-time progress monitoring and dynamic adjustment, neglect of the influence of environmental factors on engineering progress, and low resource scheduling efficiency in the current traditional progress management method.

[0019] As a preferred scheme of the engineering progress optimization system based on data analysis, it comprises a workload prediction module, a progress calculation module, and a construction period adjustment module; the workload prediction module is used to obtain an engineering plan of a target building engineering and determine an expected workload; the progress calculation module is used to determine actual workload information and a completed amount of multiple workers, and obtain a target engineering progress corresponding to the target building engineering; and the construction period adjustment module is used to adjust and optimize the construction period.

[0020] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps of the engineering progress optimization method based on data analysis.

[0021] A computer readable storage medium, having stored thereon a computer program, the computer program being executed by a processor to implement the steps of the method for optimizing project progress based on data analysis.

[0022] The method for optimizing project progress based on data analysis provided by the present application can more comprehensively evaluate workload and progress by combining historical data, environmental factors, and staff efficiency, avoiding the limitations of relying on a single data source or simple averaging, and significantly improving the adaptability of the project. By using multi-objective optimization algorithms and reinforcement learning, the present application can improve the efficiency of overall project progress management through intelligent scheduling and task priority optimization when multiple sub-projects are running in parallel. Especially in the case of multi-project collaboration, resource sharing and task adjustment can be achieved, thereby avoiding progress lag and resource conflicts between projects and effectively improving the flexibility of engineering management. The present application achieves better results in adaptability, flexibility, and reliability. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor.

[0024] Figure 1 The overall flowchart of the method for optimizing project progress based on data analysis provided by the first embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings in the specification. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0026] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a method for optimizing project progress based on data analysis is provided, comprising:

[0027] S1: Obtain the planning information of the target building project, and construct a first workload prediction model based on historical engineering data.

[0028] Further, obtaining the planning information of the target building project includes constructing an engineering plan by obtaining engineering information.

[0029] The engineering information includes work data and historical project data of each worker, and the historical data is feature extracted, and a prediction model is established based on the features.

[0030] The collection mode is that IoT sensors such as temperature and humidity sensors, position tracking sensors, accelerometers, etc. are deployed on the construction site to collect environmental conditions, activity data and position data of workers in real time.

[0031] The historical project data is collected, including construction period, type of work, working hours, and resource allocation.

[0032] The historical data is feature extracted, including the type of work, worker experience, environmental factors and historical delay, and a prediction model is established based on the features.

[0033] It should be noted that the first workload prediction model includes task workload and work efficiency prediction, the working time and efficiency of each type of work are weighted and accumulated, and the actual value of the environmental factor and its influence coefficient are combined for dynamic correction to obtain the expected task load of the worker.

[0034] In an optional embodiment, the first workload prediction model adopts a weighted correction model that integrates work type efficiency and environmental factors, specifically:

[0035] Determining the expected workload includes task workload and work efficiency prediction, and the expected workload of each worker is represented as:

[0036]

[0037] where W plan is the expected workload of each worker, T i is the working time of work type i, E i is the work efficiency of work type i, based on historical data and worker skills, R j is the influence coefficient of environmental factor j, S j is the actual value of environmental factor j, and β is the correction factor of environmental factor on workload.

[0038] In another optional embodiment, the first workload prediction model adopts a machine learning regression model, specifically:

[0039] Using historical construction project data, features such as work type, personnel experience level, task complexity, temperature and humidity are extracted. Random forest, gradient boosting tree and other algorithms are used to train the "task completion time prediction model". Input the current task and environmental characteristics, and output the task workload distribution of each worker. Further, the most important environmental impact factor can be automatically determined through feature importance analysis, and the prediction bias can be automatically corrected.

[0040] S2: Based on the activity and location data collected by wearable devices, the task execution status of each staff member is monitored in real time to build a second progress evaluation.

[0041] Furthermore, determining the workload of multiple workers involves each worker wearing a monitoring bracelet equipped with an accelerometer and GPS to monitor their activity data and work status in real time. These two devices can detect whether workers are performing work-related tasks (such as moving and installing). For example, the accelerometer can be used to determine whether a worker is performing repetitive object handling, while the GPS can be used to detect whether the work is occurring within a specified location range.

[0042] Use Apache Kafka real-time data stream processing framework for data transmission.

[0043] The system detects real-time workload, expressed as:

[0044]

[0045] Among them, P actual (t) is the actual work progress at time t, T i,actual (t) is the actual workload of job type i completed at time t, T i,planned (t) is the workload of job type i planned to be completed at time t. A progress value greater than 1 indicates that the task is completed ahead of schedule, less than 1 indicates that the task is delayed, and equal to 1 indicates that it is completed as planned.

[0046] It should be noted that obtaining the target project progress corresponding to the target construction project involves dividing the project time into multiple time periods according to the nodes. Each time period is a sub-project, and each sub-project consists of multiple staff members, which can be expressed as:

[0047]

[0048] Among them, P project is the overall progress of the target construction project, P sub,i is the progress of the i-th sub-project, W sub,i is the weight of the i-th sub-project. When multiple sub-projects are executed in parallel, the progress of multiple sub-projects is processed through a distributed computing architecture.

[0049] Furthermore, constructing a second progress assessment includes calculating the standardized progress value by the current time point plan and actual completion ratio when the target project progress deviates from the predetermined target, and further introducing the importance of the type of work and resource consumption factors to construct priority indicators, dynamically adjusting the construction period and task arrangement, calculating the progress difference of the project plan, and automatically adjusting the remaining workload.

[0050] In an alternative embodiment, the second progress evaluation employs a priority ranking difference calculation combined with a weighting factor, specifically:

[0051] The duration adjustment and optimization includes dynamic adjustment of the duration and task arrangement when the target project progress deviates from the predetermined target, calculation of the progress difference of the project plan, and automatic adjustment of the remaining workload, represented as:

[0052]

[0053] where ΔP project is the correction value of the progress difference, T i,planned and T i,actual are the planned and actual workloads of trade i, γ i is the correction weight of trade i.

[0054] In an alternative embodiment, the second progress evaluation employs a computer vision combined with edge computing scheme, specifically:

[0055] Cameras and edge inference modules (such as JetsonNano) are placed in the construction area to identify the type and location of personnel work actions (such as carrying, welding, and installing) in real time, map the association between identified actions and task types, estimate the current task completion ratio, and the back-end system compares the image annotation with the progress plan to calculate the progress deviation and adjust the process. It can combine BIM model for position-task mapping to improve scheduling accuracy.

[0056] S3: When the overall progress deviates from the target threshold, dynamically adjust the task scheduling sequence and the allocation strategy of the remaining workload to achieve closed-loop optimization control of the duration.

[0057] It should be noted that the duration adjustment and optimization also includes determining the adjusted priority resource scheduling and task priority optimization during the progress adjustment process. The system determines which tasks need to be completed first and how to adjust task allocation based on resource availability and workload. The task priority is represented as:

[0058]

[0059] where Priority i (t) is the priority of trade i at time t, W i is the weight of trade i, T i,planned (t) and T i,actual (t) are the planned and actual workloads of trade i at time t, and C i is the influence coefficient of trade i on resource consumption.

[0060] Embodiment 2, an embodiment of the present application, provides a data analysis-based engineering progress optimization method. In order to verify the beneficial effects of the present application, economic benefit calculation and simulation experiments are used for scientific demonstration.

[0061] Firstly, a medium-sized construction project is selected as the experimental object, which includes multiple sub-projects and workers of different types. Through the deployment of Internet of Things sensors and smart wearable devices, the working status, task progress and environmental changes of the on-site workers are monitored in real time. The purpose of this experiment is to prove that the engineering progress optimization method of the present application can effectively improve the accuracy of engineering progress, timely adjust the construction period and task allocation, and thus avoid common progress lag and resource waste problems.

[0062] During the experiment, the preliminary engineering plan of the construction project is first obtained, including the estimated workload, task allocation and time nodes of each type of work. Then, using historical data such as similar project construction period, work type, working hours and resource allocation, the engineering plan is trained with a prediction model. The prediction model uses regression analysis method combined with machine learning technology to calculate the estimated workload of each worker.

[0063] Next, using smart wristbands and environmental sensors installed on the workers, real-time work progress and environmental data are collected. The work progress is transmitted to the central control system through the Apache Kafka real-time data stream processing framework, and the system adjusts the progress according to the real-time data. The actual workload of each worker is compared with the planned workload to calculate the actual progress. To ensure real-time updating of the progress, the system uses reinforcement learning algorithm to adjust the priority of the work tasks and adjusts the construction period according to the real-time progress.

[0064] During the progress evaluation process, multiple sub-projects are carried out in parallel, and the system calculates the progress of each sub-project by weighted average method and dynamically optimizes it. If some sub-projects lag behind, the system will adjust the resource allocation and prioritize the key tasks to ensure the overall project progress. Finally, through the adjustment of the construction period and the optimization of the tasks, the entire project is completed on time, and the efficiency of each task is significantly improved.

[0065] Table 1 Comparison of experimental data

[0066]

[0067] By comparing the progress difference (i.e., the difference between actual workload and expected workload) of each work type, it can be found that the progress difference of all work types is lower than the deviation commonly seen in traditional methods. For example, the progress difference of work type 1 is 5, indicating that the task is completed ahead of schedule. However, in traditional methods, it is often difficult to discover progress lag problems in advance due to the lack of real-time monitoring and dynamic adjustment, resulting in overall project delays. In the embodiment of the present invention, through real-time monitoring and progress correction, the progress difference is effectively controlled, ensuring that the project is completed on time.

[0068] The setting of task priority adopts a weighted algorithm based on resource consumption and workload progress. According to the task priority data in the table, it can be seen that work type 4 is set as the highest priority (1.3), because this work type has a greater impact on project progress. During the implementation of the project, the system adjusts the task priority according to real-time data to ensure that the progress of key work types is not delayed, thereby ensuring the smooth progress of the overall project. In traditional methods, task priority is often determined subjectively by project managers, which can lead to unreasonable resource allocation and task delays.

[0069] The progress correction value represents the progress adjustment automatically calculated and performed by the system. According to the data in the table, the correction values of all work types are small and accurate, indicating that the progress adjustment of the present invention can quickly respond to progress deviations and perform efficient resource allocation and task adjustment. Compared with traditional methods, which rely more on manual intervention and lack real-time feedback mechanisms, the adjustment process is relatively slow, which can lead to resource waste or project delays.

[0070] In this embodiment, through the corrected workload data, it can be seen that the system has made the workload allocation of each work type more reasonable through progress adjustment. For example, the workload of work type 3 has been increased by 2 units, reflecting that the system has intelligently optimized the workload based on real-time progress and environmental factors. Traditional methods often cannot optimize task allocation in real time due to the lack of intelligent adjustment mechanisms, resulting in low resource utilization.

[0071] In Embodiment 3, an embodiment of the present invention provides an engineering progress optimization system based on data analysis, which includes a workload prediction module, a progress calculation module, and a construction period adjustment module.

[0072] The workload prediction module is used to obtain the engineering plan of the target building project and determine the expected workload. The progress calculation module is used to determine the actual workload information and the completed amount of multiple workers, and obtain the target engineering progress corresponding to the target building project. The construction period adjustment module is used for construction period adjustment and optimization.

[0073] If the functions are implemented in software, the functions can be stored in or implemented as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, or twisted pair, then the coaxial cable, fiber optic cable, or twisted pair are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-Ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0074] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0075] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0076] It should be understood that portions of the present application can be implemented with hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be understood that the foregoing embodiments are merely illustrative of the present application and are not to be used to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it will be apparent to those skilled in the art that various changes and modifications can be contributed to the present application without departing from the spirit and scope of the present application, and such changes and modifications should be encompassed within the scope of the appended claims.

[0077] It should be understood that the foregoing embodiments are merely illustrative of the present application and are not to be used to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it will be apparent to those skilled in the art that various changes and modifications can be contributed to the present application without departing from the spirit and scope of the present application, and such changes and modifications should be encompassed within the scope of the appended claims.

Claims

1. A method for optimizing project progress based on data analysis, characterized in that: include: Obtaining planned information of a target construction project and constructing a first workload prediction model based on historical project data; Based on the activity and location data collected by wearable devices, the task execution status of each staff member is monitored in real time to build a second progress assessment; When it is detected that the overall progress deviates from the target threshold, the task scheduling order and the allocation strategy of the remaining workload are dynamically adjusted to achieve closed-loop optimization control of the construction period.

2. The method for optimizing project progress based on data analysis according to claim 1, wherein: The obtaining of the plan information of the target construction project includes obtaining the project information to construct a project plan; Engineering information includes the work data and historical project data of each staff member, and features are extracted from the historical data, and a prediction model is established based on the features.

3. The method for optimizing project progress based on data analysis according to claim 2, wherein: The first workload prediction model includes task workload and work efficiency prediction, weighted accumulation of working time and efficiency of each type of work, and dynamic correction based on the actual value of environmental factors and their influence coefficients to obtain the expected task load of the staff.

4. The method for optimizing project progress based on data analysis according to claim 3, wherein: The real-time monitoring of the task execution status of each staff member includes each staff member wearing a detection bracelet with a built-in accelerometer and GPS to monitor the staff member's activity data and work status in real time; Use Apache Kafka real-time data stream processing framework for data transmission and system detection of real-time workload.

5. The method for optimizing project progress based on data analysis according to claim 4, characterized in that: The real-time monitoring of the task execution status of each worker also includes dividing the project time into multiple time periods according to the nodes, each time period is a sub-project, and each sub-project is composed of multiple workers; When multiple sub-projects are executed in parallel, the progress of multiple sub-projects is handled through a distributed computing architecture.

6. The method for optimizing project progress based on data analysis according to claim 5, characterized in that: The construction of the second progress assessment includes calculating the standardized progress value by the current time point plan and actual completion ratio when the target project progress deviates from the predetermined target, and further introducing the importance of the type of work and resource consumption factors to construct a priority index, dynamically adjusting the construction period and task arrangement, calculating the progress difference of the project plan, and automatically adjusting the remaining workload.

7. The method for optimizing project progress based on data analysis according to claim 6, wherein: The dynamic adjustment of the task scheduling sequence and the allocation strategy of the remaining workload includes determining the allocation strategy of the task scheduling sequence and the remaining workload based on the priority index and the progress deviation residual output by the second model during the progress adjustment process.

8. A system using the engineering progress optimization method based on data analysis according to any one of claims 1 to 7, characterized in that: Including workload forecast module, progress calculation module, and construction period adjustment module; The workload prediction module is used to obtain the engineering plan of the target construction project and determine the expected workload; The progress calculation module is used to determine the actual workload information and completed workload of multiple workers to obtain the target project progress corresponding to the target construction project; The construction period adjustment module is used to adjust and optimize the construction period.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the engineering progress optimization method based on data analysis according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the engineering progress optimization method based on data analysis according to any one of claims 1 to 7 are implemented.

Images