Method and device for determining working hours in flexible working scene

Abstract

The invention provides a man-hour determination method and device in a flexible operation scene, and belongs to the technical field of man-hour determination, and the method comprises the steps: obtaining an operation region video collected based on a collection device, and recognizing task personnel in the operation region video and the personnel positions of the task personnel; when the task worker is matched with the task worker, determining a target operation area in the operation area based on the worker position and the duration of the task worker in the worker position; and determining the video duration of the task personnel meeting the man-hour counting condition in the target operation area, and taking the video duration as the operation man-hour of the task personnel. According to the method, the target operation areas of different tasks can be determined in the flexible operation scene, and then the working hours of the target operation areas are counted, so that the working hours of task personnel under different tasks can be obtained, and the accuracy of the determined working hours under the flexible operation scene is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of man-hour determination, and in particular to a method and device for determining man-hours in a flexible working scenario. Background Art

[0002] The working hour quota is the basic unit of cost measurement. It is the most widely used cost management tool in manufacturing enterprises and an important basis for enterprises to reasonably carry out production planning and production scheduling. It is also the basis and important premise for enterprises to carry out scientific management and improve labor productivity. The premise of the working hour quota is to accurately determine the working hours of task personnel when completing the task.

[0003] The determination of traditional working hours relies on manual reporting, which is subject to problems such as task operation errors and data inconsistency, making it difficult to ensure the accuracy and real-time nature of working hour data. In order to solve this technical problem, the prior art proposes a solution for automatically identifying and recording working hours, specifically: installing camera points, and determining working hours based on the videos collected by the camera points, but this technology is suitable for fixed work scenarios, that is: the tasks in the scene are single, and each tasker is only responsible for one work task. However, when the tasks in the scene are diverse and changeable, and the same tasker needs to stagger production in multiple tasks and other complex situations, the prior art cannot accurately identify different tasks, which leads to inaccurate determined working hours.

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

[0005] In view of this, it is necessary to provide a method and device for determining working hours in a flexible working scenario to solve the technical problem that the prior art cannot adapt to flexible working scenarios, resulting in low accuracy of working hours determined in flexible working scenarios.

[0006] On the one hand, in order to solve the above technical problems, the present invention provides a method for determining working hours in a flexible working scenario, comprising: Acquire a video of the work area collected by a collection device, and identify a task person in the video of the work area and a position of the task person; When the task reporting person matches the task personnel, determining the target work area in the work area based on the personnel position and the duration of the task personnel at the personnel position; Determine the video duration of the task personnel in the target work area that meets the working hours counting condition, and use the video duration as the working hours of the task personnel.

[0007] In a possible implementation, determining a target working area in the working area based on the personnel location and the duration of the task personnel at the personnel location includes: Identifying the area where the workpiece is located in the video of the working area; Determining whether the distance between the personnel location and the area where the workpiece is located is less than a preset distance; When the distance is less than the preset distance, determining whether the duration of the task personnel at the personnel location is greater than a preset duration; When the duration is greater than the preset duration, taking the rectangular frame enclosing the task personnel and the workpiece as the target working area.

[0008] In a possible implementation, determining the video duration for which the task personnel in the target working area meet the working hour accounting condition includes: Taking the start frame and the end frame of the video of the working area as the initial video duration; Determining the video frames to be excluded in the video of the working area where the task personnel do not exist, and determining the duration to be excluded of the video frames to be excluded; Taking the difference between the initial video duration and the duration to be excluded as the video duration.

[0009] In a possible implementation, determining the video duration for which the task personnel in the target working area meet the working hour accounting condition further includes: Determining the video frames of the task personnel away from the workpiece in the video of the working area where the task personnel exist and the distance between the location of the task personnel and the target working area is greater than a distance threshold; Determining the duration of being away of the video frames away from the workpiece, and taking the difference between the initial video duration, the duration to be excluded and the duration of being away as the video duration.

[0010] In a possible implementation, if the video of the working area includes a first working task video and a second working task video, then determining the video duration for which the task personnel in the target working area meet the working hour accounting condition further includes: When there is an overlap between the first working task video and the second working task video, determining the overlap duration; Based on the first working task video and the second working task video, determining the inserted task and the task being inserted among the first task and the second task; Taking the difference between the first task video duration between the start frame and the end frame of the working task video corresponding to the task being inserted and the overlap duration as the video duration of the task personnel in the task being inserted.

[0011] In a possible implementation, determining the video duration in which the task personnel in the target work area meet the working hour inclusion condition further includes: Performing action recognition on the work area video based on a preset action recognition model to obtain a plurality of action recognition results corresponding one by one to a plurality of work area video frames; Comparing the plurality of action recognition results with the task start action and the task end action to determine the task start frame and the task end frame in the plurality of work area video frames; Taking the duration between the task start frame and the task end frame as the initial video duration.

[0012] In a possible implementation, determining the video duration in which the task personnel in the target work area meet the working hour inclusion condition further includes: Obtaining a plurality of workpiece states of the workpiece, the plurality of workpiece states corresponding one by one to a plurality of video frames in the work area video; the workpiece state includes the workpiece weight; Matching the plurality of workpiece states with the calibrated task start state and task end state to obtain the task start frame and the task end frame in the plurality of video frames; Taking the duration between the task start frame and the task end frame as the initial video duration.

[0013] In a possible implementation, obtaining the work area video collected by the collection device includes: Obtaining an initial work area video collected by an initial collection device; Determining the resolution of the initial work area video and determining whether the resolution is less than a resolution threshold; If it is less, adjusting the number and position of the collection devices and obtaining the work area video collected by the adjusted collection devices; If it is greater than or equal to, taking the initial work area video as the work area video.

[0014] In a possible implementation, the method further includes: Identifying and recording violation behaviors in the target work area based on a behavior recognition model; The violation behaviors include not wearing protective equipment, roughhousing behaviors, and sleeping behaviors.

[0015] On the other hand, the present invention also provides a working hour determination device in a flexible work scenario, including: A work area video acquisition unit, configured to acquire a work area video collected by a collection device, and identify a task personnel in the work area video and a personnel position where the task personnel is located; An operation area division unit, configured to determine a target operation area in the operation area based on the personnel location and the duration of the task personnel at the personnel location when the task reporting personnel and the task personnel match; An operation working hour determination unit, configured to determine the video duration in which the task personnel in the target operation area meet the working hour inclusion condition, and use the video duration as the working hours of the task personnel.

[0016] The beneficial effects of the present invention are as follows: The working hour determination method in a flexible operation scenario provided by the present invention divides the operation area based on the identified personnel location and the duration of the task personnel at the personnel location, and determines the target operation area in the operation area. The target operation areas of different tasks can be determined in a flexible operation scenario, and then the working hours of the target operation area are counted, so that the working hours of the task personnel under different tasks can be obtained, improving the accuracy of the working hours determined in a flexible operation scenario. Moreover, since it takes a certain duration to execute an operation task, the present invention determines the target operation area through the two-dimensional parameters of the personnel location and the duration of the task personnel at the personnel location, eliminating the adverse impact of passing through the target operation area and staying briefly on the target operation area, and further ensuring the accuracy of the working hours.

[0017] Further, 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 the task reporting personnel, eliminating the influence of idle personnel on the determination of the target operation area, and further improving the accuracy of the determined working hours. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart of an embodiment of the working hour determination method in a flexible operation scenario provided by the present invention; Figure 2 It is a schematic flowchart of an embodiment of determining the target operation area provided by the present invention; Figure 3 It is a schematic diagram of an embodiment of the target operation area provided by the present invention; Figure 4 It is a schematic flowchart of an embodiment of determining the duration to be excluded provided by the present invention; Figure 5 It is a schematic diagram of an embodiment of the video duration provided by the present invention; Figure 6 Schematic flowchart of an embodiment for determining the away duration provided by the present invention; Figure 7 Schematic flowchart of an embodiment for determining order insertion provided by the present invention; Figure 8 Schematic diagram of an embodiment of the order insertion situation provided by the present invention; Figure 9 Schematic flowchart of an embodiment for determining the initial video duration provided by the present invention; Figure 10 Schematic flowchart of another embodiment for determining the initial video duration provided by the present invention; Figure 11 Schematic flowchart of an embodiment for obtaining the video of the operation area provided by the present invention; Figure 12 Schematic structural diagram of an embodiment of the working hour determination device in the flexible operation scenario provided by the present invention. Detailed implementation manners

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0021] It should be understood that the schematic drawings are not drawn to actual scale. The flowcharts used in the present invention illustrate the operations implemented according to some embodiments of the present invention. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present invention. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0022] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in conjunction with the embodiments can be included in at least one embodiment of the present invention. The phrase appears at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0023] The specific scenario of automatic working hour determination in the prior art is as follows: in a standardized and assembly-line production process, which has the following characteristics: (1) single-piece flow production: production is carried out in the form of single pieces; (2) production with materials in fixed positions: multiple processes are carried out in the same area, and the background changes less. In other words: directly use an identification model to identify the task personnel in the scenario, start timing when there are task personnel, and take the total timing duration as the working hours of the operation. It has the following technical problems: when the operation scenario is variable (i.e., the flexible operation scenarios in many subsequent embodiments of the present invention), that is: multi-piece flow production, or, the operation area is not fixed and changes flexibly, based on the prior art's automatic working hour identification method, the working hours of multiple tasks will be counted together, resulting in the problem of low statistical accuracy.

[0024] To solve this technical problem, the present invention provides a method and device for determining working hours in a flexible operation scenario, which will be described separately below.

[0025] Figure 1 It is a schematic flowchart of an embodiment of the method for determining working hours in a flexible operation scenario provided by the present invention, as Figure 1 shown, the method for determining working hours in a flexible operation scenario includes: S101. Obtain the video of the operation area collected by the collection device, and identify the task personnel in the video of the operation area and the personnel position where the task personnel are located.

[0026] Among them, the way to obtain the video of the operation area can be: when performing step S101, directly and real-time collect the video of the operation area based on the collection device, or it can also be: call the video of the operation area from the storage medium storing the video of the operation area.

[0027] In some embodiments, the collection device is a video collection device, specifically, it can be a camera or a high-definition camera, etc.

[0028] It should be understood that: the identification process of the task personnel and the personnel position is specifically: based on the trained personnel and position identification model, identify the video of the operation area to obtain the task personnel and the personnel position. Among them, the personnel and position identification model is a neural network model with video frames as the input and the task personnel and the personnel position as the output.

[0029] It should be noted that the neural network model can be any one of the YOLO series, Faster R-CNN, SSD, etc.

[0030] Among them, since task personnel need to wear protective equipment such as safety helmets in flexible operation scenarios, the specific identification method for task personnel is as follows: Each task personnel has their own nameplate attached to their back or other positions, and the personnel and position identification model identifies the nameplate to obtain the task personnel.

[0031] In other embodiments, task personnel can also be determined through identification methods such as morphology recognition and gait recognition. The specific identification method can adopt existing technologies.

[0032] S102. When the task reporting personnel and the task personnel match, determine the target operation area in the operation area based on the personnel position and the duration of the task personnel at the personnel position.

[0033] Among them, the task reporting personnel refers to the proposed task personnel who report that they are ready to complete this operation task when scheduling or planning the task.

[0034] Specifically, the matching of the task reporting personnel and the task personnel means that the task reporting personnel and the task personnel are the same.

[0035] S103. Determine the video duration in which the task personnel in the target operation area meet the working hour counting conditions, and use the video duration as the working hours of the task personnel.

[0036] It should be understood that: The working hour determination method in the flexible operation scenario in the embodiments of the present invention can be implemented in any device based on the working hour determination method in the flexible operation scenario. For example: Manufacturing Operation Management (MOM) devices, etc. Specifically, the working hour determination method in the flexible operation scenario is stored in the above-mentioned device in the form of a prepared program. When the device is started, the program is called, and the working hour determination method in the flexible operation scenario is implemented.

[0037] Compared with the prior art, the working hour determination method in the flexible operation scenario provided by the embodiments of the present invention divides the operation area by setting the personnel position identified and the duration of the task personnel at the personnel position, determines the target operation area in the operation area, can determine the target operation area of different tasks in the flexible operation scenario, and then statistically calculates the working hours of the target operation area, so as to obtain the working hours of the task personnel under different tasks, improving the accuracy of the working hours determined in the flexible operation scenario. And, since it takes a certain duration to execute the operation task, therefore, the embodiments of the present invention determine the target operation area through the two-dimensional parameters of the personnel position and the duration of the task personnel at the personnel position, eliminating the adverse impact of passing through the target operation area and staying briefly on the target operation area, further ensuring the accuracy of the working hours.

[0038] Furthermore, before determining the target area, the embodiment of the present invention matches the task personnel with the task reporting personnel to ensure that the identified task personnel are the task reporting personnel, eliminating the influence of idlers on the determination of the target operation area and further improving the accuracy of the determined working hours.

[0039] In some embodiments of the present invention, as Figure 2 shown, determining the target operation area in the operation area based on the personnel position and the duration of the task personnel at the personnel position in step S102 includes: S201. Identify the area where the workpiece is located in the video of the operation area.

[0040] There are two methods for identifying the area where the workpiece is located. One is to identify through a pre-trained identification model, and the other is to directly determine the area where the workpiece is located based on the pre-established three-dimensional model of the workpiece and the conversion relationship between the coordinate system of the acquisition device and the spatial coordinate system.

[0041] S202. Determine whether the distance between the personnel position and the area where the workpiece is located is less than a preset distance.

[0042] When the distance is greater than or equal to the preset distance, it means that the task personnel are not operating on the workpiece in the area where the workpiece is located. Therefore, this task personnel should not be included in the target operation area.

[0043] S203. When the distance is less than the preset distance, determine whether the duration of the task personnel at the personnel position is greater than the preset duration; S204. When the duration is greater than the preset duration, use the rectangular frame enclosing the task personnel and the workpiece as the target operation area.

[0044] It should be understood that when the duration is less than or equal to the preset duration, it means that the task personnel only stay in this area briefly and are not operating on this workpiece. Therefore, this task personnel does not need to be included in the target operation area.

[0045] It should also be understood that both the preset distance and the preset duration can be set according to the actual application scenario and are not specifically limited here.

[0046] In a specific embodiment of the present invention, as Figure 3 shown, there are three task personnel whose distances from the workpiece are less than the preset distance, namely personnel A, personnel B, and personnel C. Then the target operation area is Figure 3 the area represented by area 1 in

[0047] Considering that the task personnel may leave the workpiece due to some reasons during the task operation, in order to avoid including the leaving time in the working hours, in some embodiments of the present invention, the working hour inclusion condition includes that the task personnel appear in the video of the operation area. Then, as Figure 4 shown, determining the video duration in step S103 includes: S401. Taking the start frame and end frame of the video of the operation area as the initial video duration.

[0048] It should be understood that: in order to make the video duration represent the task operation duration, the video of the operation area refers to the video collected by the acquisition device in response to the task operation start instruction.

[0049] S402. Determining the video frames to be excluded in the video of the operation area where there is no task personnel, and determining the duration to be excluded of the video frames to be excluded; S403. Taking the difference between the initial video duration and the duration to be excluded as the video duration.

[0050] By determining the duration to be excluded in the video of the operation area where there is no task personnel in the embodiments of the present invention, the working hours of the operation are the duration after excluding the time when the task personnel leave the video, which improves the accuracy of the determined working hours of the operation.

[0051] In a specific embodiment of the present invention, as Figure 5 shown, Figure 5 The black solid line in represents the duration of the task personnel in the video of the operation area, and the black dashed line represents the duration when the task personnel are not in the video of the operation area. Then the video duration is the duration represented by the black solid line.

[0052] In an actual application scenario, when the shooting field of view of the acquisition device is relatively wide, the following situation will also occur: the task personnel are present in the video of the operation area, but the task personnel do not perform the operation but rest at a place far from the workpiece. In order to exclude this duration from the working hours of the operation, in some embodiments of the present invention, as Figure 6 shown, determining the video duration in step S103 further includes: S601. Determining the video frames far from the workpiece in the video of the operation area where there are task personnel and the distance between the position of the task personnel and the target operation area is greater than the distance threshold; S602. Determining the duration far from the workpiece of the video frames far from the workpiece, and taking the difference between the initial video duration, the duration to be excluded and the duration far from the workpiece as the video duration.

[0053] In an embodiment of the present invention, taking advantage of the fact that when a task worker performs an operation on a workpiece, the distance between the task worker and the target operation area is relatively close, a video frame far from the workpiece in the operation area video where the task worker is located but not performing an operation is set based on the distance between the position of the task worker and the target operation area, which can further ensure the accuracy of the determined operation time.

[0054] Specifically, as Figure 5 shown, Figure 5 the dotted line in

[0055] It should be noted that: there is a specific situation in the flexible operation scenario: the operation areas of different operation tasks are the same. In other words, there is an order-insertion situation in the flexible operation scenario. The order-insertion situation means that when a task worker is performing a first operation task, the task worker needs to stop performing the first operation task and perform a second operation task at the same location. After the second operation task is completed, the first operation task is performed again. If the operation duration is judged only by whether it exists in the operation area video and / or the distance from the target operation area, the influence of the order-insertion situation on the operation time of the first operation task cannot be effectively eliminated, resulting in inaccurate statistics of the operation time of the first operation task.

[0056] To solve the above technical problems, in some embodiments of the present invention, the operation area video includes a first operation task video corresponding to the first operation task and a second operation task video corresponding to the second operation task. Then, as Figure 7 shown, determining the video duration in step S103 further includes: S701. When there is an overlap between the first operation task video and the second operation task video, determine the overlap duration.

[0057] Wherein, the overlap duration refers to that two different operation task video frames appear at the same position at the same time, that is: there is an order-insertion situation.

[0058] S702. Determine the order-insertion task and the task being inserted in the first task and the second task based on the first operation task video and the second operation task video.

[0059] Wherein, the determination process of the order-insertion task and the task being inserted is: based on the first operation task video and the second operation task video, determine the operation task with an earlier start time and a later completion time as the task being inserted.

[0060] S703. Take the difference between the first task video duration between the start frame and the end frame of the operation task video corresponding to the task being inserted and the overlap duration as the video duration of the task worker in the task being inserted.

[0061] In the embodiments of the present invention, by determining the overlapping duration, the adverse impact on the operation man-hours when a task is inserted in a flexible operation scenario is solved, the inserted order time is eliminated, and the accuracy of the operation man-hours is further ensured.

[0062] In a specific embodiment of the present invention, as Figure 8 shown, the operation tasks include Task A and Task B. The time axis of Task A and the time axis of Task B can be obtained through the video of the operation area. There is an overlapping time period between the time axis of Task A and the time axis of Task B. If Task B is inserted into Task A at this time, the actual time of Task A is the time difference between the total time of the time axis of Task A and the total time of Task B.

[0063] Specifically, as Figure 5 shown, Figure 5 the shaded part in

[0064] is the inserted order duration, that is: the video duration is the difference between the initial video duration and the duration to be eliminated, the away duration and the inserted order duration. Figure 9 Since the task personnel also need to prepare before the task operation and need to tidy up after the task operation, etc., the preparation work and tidying up work, etc. are not the actual operation man-hours. Therefore, in some embodiments of the present invention, as shown, determining the video duration in step S103 further includes:

[0065] S901. Perform action recognition on the operation area video based on a preset action recognition model to obtain multiple action recognition results corresponding to multiple operation area video frames one by one.

[0066] S902. Compare the multiple action recognition results with the task start action and the task end action to determine the task start frame and the task end frame in the multiple operation area video frames.

[0067] Among them, the task start action and the task end action are actions different from the operation process actions. In other words, the task start action and the task end action are actions different from the work in the operation process, so as to ensure the accuracy of the task start frame and the task end frame.

[0068] S903. Take the duration between the task start frame and the task end frame as the initial video duration.

[0069] The embodiments of the present invention do not take the start frame and the end frame of the operation area video as the task start frame and the task end frame, considering other actions before and after the actual operation, and further ensuring the accuracy of the operation man-hours.

[0070] As described above, the prerequisite for determining the task start frame and the task end frame based on the action recognition result is that the actions at the task start and end are different from the actions during the task process. If some tasks do not have this characteristic, it is impossible to eliminate the preparation and sorting work through the above method. To address this situation, in a specific embodiment of the present invention, as Figure 10 shown, determining the video duration in step S103 further includes: S1001. Obtain multiple workpiece states of the workpiece, and the multiple workpiece states correspond one-to-one to multiple video frames in the operation area video; the workpiece state includes the workpiece weight. S1002. Match the multiple workpiece states with the calibrated task start state and task end state to obtain the task start frame and task end frame in the multiple video frames. S1003. Use the duration between the task start frame and the task end frame as the initial video duration.

[0071] In the embodiment of the present invention, the task start frame and the task end frame are determined through the change of the workpiece state, without relying on the action recognition result, which improves the diversity of the method for determining the task start frame and the task end frame and ensures the accuracy of the operation working hours.

[0072] Among them, the working state may further include other states that can accurately represent the start and end of the task, such as the equipment state when the equipment needs to be used to operate on the workpiece, etc., to determine the task start frame and the task end frame.

[0073] Since there are multiple tasks in the operation area, therefore, in order to ensure the resolution of the operation area video to ensure the recognition accuracy and further ensure the accuracy of the operation working hours, in some embodiments of the present invention, as Figure 11 shown, step S101 includes: S1101. Obtain the initial operation area video collected based on the initial collection device. Among them, the initial collection device refers to the original existing collection device without considering the flexible operation scenario.

[0074] S1102. Determine the resolution of the initial operation area video, and judge whether the resolution is less than the resolution threshold. S1103. If it is less, adjust the number and position of the collection devices, and obtain the operation area video collected based on the adjusted collection devices. S1104. If it is greater than or equal to, use the initial operation area video as the operation area video.

[0075] In an embodiment of the present invention, by setting that when the resolution is less than the resolution threshold, the number and positions of the acquisition devices are adjusted, the resolution of the video of the operation area acquired after adjustment can be improved by increasing the number of acquisition devices and narrowing the acquisition range of the acquisition devices, thereby ensuring the accuracy of the operation working hours.

[0076] It should be understood that when the target operation area is enlarged and two or more acquisition devices are required to acquire the video of the operation area with the required resolution, the operation working hours of each acquisition device can be determined respectively, and then the operation working hours determined by multiple acquisition devices can be added up to obtain the final operation working hours.

[0077] In an actual application scenario, when the task personnel are performing tasks, there will be violation behaviors such as not wearing protective equipment, playing around, and sleeping. To implement the supervision of these violation behaviors, in some embodiments of the present invention, the method for determining working hours in a flexible operation scenario further includes: Identifying and recording violation behaviors in the target operation area based on the behavior recognition model.

[0078] Wherein, the behavior recognition model is a pre-constructed and trained model.

[0079] By identifying and recording the violation behaviors in the embodiments of the present invention, the supervision of the violation behaviors of the task personnel can be realized, and safety accidents and project delays can be avoided.

[0080] In summary, the method for determining working hours in a flexible operation scenario proposed in the embodiments of the present invention realizes the automatic determination of working hours, reduces manual intervention, and improves the accuracy of the determined operation working hours, which can help the management make data-driven decisions and optimize production scheduling.

[0081] To better implement the method for determining working hours in a flexible operation scenario in the embodiments of the present invention, correspondingly, based on the method for determining working hours in a flexible operation scenario, the embodiments of the present invention further provide a device for determining working hours in a flexible operation scenario, as Figure 12 shown, the device 1200 for determining working hours in a flexible operation scenario includes: An operation area video acquisition unit 1201, configured to acquire the video of the operation area acquired by the acquisition device, and identify the task personnel in the video of the operation area and the personnel positions where the task personnel are located; An operation area division unit 1202, configured to determine the target operation area in the operation area based on the personnel position and the duration of the task personnel at the personnel position when the task reporting worker and the task personnel match; An operation working hours determination unit 1203, configured to determine the video duration in which the task personnel in the target operation area meet the working hours inclusion condition, and use the video duration as the operation working hours of the task personnel.

[0082] The working hour determination device 1200 in the flexible operation scenario provided by the above embodiments can implement the technical solutions described in the embodiments of the working hour determination method in the flexible operation scenario. For the specific implementation principles of the above modules or units, reference can be made to the corresponding content in the embodiments of the working hour determination method in the flexible operation scenario, which will not be elaborated here.

[0083] Those skilled in the art can understand that all or part of the processes for implementing the methods of the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0084] The above has introduced in detail a working hour determination method and device provided by the present invention. Specific examples are used in this article to elaborate on the principles and implementation manners of the present invention. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for determining working hours in a flexible working scenario, characterized in that: include: Acquire a video of the work area collected by a collection device, and identify a task person in the video of the work area and a position of the task person; When the task reporting person matches the task personnel, determining the target work area in the work area based on the personnel position and the duration of the task personnel at the personnel position; Determine the video duration of the task personnel in the target work area that meets the working hours counting condition, and use the video duration as the working hours of the task personnel.

2. The method for determining working hours in a flexible working scenario according to claim 1, characterized in that: The step of determining a target operating area in an operating area based on the personnel position and the duration of time the task personnel are at the personnel position includes: Identify the area where the workpiece is located in the video of the working area; Determine whether the distance between the position of the personnel and the area where the workpiece is located is less than a preset distance; When the distance is less than the preset distance, determining whether the duration of the task personnel at the personnel position is greater than the preset duration; When the duration is greater than the preset duration, a rectangular frame enveloping the task personnel and the workpiece is used as the target operation area.

3. The method for determining working hours in a flexible working scenario according to claim 1, characterized in that: The step of determining the video duration of the task personnel in the target operation area that meets the working time counting condition includes: Taking the start frame and the end frame of the operation area video as the initial video duration; Determine that there are no video frames to be removed in the work area video in which the task personnel are present, and determine the length of time for which the video frames to be removed are to be removed; The difference between the initial video duration and the duration to be removed is used as the video duration.

4. The method for determining working hours in a flexible working scenario according to claim 3 is characterized in that: The step of determining the video duration of the task personnel in the target operation area that meets the working time counting condition further includes: Determine the video frame far away from the workpiece that the task personnel exists in the work area video and the distance between the position of the task personnel and the target work area is greater than a distance threshold; The distance time of the video frame away from the artifact is determined, and the difference between the initial video time, the time to be removed and the distance time is used as the video time.

5. The method for determining working hours in a flexible working scenario according to claim 1, characterized in that: The work area video includes a first work task video and a second work task video, and the step of determining the video duration of the task personnel in the target work area that meets the working time counting condition further includes: When the first operation task video and the second operation task video overlap, determining the overlapping duration; Determine an inserting task and an inserted task in the first task and the second task based on the first operation task video and the second operation task video; The difference between the first task video duration between the start frame and the end frame of the work task video corresponding to the inserted task and the overlapping duration is used as the video duration of the task personnel in the inserted task.

6. The method for determining working hours in a flexible working scenario according to claim 3, characterized in that: The step of determining the video duration of the task personnel in the target operation area that meets the working time counting condition further includes: Performing action recognition on the operation area video based on a preset action recognition model to obtain a plurality of action recognition results corresponding to a plurality of operation area video frames; Compare the multiple action recognition results with the task start action and the task end action to determine the task start frame and the task end frame in the multiple operation area video frames; The duration between the task start frame and the task end frame is used as the initial video duration.

7. The method for determining working hours in a flexible working scenario according to claim 3, characterized in that: The step of determining the video duration of the task personnel in the target operation area that meets the working time counting condition further includes: Acquire multiple workpiece states of the workpiece, wherein the multiple workpiece states correspond one-to-one to multiple video frames in the video of the operation area; the workpiece states include the weight of the workpiece; Matching the multiple workpiece states with the calibrated task start states and task end states to obtain task start frames and task end frames in the multiple video frames; The duration between the task start frame and the task end frame is used as the initial video duration.

8. The method for determining working hours in a flexible working scenario according to claim 1, characterized in that: Get the video of the working area collected by the acquisition equipment, including: Acquire the initial operation area video collected by the initial acquisition device; Determine the resolution of the initial operation area video, and judge whether the resolution is less than a resolution threshold; If it is less than, the number and position of the acquisition devices are adjusted, and the video of the operation area acquired based on the adjusted acquisition devices is obtained; If it is greater than or equal to, the initial working area video is used as the working area video.

9. The method for determining working hours in a flexible working scenario according to claim 1, characterized in that: The method further comprises: Identify and record illegal behaviors in the target operation area based on a behavior recognition model; Said violations included failure to wear protective gear, roughhousing and sleeping behavior.

10. A working time determination device in a flexible working scenario, characterized in that: include: An operation area video acquisition unit, used to acquire an operation area video acquired by an acquisition device, and identify a task person in the operation area video and a position of the task person; An operation area division unit, for determining a target operation area in an operation area based on a position of the person and a duration of time that the task person is at the position of the person when a task reporting person matches the task person; The operation working time determination unit is used to determine the video duration of the task personnel in the target operation area that meets the working time counting conditions, and use the video duration as the operation working time of the task personnel.

Images