A work time determination method and device in a flexible work scenario

Abstract

The application provides a work time determination method and device in a flexible work scene, and belongs to the technical field of work time determination. The method comprises the following steps: acquiring a work area video collected based on a collection device, and identifying task personnel in the work area video and a personnel position where the task personnel are located; when a task reporting personnel and the task personnel are matched, determining a target work area in a work area based on the personnel position and a duration of the task personnel at the personnel position; determining a video duration in which the task personnel in the target work area meet work time counting conditions, and taking the video duration as work time of the task personnel. The application can determine target work areas of different tasks in a flexible work scene, and then count work time of the target work areas, so that work time of task personnel under different tasks can be obtained, and accuracy of the determined work time in the flexible work scene is improved.

Description

Technical Field

[0001] This invention relates to the field of working time determination technology, and specifically to a method and apparatus for determining working time in flexible work scenarios. Background Technology

[0002] Time quotas are the basic unit of cost measurement, the most widely used cost management tool in manufacturing enterprises, and an important basis for enterprises to rationally plan and schedule production. They are also the foundation and an important prerequisite for enterprises to conduct scientific management and improve labor productivity. The premise of time quotas is the accurate determination of the time spent by personnel in completing their tasks.

[0003] Traditional work time determination relies on manual entry, which is prone to errors in task operation and data inconsistencies, making it difficult to guarantee the accuracy and real-time nature of work time data. To address this technical problem, existing technologies propose automatic identification and recording solutions for work times, specifically: installing camera points and determining work times based on the video captured by these points. However, this technology is suitable for fixed work scenarios, i.e., where the task is singular and each worker is only responsible for one task. When the task in a scenario is diverse and variable, or when the same worker needs to perform multiple tasks simultaneously, existing technologies cannot accurately identify different tasks, leading to inaccurate work time determination.

[0004] Therefore, there is an urgent need to provide a method and device for determining working hours in flexible work scenarios, so as to achieve accurate prediction of working hours in flexible work scenarios. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and apparatus for determining working hours in flexible work scenarios, so as to solve the technical problem that the existing technology cannot adapt to flexible work scenarios, resulting in low accuracy of working hours determined in flexible work scenarios.

[0006] On the one hand, in order to solve the above-mentioned technical problems, the present invention provides a method for determining working hours in flexible work scenarios, including:

[0007] Acquire video of the work area collected by the acquisition device, and identify the personnel in the video of the work area and their locations;

[0008] When a task reporting person and a task personnel are matched, the target work area in the work area is determined based on the personnel's location and the duration of the task personnel's stay at the personnel's location;

[0009] Determine the video duration in the target work area that meets the conditions for calculating work hours for the task personnel, and use the video duration as the work hours for the task personnel.

[0010] In one possible implementation, determining the target work area within the work area based on the personnel's location and the duration of the task personnel's stay at the personnel's location includes:

[0011] Identify the area where the workpiece is located in the video of the work area;

[0012] Determine whether the distance between the personnel's location and the area where the workpiece is located is less than a preset distance;

[0013] When the distance is less than a preset distance, determine whether the duration of the task personnel in the personnel position is greater than a preset duration;

[0014] When the duration exceeds the preset duration, the rectangle enclosing the task personnel and the workpiece will be used as the target work area.

[0015] In one possible implementation, determining the video duration for which the task personnel in the target work area meet the time-counting criteria includes:

[0016] The start and end frames of the video in the work area are used as the initial video duration.

[0017] Determine that there are no video frames to be removed for the task personnel in the video of the work area, and determine the removal duration of the video frames to be removed;

[0018] The difference between the initial video duration and the duration to be removed is taken as the video duration.

[0019] In one possible implementation, determining the video duration for which the task personnel in the target work area meet the time-counting criteria further includes:

[0020] The video frame indicating that the task personnel are present in the video of the work area and that the distance between the task personnel's location and the target work area is greater than a distance threshold is identified as a video frame far from the workpiece.

[0021] Determine the distance duration of the video frame that is far from the workpiece, and use the difference between the initial video duration, the duration to be removed, and the distance duration as the video duration.

[0022] In one possible implementation, the work area video includes a first work task video and a second work task video. Then, determining the video duration for which the personnel in the target work area meet the conditions for time calculation further includes:

[0023] When the first task video and the second task video overlap, determine the overlap duration;

[0024] Based on the first task video and the second task video, determine the inserting task and the inserted task in the first task and the second task.

[0025] The difference between the first task video duration and the overlap duration between the start and end frames of the task video corresponding to the inserted task is taken as the video duration of the task personnel in the inserted task.

[0026] In one possible implementation, determining the video duration for which the task personnel in the target work area meet the time-counting criteria further includes:

[0027] Based on a preset action recognition model, the video of the work area is used to perform action recognition, and multiple action recognition results are obtained that correspond one-to-one with multiple video frames of the work area.

[0028] The multiple action recognition results are compared with the task start action and the task end action to determine the task start frame and task end frame in the multiple work area video frames.

[0029] The duration between the task start frame and the task end frame is used as the initial video duration.

[0030] In one possible implementation, determining the video duration for which the task personnel in the target work area meet the time-counting criteria further includes:

[0031] Multiple workpiece states are obtained, and each workpiece state corresponds one-to-one with multiple video frames in the video of the work area; the workpiece state includes the workpiece weight.

[0032] The states of the multiple workpieces are matched with the calibrated task start and task end states to obtain the task start frame and task end frame in the multiple video frames.

[0033] The duration between the task start frame and the task end frame is used as the initial video duration.

[0034] In one possible implementation, acquiring video of the work area based on data acquisition equipment includes:

[0035] Acquire the initial work area video based on the initial acquisition equipment;

[0036] Determine the resolution of the video in the initial work area, and determine whether the resolution is less than a resolution threshold;

[0037] If the number and position of the acquisition devices are less than the target number, the video of the work area acquired by the acquisition devices after adjustment is obtained.

[0038] If it is greater than or equal to, then the initial work area video is used as the work area video.

[0039] In one possible implementation, the method further includes:

[0040] Identify and record violations in the target work area based on a behavior recognition model;

[0041] The violations include not wearing protective equipment, horseplay, and sleeping.

[0042] On the other hand, the present invention also provides a time determination device for flexible work scenarios, comprising:

[0043] The work area video acquisition unit is used to acquire work area videos collected by the acquisition device and identify the personnel in the work area videos and the location of the personnel.

[0044] The work area division unit is used to determine the target work area in the work area based on the location of the person reporting the task and the duration of the task person's stay at the person's location when the person reporting the task and the task person are matched.

[0045] The work time determination unit is used to determine the video duration in the target work area that meets the work time calculation conditions for the task personnel, and to use the video duration as the work time of the task personnel.

[0046] The beneficial effects of this invention are as follows: The method for determining working hours in flexible work scenarios provided by this invention divides the work area based on the identified personnel location and the duration of the task personnel's stay at the personnel location, thereby determining the target work area within the work area. This allows for the identification of target work areas for different tasks in flexible work scenarios. Then, by statistically analyzing the working hours of the target work areas, the working hours of the task personnel under different tasks can be obtained, improving the accuracy of the working hours determined in flexible work scenarios. Furthermore, since performing a work task requires a certain amount of time, this invention determines the target work area using parameters of personnel location and the duration of the task personnel's stay at the personnel location, eliminating the adverse effects of passing through or briefly stopping at the target work area, further ensuring the accuracy of the working hours.

[0047] Furthermore, before determining the target area, the present invention matches the task personnel with the task reporting personnel to ensure that the identified task personnel are indeed task reporting personnel, thereby eliminating the influence of irrelevant personnel on the determination of the target work area and further improving the accuracy of the determined working hours. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A schematic flowchart of an embodiment of the working time determination method for flexible work scenarios provided by the present invention;

[0050] Figure 2 A schematic flowchart illustrating an embodiment of the present invention for determining a target work area;

[0051] Figure 3 A schematic diagram of an embodiment of the target work area provided by the present invention;

[0052] Figure 4 A schematic flowchart of an embodiment of the present invention for determining the duration to be removed;

[0053] Figure 5 A schematic diagram illustrating an embodiment of the video duration provided by the present invention;

[0054] Figure 6 A schematic flowchart illustrating an embodiment of the present invention for determining the distance duration;

[0055] Figure 7 A schematic diagram of an embodiment of the process for determining the insertion order provided by the present invention;

[0056] Figure 8 A schematic diagram illustrating an embodiment of the order insertion scenario provided by the present invention;

[0057] Figure 9 A schematic diagram of an embodiment of the present invention for determining the initial video duration;

[0058] Figure 10 A schematic diagram of another embodiment of the present invention for determining the initial video duration;

[0059] Figure 11 This is a schematic diagram of a process for obtaining video of a work area according to an embodiment of the present invention;

[0060] Figure 12 This is a schematic diagram of an embodiment of the working time determination device for flexible work scenarios provided by the present invention. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0062] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0063] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0064] The specific scenario for automatic determination of working hours in the prior art is: standardized, assembly line production process, which has the following characteristics: (1) single-piece flow production: flow production in the form of single pieces; (2) fixed-position production of materials: multiple processes are produced in the same area with little background change. In other words: the recognition model is used directly to identify the task personnel in the scenario, and the timing starts when there are task personnel, and the total timing time is used as the working hours. It has the following technical problems: when the work scenario is variable (i.e., the flexible work scenario in many subsequent embodiments of the present invention), i.e., multi-piece flow production, or, the work area is not fixed and changes flexibly, the automatic working hours identification method in the prior art will count the working hours of multiple tasks together, resulting in low statistical accuracy.

[0065] To address this technical problem, the present invention provides a method and apparatus for determining working hours in flexible work scenarios, which will be described below.

[0066] Figure 1A schematic flowchart of an embodiment of the working time determination method for flexible work scenarios provided by the present invention is shown below. Figure 1 As shown, the methods for determining working hours in flexible work scenarios include:

[0067] S101. Acquire video of the work area based on the acquisition device, and identify the personnel in the work area video and their locations.

[0068] The method for obtaining the work area video can be either: directly acquiring the work area video in real time based on the acquisition device during step S101, or retrieving the work area video from the storage medium that stores the work area video.

[0069] In some embodiments, the acquisition device is a video acquisition device, specifically a camera or a high-definition camera, etc.

[0070] It should be understood that the process of identifying personnel and their locations involves: using a trained personnel and location recognition model to identify the video of the work area and obtain the personnel and their locations. The personnel and location recognition model is a neural network model that takes video frames as input and outputs the personnel and their locations.

[0071] It should be noted that the neural network model can be any of the YOLO series, Faster R-CNN, SSD, etc.

[0072] In flexible work scenarios, personnel are required to wear safety helmets and other protective equipment. Therefore, the specific identification method for personnel is as follows: each personnel has a name tag attached to their back or other location. The personnel and location recognition model identifies the personnel by recognizing the name tag.

[0073] In other embodiments, personnel can be identified through morphological recognition, gait recognition, or other identification methods. Existing technologies can be used for the specific identification methods.

[0074] S102. When the task reporting personnel and the task personnel are matched, the target work area in the work area is determined based on the personnel's location and the duration of the task personnel's stay at the personnel's location.

[0075] Among them, the task reporting personnel refers to the personnel who are responsible for planning and preparing to complete the task when scheduling or planning the task.

[0076] Specifically, matching the task reporting personnel and the task personnel means that the task reporting personnel and the task personnel are the same.

[0077] S103. Determine the video duration for which the task personnel in the target work area meet the conditions for calculating work hours, and use the video duration as the work hours of the task personnel.

[0078] It should be understood that the time determination method for flexible work scenarios in the embodiments of the present invention can be implemented in any device based on the time determination method for flexible work scenarios, such as Manufacturing Operation Management (MOM) devices. Specifically, the time determination method for flexible work scenarios is stored in the aforementioned device as a pre-programmed program. When the device is started, the program is invoked, and the time determination method for flexible work scenarios is implemented.

[0079] Compared with existing technologies, the time determination method for flexible work scenarios provided by this invention divides the work area based on the identified personnel location and the duration of the task personnel's stay at the personnel location, thereby determining the target work area within the work area. This allows for the identification of target work areas for different tasks in flexible work scenarios. Then, by statistically analyzing the time spent in the target work areas, the working hours of the task personnel under different tasks can be obtained, improving the accuracy of time determination in flexible work scenarios. Furthermore, since performing a work task requires a certain amount of time, this invention determines the target work area using parameters of personnel location and the duration of the task personnel's stay at the personnel location, eliminating the adverse effects of passing through or briefly stopping at the target work area, further ensuring the accuracy of time determination.

[0080] Furthermore, in this embodiment of the invention, before determining the target area, the task personnel are matched with the task reporting personnel to ensure that the identified task personnel are indeed task reporting personnel, thereby eliminating the influence of irrelevant personnel on the determination of the target work area and further improving the accuracy of the determined working hours.

[0081] In some embodiments of the present invention, such as Figure 2 As shown, step S102, which determines the target work area based on personnel location and the duration of personnel at their location, includes:

[0082] S201. Identify the area where the workpiece is located in the video of the work area.

[0083] There are two methods for identifying the area where the workpiece is located. One method is to identify it using a pre-trained recognition model. The other method is to directly determine the area where the workpiece is located based on a pre-established three-dimensional model of the workpiece and the transformation relationship between the coordinate system of the acquisition device and the spatial coordinate system.

[0084] S202. Determine whether the distance between the personnel's position and the area where the workpiece is located is less than the preset distance.

[0085] When the distance is greater than or equal to the preset distance, it indicates that the task personnel are not working on the workpiece within the workpiece's area, and therefore this task personnel should not be included in the target work area.

[0086] S203. When the distance is less than the preset distance, determine whether the duration of the task personnel in the personnel position is greater than the preset duration.

[0087] S204. When the duration exceeds the preset duration, the rectangle enclosing the task personnel and workpieces will be used as the target work area.

[0088] It should be understood that when the duration is less than or equal to the preset duration, it means that the personnel only stay in this area briefly and are not working on this workpiece. Therefore, this personnel should not be included in the target work area.

[0089] It should also be understood that the preset distance and preset duration can be set according to the actual application scenario, and no specific limitations are made here.

[0090] In specific embodiments of the present invention, such as Figure 3 As shown, there are three personnel, namely personnel A, personnel B, and personnel C, whose distance from the workpiece is less than the preset distance. The target work area is... Figure 3 The region represented by region 1 in the diagram.

[0091] Considering that personnel may leave the workpiece for various reasons during task operations, to avoid including the time spent away in the work hours, in some embodiments of the present invention, the condition for including work hours includes the personnel appearing in the video of the work area. Figure 4 As shown, determining the video duration in step S103 includes:

[0092] S401. Use the start and end frames of the video in the work area as the initial video duration.

[0093] It should be understood that, in order for the video duration to represent the task operation duration, the video in the operation area refers to the video acquired by the acquisition device in response to the task operation start command.

[0094] S402. Determine which video frames to be removed do not contain any personnel on the task in the video of the work area, and determine the removal duration of the video frames to be removed.

[0095] S403. Use the difference between the initial video duration and the duration to be removed as the video duration.

[0096] This invention improves the accuracy of determining the work time by determining the duration for which no personnel are present in the video of the work area to be removed, thus making the work time the duration for which the personnel are removed from the video.

[0097] In specific embodiments of the present invention, such as Figure 5 As shown, Figure 5 The solid black line represents the duration of the task personnel in the video of the work area, and the dashed black line represents the duration of the task personnel not in the video of the work area. The video duration is the duration represented by the solid black line.

[0098] In practical applications, when the acquisition device has a wide field of view, the following situation may occur: the personnel are present in the video of the work area, but they are not performing any work; instead, they are resting away from the workpiece. To exclude this time from the work hours, in some embodiments of the present invention, such as... Figure 6 As shown, determining the video duration in step S103 also includes:

[0099] S601. Determine video frames in the work area video that contain personnel and whose distance from the target work area is greater than a distance threshold.

[0100] S602. Determine the distance duration of the video frame that is far from the workpiece, and use the difference between the initial video duration, the duration to be removed, and the distance duration as the video duration.

[0101] This invention utilizes the characteristic that when a worker is performing an operation on a workpiece, the distance between the worker and the target work area is relatively short. By setting up video frames that are far from the workpiece but are not performing any operations, based on the distance between the worker's location and the target work area, the accuracy of the determined work time can be further ensured.

[0102] Specifically, such as Figure 5 As shown, Figure 5 The dotted line in the text represents the distance traveled.

[0103] It's important to note that flexible work scenarios present a specific situation: different tasks may operate in the same area. In other words, there's a "task insertion" issue. This occurs when a worker, while performing their first task, needs to stop and perform a second task at the same location. After completing the second task, the first task resumes. If the time taken to determine the duration of the task is solely based on its presence in the work area video and / or its distance from the target work area, the impact of task insertion on the first task's work time cannot be effectively eliminated, leading to inaccurate work time statistics for the first task.

[0104] To address the aforementioned technical problems, in some embodiments of the present invention, the work area video includes a first work task video corresponding to a first work task and a second work task video corresponding to a second work task, such as... Figure 7 As shown, determining the video duration in step S103 also includes:

[0105] S701. When the video of the first task and the video of the second task overlap, determine the overlap duration.

[0106] The overlap duration refers to the occurrence of video frames from two different tasks at the same time in the same location, i.e., there is a situation of interpolation.

[0107] S702. Based on the video of the first task and the video of the second task, determine the inserting task and the inserted task in the first task and the second task.

[0108] The process for determining the inserting task and the inserted task is as follows: based on the first task video and the second task video, the task with the earlier start time and the earlier completion time is determined as the inserted task.

[0109] S703. The difference between the duration of the first task video and the overlap duration between the start and end frames of the task video corresponding to the inserted task is taken as the video duration of the task personnel in the inserted task.

[0110] By determining the overlap duration, this invention addresses the adverse impact of task insertion on work hours in flexible work scenarios, eliminates the insertion time, and further ensures the accuracy of work hours.

[0111] In specific embodiments of the present invention, such as Figure 8 As shown, the work tasks include Task A and Task B. The timelines of Task A and Task B can be obtained through the video of the work area. There is an overlap between the timelines of Task A and Task B. If Task B inserts Task A at this time, the actual time of Task A is the time difference between the total time of Task A and the total time of Task B.

[0112] Specifically, such as Figure 5 As shown, Figure 5 The shaded area represents the insertion duration, which is the difference between the initial video duration, the duration to be removed, the distance duration, and the insertion duration.

[0113] Since personnel need to prepare before performing tasks and clean up after completing them, these preparation and cleanup tasks are not considered actual work hours. Therefore, in some embodiments of the present invention, such as... Figure 9 As shown, determining the video duration in step S103 also includes:

[0114] S901. Based on a preset action recognition model, perform action recognition on the video of the work area to obtain multiple action recognition results that correspond one-to-one with multiple video frames of the work area.

[0115] The action recognition model can be a SlowFast Network model, which is used to accurately identify the actions of the personnel on the task.

[0116] S902. Compare the results of multiple action recognition with the task start action and the task end action to determine the task start frame and task end frame in the video frames of multiple work areas.

[0117] Among them, the task start action and the task end action are actions that are different from the actions in the work process. In other words, the task start action and the task end action are actions that are different from the work in the work process, so as to ensure the accuracy of the task start frame and the task end frame.

[0118] S903. Use the duration between the start frame and the end frame of the task as the initial video duration.

[0119] In this embodiment of the invention, the start and end frames of the video of the work area are not used as the start and end frames of the task. Other actions before and after the actual work are taken into account, which further ensures the accuracy of the work time.

[0120] As described above, the premise for determining the task start and end frames based on action recognition results is that the actions at the task start and end are different from the actions during the task process. If some tasks do not possess this characteristic, it is impossible to eliminate preparation and organization work using the above method. To address this situation, in a specific embodiment of the present invention, such as... Figure 10 As shown, determining the video duration in step S103 also includes:

[0121] S1001. Obtain multiple workpiece states, each corresponding to a video frame in the work area video; the workpiece states include workpiece weight.

[0122] S1002. Match multiple workpiece states with the calibrated task start state and task end state to obtain the task start frame and task end frame in multiple video frames.

[0123] S1003. Use the duration between the task start frame and the task end frame as the initial video duration.

[0124] The embodiments of the present invention determine the task start frame and task end frame by changing the workpiece state, without relying on the action recognition result, thereby improving the diversity of the methods for determining the task start frame and task end frame and ensuring the accuracy of the operation time.

[0125] The working status may also include other statuses such as the equipment status when it is necessary to perform operations on the workpiece, which can accurately represent the start and end of the task and determine the task start frame and task end frame.

[0126] Since the work area may include multiple tasks, in order to ensure the resolution of the video in the work area, thereby ensuring the accuracy of recognition and ultimately the accuracy of work time, in some embodiments of the present invention, such as... Figure 11 As shown, step S101 includes:

[0127] S1101. Obtain the initial work area video based on the initial acquisition device;

[0128] The initial acquisition equipment refers to the existing acquisition equipment that did not take into account flexible operating scenarios.

[0129] S1102. Determine the resolution of the initial working area video and check whether the resolution is less than the resolution threshold.

[0130] S1103. If the number and location of the acquisition devices are less than the target size, adjust the number and location of the acquisition devices and acquire the video of the work area based on the adjusted acquisition devices.

[0131] S1104. If it is greater than or equal to, then the initial work area video shall be used as the work area video.

[0132] This invention improves the resolution of the video of the work area acquired after adjustment by setting the number and position of the acquisition devices when the resolution is less than the resolution threshold. This can be achieved by increasing the number of acquisition devices and reducing their acquisition range, thereby ensuring the accuracy of the work time.

[0133] It should be understood that when the target work area is enlarged, requiring two or more acquisition devices to acquire video of the work area with the required resolution, the working hours of each acquisition device can be determined separately, and then the working hours determined by multiple acquisition devices can be superimposed to obtain the final working hours.

[0134] In practical applications, violations such as not wearing protective equipment, horseplay, and sleeping may occur while personnel are performing tasks. To monitor these violations, in some embodiments of this invention, the method for determining working hours in flexible work scenarios further includes:

[0135] Identify and record violations in the target work area based on behavior recognition models.

[0136] Among them, the behavior recognition model is a pre-built and trained model.

[0137] This invention enables the monitoring of personnel misconduct by identifying and recording violations, thereby preventing safety accidents and project delays.

[0138] In summary, the time determination method for flexible work scenarios proposed in this embodiment of the invention realizes automated time determination, reduces manual intervention, and improves the accuracy of the determined work hours. It can help management make data-driven decisions and optimize production scheduling.

[0139] To better implement the working hour determination method for flexible work scenarios in the embodiments of the present invention, the embodiments of the present invention also provide a working hour determination device for flexible work scenarios, such as... Figure 12 As shown, the time determination device 1200 for flexible work scenarios includes:

[0140] The work area video acquisition unit 1201 is used to acquire work area video based on acquisition equipment, and identify the task personnel and their locations in the work area video.

[0141] The work area division unit 1202 is used to determine the target work area in the work area based on the personnel location and the duration of the task personnel in the personnel location when the task reporting personnel and the task personnel are matched.

[0142] The work time determination unit 1203 is used to determine the video duration of the task personnel in the target work area that meets the conditions for work time calculation, and to use the video duration as the work time of the task personnel.

[0143] The flexible work scenario time determination device 1200 provided in the above embodiments can realize the technical solutions described in the above flexible work scenario time determination method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above flexible work scenario time determination method embodiments, which will not be repeated here.

[0144] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0145] The above provides a detailed description of the method and apparatus for determining working hours in flexible work scenarios provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining working hours in flexible work scenarios, characterized in that, include: Acquire video of the work area collected by the acquisition device, and identify the personnel in the video of the work area and their locations; When a task reporting person and a task personnel are matched, the target work area in the work area is determined based on the personnel's location and the duration of the task personnel's stay at the personnel's location; Determine the video duration in the target work area that meets the conditions for calculating work hours for the task personnel, and use the video duration as the work hours for the task personnel; The determination of the video duration for which the task personnel in the target work area meet the conditions for time calculation includes: Multiple workpiece states are acquired, and each workpiece state corresponds one-to-one with multiple video frames in the video of the work area; the workpiece state includes the workpiece weight. The states of the multiple workpieces are matched with the calibrated task start and task end states to obtain the task start frame and task end frame in the multiple video frames. The duration between the task start frame and the task end frame is used as the initial video duration. Determine that there are no video frames to be removed for the task personnel in the video of the work area, and determine the removal duration of the video frames to be removed; Determine the video frame in the work area where the task personnel are present and the distance between the task personnel's location and the target work area is greater than a distance threshold, and determine the duration of the distance from the workpiece in the video frame. The difference between the initial video duration, the duration to be eliminated, and the duration of distance is taken as the video duration. When the work area video includes a first work task video and a second work task video, determining the video duration for which the personnel in the target work area meet the conditions for time calculation further includes: When the first task video and the second task video overlap, determine the overlap duration; Based on the first task video and the second task video, determine the inserting task and the inserted task in the first task and the second task. The difference between the first task video duration and the overlap duration between the start and end frames of the task video corresponding to the inserted task is taken as the video duration of the task personnel in the inserted task.

2. The method for determining working hours in flexible work scenarios according to claim 1, characterized in that, The step of determining the target work area within the work area based on the personnel's location and the duration of the task personnel's stay at the personnel's location includes: Identify the area where the workpiece is located in the video of the work area; Determine whether the distance between the personnel's location and the area where the workpiece is located is less than a preset distance; When the distance is less than a preset distance, determine whether the duration of the task personnel in the personnel position is greater than a preset duration; When the duration exceeds the preset duration, the rectangle enclosing the task personnel and the workpiece will be used as the target work area.

3. The method for determining working hours in flexible work scenarios according to claim 1, characterized in that, The determination of the video duration for which the task personnel in the target work area meet the conditions for time calculation also includes: Based on a preset action recognition model, the video of the work area is used to perform action recognition, and multiple action recognition results are obtained that correspond one-to-one with multiple video frames of the work area. The multiple action recognition results are compared with the task start action and the task end action to determine the task start frame and task end frame in the multiple work area video frames. The duration between the task start frame and the task end frame is used as the initial video duration.

4. The method for determining working hours in flexible work scenarios according to claim 1, characterized in that, Acquire video of the work area based on the acquisition device, including: Acquire the initial work area video based on the initial acquisition equipment; Determine the resolution of the video in the initial work area, and determine whether the resolution is less than a resolution threshold; If the number and position of the acquisition devices are less than the target number, the video of the work area acquired by the acquisition devices after adjustment is obtained. If it is greater than or equal to, then the initial work area video is used as the work area video.

5. The method for determining working hours in flexible work scenarios according to claim 1, characterized in that, The method further includes: Identify and record violations in the target work area based on a behavior recognition model; The violations include not wearing protective equipment, horseplay, and sleeping.

6. A time determination device for flexible work scenarios, characterized in that, The method for determining working hours in flexible work scenarios according to any one of claims 1-5, the apparatus comprising: The work area video acquisition unit is used to acquire work area videos collected by the acquisition device and identify the personnel in the work area videos and the location of the personnel. The work area division unit is used to determine the target work area in the work area based on the location of the person reporting the task and the duration of the task person's stay at the person's location when the person reporting the task and the task person are matched. The work time determination unit is used to determine the video duration in the target work area that meets the work time calculation conditions for the task personnel, and to use the video duration as the work time of the task personnel.

Images