Work analysis device and work analysis method
The work analysis device and method address the challenge of complex tasks by analyzing worker movements, comparing with expert models, and providing visualized improvement elements, enhancing the understanding of overall work status and optimization.
Patent Information
- Application Number
- JP2023086966
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-26
- Publication Date
- 2024-12-06
AI Technical Summary
Conventional work analysis methods struggle to provide an overview of complex tasks involving movement between multiple work sections, as they are time-consuming and fail to grasp the overall situation effectively.
A work analysis device and method that analyze a worker's work situation through video footage, extracting flow line information, comparing it with an expert model, and generating display information that visualizes improvement elements, including flow line images and superimposing them on workplace maps.
Enables easy grasping of the overall work status, even in complex scenarios, by visualizing improvement factors and allowing comparison with expert models and past performance, facilitating efficient work optimization.
Smart Images

Figure 2024170040000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an activity analysis device and an activity analysis method that output analytical information on the activity status of a worker based on a video of the activity of the worker. [Background technology]
[0002] In factories, for example, work efficiency can be improved by analyzing the work status of workers and reviewing work procedures based on the results of that analysis.
[0003] As a technique for analyzing such a worker's working situation, a technique for outputting analytical information on the working situation of a worker based on a video of the worker's working state is known (see Patent Document 1). With this technique, model behavior cases with high efficiency are selected as motion cases to be compared with the motion cases to be analyzed, and analytical information on the motion cases to be analyzed and analytical information on the model behavior cases are output, making it possible to easily check the proficiency (efficiency) of the worker's work actions. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] International Publication No. 2021 / 131552 Summary of the Invention [Problem to be solved by the invention]
[0005] Conventional techniques can check the work status of a worker when the worker stays in a specific location to perform the work. On the other hand, there are cases where the worker performs the work while moving between multiple work sections. In such cases, conventional techniques can, for example, evaluate the work performed in each work section individually and integrate the evaluation results for the multiple work sections. However, such analysis techniques have the problem that, while they are time-consuming, they make it difficult to grasp the overall status of complex work.
[0006] Therefore, the main object of the present invention is to provide a work analysis device and a work analysis method that allow a user to easily grasp the overall status of a work task, even if the work is complex and involves moving between multiple work areas. [Means for solving the problem]
[0007] The work analysis device of the present invention is a work analysis device that uses a processor to execute a process of outputting analytical information regarding the work status of a worker based on video footage of the worker working, and the processor is configured to obtain movement line information representing the work status of a target worker based on the video footage of a series of tasks performed by the worker including movement between multiple work sections, compare the movement line information regarding the target worker with movement line information regarding an expert model, and determine whether or not there are areas for improvement in the work of the target worker based on the degree of deviation between the two, and generate display information including a movement line image that visualizes the areas for improvement as the analytical information.
[0008] Furthermore, the work analysis method of the present invention is a work analysis method in which a processor executes a process to output analytical information regarding the work status of a worker based on video footage of the worker working, and is configured to obtain movement line information representing the work status of a target worker based on the video footage of a series of tasks performed by the worker including movement between a number of work sections, compare the movement line information regarding the target worker with movement line information regarding an expert model, and determine whether or not there are areas for improvement in the work of the target worker based on the degree of deviation between the two, and generate display information including a movement line image that visualizes the areas for improvement as the analytical information. Effect of the Invention
[0009] According to the present invention, a traffic line image is displayed that visualizes the improvement factors in the work of a target worker, allowing the user to easily grasp the overall status of the work, even if the work is complex and requires moving between multiple work areas. [Brief description of the drawings]
[0010] [Figure 1] Overall configuration of a work analysis system according to the present embodiment. [Diagram 2] Block diagram showing the general configuration of the server [Diagram 3] Flow diagram showing the processing steps performed on the server [Figure 4] FIG. 13 is an explanatory diagram showing a map screen displayed on a user terminal. [Diagram 5] FIG. 13 is an explanatory diagram showing a map screen displayed on a user terminal. [Figure 6] FIG. 13 is an explanatory diagram showing a map screen displayed on a user terminal. [Figure 7] FIG. 13 is an explanatory diagram showing a map screen displayed on a user terminal. [Figure 8] FIG. 13 is an explanatory diagram showing a state when a display condition setting section on a map screen is operated; [Figure 9] FIG. 13 is an explanatory diagram showing a video timeline screen displayed on a user terminal. [Figure 10]FIG. 13 is an explanatory diagram showing a video timeline screen displayed on a user terminal. [Figure 11] FIG. 13 is an explanatory diagram showing a video timeline screen displayed on a user terminal. [Figure 12] FIG. 13 is an explanatory diagram showing a video timeline screen displayed on a user terminal. [Figure 13] FIG. 13 is an explanatory diagram showing a worker-specific graph screen and a daily graph screen displayed on a user terminal. [Figure 14] An explanatory diagram showing the transition status of the video timeline screen, the worker graph screen, and the day graph screen displayed on the user terminal. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] A first invention made to solve the above problems is a work analysis device that uses a processor to execute a process of outputting analytical information regarding a worker's work status based on video footage of the worker working, in which the processor acquires movement line information representing the work status of a target worker based on the video footage of the worker performing a series of tasks including movement between multiple work sections, compares the movement line information regarding the target worker with movement line information regarding an expert model, and determines whether or not there are areas for improvement in the work of the target worker based on the degree of deviation between the two, and generates display information including a movement line image that visualizes the areas for improvement as the analytical information.
[0012] According to this, a flow line image is displayed that visualizes improvement elements (issues to be improved) in the work of a target worker. This allows the user to easily grasp the overall status of the work, even if the work is complex and involves moving between multiple work sections. In this case, as a flow line image in which improvement elements are visualized, for example, a section including improvement elements in the flow line image may be drawn in a different form (e.g., color) from other sections.
[0013] In a second aspect of the present invention, the processor is configured to superimpose the movement line image relating to the target worker on a work area map including a plurality of work sections.
[0014] This allows the user to easily grasp the overall working status of the target worker in the workplace.
[0015] In a third aspect of the present invention, the processor is configured to superimpose, on the workspace map, the flow line image relating to the expert model, in addition to the flow line image relating to the target worker.
[0016] This allows the user to consider the working conditions of the target worker while comparing them with the working conditions of an expert.
[0017] In addition, in a fourth aspect of the present invention, the processor is configured to superimpose a traffic line image that visualizes the improvement factors that have occurred in the past on the work area map.
[0018] This allows the user to consider the working status of a target worker while comparing it with past working statuses that include improvement factors.
[0019] In a fifth aspect of the present invention, the processor determines the presence or absence of the improvement factor with respect to at least one of time and route.
[0020] This allows the user to easily check whether there are any improvement factors regarding time or route.
[0021] In addition, a sixth invention is configured such that the processor generates the display information in which an operation unit that instructs playback of the video relating to a period in which the improvement element is included generates the display information that is positioned in the vicinity of a section on the traffic line image related to the improvement element.
[0022] This allows the user to easily view the video relating to the period that includes the improvement element, and to specifically check the status of the improvement element.
[0023] A seventh invention is a work analysis method in which a processor executes a process to output analytical information on the work status of a worker based on video footage of the worker working, and the method is configured to obtain movement line information representing the work status of a target worker based on the video footage of a series of tasks performed by the worker including movement between a plurality of work sections, compare the movement line information on the target worker with movement line information on an expert model, and determine whether or not there are areas for improvement in the work of the target worker based on the degree of deviation between the two, and generate display information including a movement line image that visualizes the areas for improvement as the analytical information.
[0024] According to this, similarly to the first aspect of the invention, even if the work is complex and requires moving between a plurality of work sections, the user can easily grasp the overall status of the work.
[0025] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0026] FIG. 1 is a diagram showing the overall configuration of a work analysis system according to this embodiment.
[0027] This system analyzes the work status of workers in a factory or the like, and presents the analysis results to managers and workers. This system includes multiple cameras 1, a recorder 2, a server 3 (work analysis device), and a user terminal 4. The cameras 1, recorder 2, server 3, and user terminal 4 are connected via a network.
[0028] Camera 1 captures images of a worker performing work in a workplace. In the example shown in Fig. 1, the workplace includes a plurality of work sections (e.g., work sections A to C) corresponding to a plurality of processes, respectively, and the worker moves around the workplace to perform each process.
[0029] The recorder 2 records the video output from the camera 1.
[0030] The server 3 acquires video from the camera 1 or the recorder 2, analyzes the working conditions of the worker based on the video, and outputs the analysis results.
[0031] The user terminal 4 is used by users such as a work manager or a worker, and is configured with a PC, a tablet terminal, etc. The user terminal 4 displays the analysis results output from the server 3, and the user can view the analysis results.
[0032] The processing performed by the server 3 may be real-time processing performed simultaneously with shooting, or post-processing performed after shooting. In the case of real-time processing, the video captured by the camera 1 is transmitted to the server 3, and in the case of post-processing, the video stored in the recorder 2 is transmitted to the server 3.
[0033] Next, a description will be given of a schematic configuration of the server 3. FIG.
[0034] The server 3 includes a communication unit 31, a storage unit 32, and a processor 33.
[0035] The communication unit 31 communicates with the camera 1, the recorder 2, and the user terminal 4.
[0036] The storage unit 32 stores programs executed by the processor 33 and the like.
[0037] The processor 33 performs various processes by executing the programs stored in the storage unit 32. In this embodiment, the processor 33 performs a person tracking process, a flow line extraction process, a rank determination process, an improvement element determination process, a visualization process, a display information generation process, an expert model generation process, and the like.
[0038] In the person tracking process, the processor 33 tracks workers who move around the workplace and perform tasks based on the images from the cameras 1, and generates person tracking information. At this time, a person detection process is performed to detect people from the images from each camera 1, and a person re-identification process is performed to match people detected from the images from each camera 1 as the same person. The person tracking information includes position information of the person at each time.
[0039] In the flow line extraction process, processor 33 extracts a flow line representing the movement status of the worker within the workplace based on the person tracking information acquired in the person tracking process, and generates worker flow line information (position information at each time).
[0040] In the rank determination process, the processor 33 determines the rank (e.g., expert, senior, beginner) of the target worker based on the image of the camera 1. Specifically, the rank is determined based on the characteristics of the worker's appearance (wearing, such as a hat or uniform) captured in the image of the camera 1.
[0041] In the improvement element determination process, the processor 33 compares the movement line of the target worker with the movement line of the expert model, and determines whether there is an improvement element (problem to be improved) in the work of the target worker based on the degree of deviation between the two. The improvement element determination process includes a time trouble determination process and a route trouble determination process. The improvement element determination process is performed in sections corresponding to individual tasks.
[0042] In the time trouble determination process, the processor 33 determines whether or not there is a time trouble based on the degree of deviation between the task time of the target worker and the task time of the expert model. A time trouble is a state in which there is an improvement factor regarding the task time of the worker, specifically, a state in which the task is taking too long compared to the expert model. For example, a state in which the worker is taking more time than necessary because of unnecessary actions in each task is determined to be a time trouble.
[0043] In the route trouble determination process, the processor 33 determines whether or not there is a route trouble based on the degree of deviation between the movement line of the target worker and the movement line of the expert model. A route trouble is a state in which there is an improvement factor regarding the movement route of the worker, specifically, a state in which the movement line is significantly deviated from the movement line of the expert model. For example, when a state in which the worker is moving to an unnecessary place is detected based on the position information indicated by the movement line of the expert model and the position information indicated by the movement line of the target worker, it is determined that there is a route trouble.
[0044] In the improvement element determination process, a normal state, a time trouble occurrence state, a route trouble occurrence state, and a route time trouble occurrence state are detected based on the determination results of the time trouble determination process and the route trouble determination process, the sections in the worker's movement line where each state is detected are identified, and work state section information for the sections in each state in the worker's movement line is generated.
[0045] In the visualization process, the processor 33 generates information that visualizes the work status of the worker based on the work state section information acquired in the improvement element determination process.
[0046] Specifically, a flow line image (visualized image) showing the movement status of the worker is generated. At this time, the work status of the worker is visualized on the flow line. Specifically, in the worker's flow line, the normal state, the time trouble occurrence state, the route trouble occurrence state, and the section where the route time trouble occurrence state was detected are color-coded.
[0047] A timeline chart (visualized image) is generated that shows the work status of each worker on a time axis. A worker-specific graph (visualized image) showing the work time of each worker and a daily graph (visualized image) showing the work time of each target worker on each day are also generated.
[0048] In the display information generation process, the processor 33 generates display information related to screens to be displayed on the user terminal 4. Specifically, display information related to a map screen (see FIG. 4, etc.) including a traffic line image (visualized image) generated in the visualization process, a video timeline screen (see FIG. 9, etc.) including a timeline chart (visualized image) generated in the visualization process and an image of the camera 1, and a graph screen (see FIG. 13) including a graph (visualized image) generated in the visualization process is generated.
[0049] In the expert model generation process, when the target worker is determined to be an expert in the rank determination process, the processor 33 generates an expert model based on the movement line information of the expert worker. The expert model is an average of the work conditions of the expert worker, and each time the movement line of the expert worker is extracted, the expert model is updated based on the movement line information. The expert model may be generated for each work section. In order to avoid excessive updates, the update timing of the expert model may be arbitrarily set by the operation of a specified work manager.
[0050] Next, a description will be given of the procedure of the process performed by the server 3. FIG.
[0051] First, the processor 33 tracks a worker moving in the workplace (person tracking process) (ST101) based on the images (frames) of the multiple cameras 1. Next, the processor 33 extracts the movement line of the detected worker and generates movement line information (position information at each time) of the worker (movement line extraction process) (ST102).
[0052] Next, the processor 33 determines the rank (skilled worker, beginner) of the target worker (rank determination process) (ST103). Note that, for example, when workers are ranked into three levels, expert, senior, and beginner, the expert may be determined as the skilled worker.
[0053] If the rank of the target worker is an expert (ST103: "expert"), the current movement line information about the expert worker is added to the expert model information to update the expert model information (expert model generation process) (ST104). Next, the process returns to the person tracking process (ST101) and proceeds to the process for the next section.
[0054] On the other hand, if the rank of the target worker is beginner ("Beginner" in ST103), processor 33 then compares the movement line of the target worker with that of the expert model, and determines whether there is an improvement factor in the work of the target worker based on the degree of deviation between the two (difference in work time and movement route) (improvement factor determination process) (ST105). At this time, it is determined whether time trouble and route trouble have occurred.
[0055] Next, the processor 33 adds the result of the current improvement element determination process to the worker history information of the target worker to update the worker history information (ST106). Next, the process returns to the person tracking process (ST101) and proceeds to the process for the next section.
[0056] Next, a description will be given of the map screen 101 displayed on the user terminal 4. Fig. 4, Fig. 5, Fig. 6, and Fig. 7 are explanatory diagrams showing the map screen 101. Fig. 8 is an explanatory diagram showing a state when the display condition setting unit 102 on the map screen 101 is operated.
[0057] 4, the map screen 101 is provided with a display condition setting section 102. The display condition setting section 102 is provided with a work area designation section 111, a date and time designation section 112, a worker designation section 113, a rank designation section 114, and a setting content display section 115.
[0058] The work place designation unit 111 allows the user to designate a work place to be displayed. As shown in Fig. 8(A), when the user operates the work place designation unit 111, a selection menu 141 is displayed. A plurality of work places (e.g., work places #1 to #4) are displayed in the selection menu 141. The user can select one of the plurality of work places in the selection menu 141.
[0059] The date and time specification section 112 allows the user to specify the date and time to be displayed. As shown in Fig. 8(B), when the user operates the date and time specification section 112, a calendar 151, a time period input section 152, and a "GO" button 153 are displayed. The user can input the date (period) to be displayed in the calendar 151. The user can also input the time period to be displayed in the time period input section 152. When the user inputs the date and time to be displayed and operates the "GO" button 153, the date and time to be displayed is set based on the input contents.
[0060] The worker designation unit 113 allows the user to designate a worker to be displayed. As shown in Fig. 8(C), when the user operates the worker designation unit 113, a worker input unit 161 and a "GO" button 162 are displayed. The user can input the ID or name of the worker to be displayed in the worker input unit 161. When the user inputs the ID or name of the worker to be displayed and operates the "GO" button 162, the worker to be displayed is set based on the input contents.
[0061] The rank designation unit 114 allows the user to designate the rank of the worker to be displayed. As shown in Fig. 8(D), when the user operates the rank designation unit 114, a rank input unit 171 and a "GO" button 172 are displayed. The user can input the rank (expert, senior, beginner, etc.) of the worker to be displayed in the rank input unit 171. When the user inputs the rank of the worker to be displayed and operates the "GO" button 172, the rank of the worker to be displayed is set based on the input contents.
[0062] As shown in Fig. 4, the setting content display section 115 displays the setting content according to the user's designation operations in the work site designation section 111, the date and time designation section 112, the worker designation section 113, and the rank designation section 114. Specifically, the information on the work site, date and time, worker, and rank designated by the user is displayed. The setting content display section 115 is also provided with a "clear" button 116. When the user operates the "clear" button 116, the setting content is erased.
[0063] The map screen 101 is also provided with a map display section 103. A work site map 121 showing the layout of the work site is displayed on the map display section 103. A plurality of work sections (e.g., work sections A to C) included in the work site are depicted on the work site map 121. Flow line images 122 to 127 showing the movement routes of workers who move around the work site while performing work are superimposed on the work site map 121. The flow line images 122 to 127 are each drawn in a different style.
[0064] In this example, the entirety of the multiple work sections included in the target workplace is depicted on the workplace map 121, but a partial map depicting only a portion of the multiple work sections included in the workplace may also be displayed, and the displayed partial map may be switched in response to user operation.
[0065] The movement line images 122 to 127 include movement line image 122 of an expert model, movement line image 123 of the subject's past trouble occurrence state, movement line image 124 of the subject's current normal state, movement line image 125 of the subject's current time trouble occurrence state, movement line image 126 of the subject's current route trouble occurrence state, and movement line image 127 of the subject's current route time trouble occurrence state.
[0066] The expert model flow line image 122 is an image showing the average flow line of a plurality of experts, that is, an image showing the flow line obtained by averaging the flow lines previously extracted for expert workers.
[0067] The flow line image 123 of the target worker in the past trouble occurrence state is an image showing the flow line when a trouble (time trouble, route trouble) occurred in the target worker's past work. Note that the flow line image 123 may be an image showing a typical example of the flow line when a trouble occurred in the past without limiting the worker.
[0068] The target person's current normal state flow line image 124 is an image showing the flow line of the target worker in the normal state of the target worker's current work, i.e., in a state where no trouble has occurred. The target person's current time trouble occurrence state flow line image 125 is an image showing the flow line when a time trouble has occurred in the target worker's current work. The target person's current route trouble occurrence state flow line image 126 is an image showing the flow line when a route trouble has occurred in the target worker's current work. The target person's current route time trouble occurrence state flow line image 127 is an image showing the flow line when both a time trouble and a route trouble have occurred in the target worker's current work.
[0069] Further, the map screen 101 is provided with a display flow line setting unit 104. The display flow line setting unit 104 is provided with a check box 131 for each of the flow line images 122 to 127. The user can select whether or not to display each of the flow line images 122 to 127 by operating the check box 131. Therefore, in a case where a plurality of flow lines are displayed overlapping each other and the user's visibility is impaired, the user can check the user's work status by narrowing down the types of flow lines of interest, as described below.
[0070] The display flow line setting unit 104 is also provided with a display unit 132 for indicating whether or not a comparison with an expert model is to be made. The display unit 132 indicates whether or not a flow line image 122 of the expert model is to be displayed on the map display unit 103 in order to compare with the flow line of a target worker.
[0071] 4, the display flow line setting unit 104 is set to display all of the flow line images 122 to 127. In this case, the user can examine the work situation of a specific worker, for example, a beginner, while comparing it with the expert model.
[0072] 5, the display flow line setting unit 104 is set to display a flow line image 122 of the expert model and a flow line image 127 of the target worker in a state where a route time trouble has occurred this time. In this case, the user can compare the target worker with the expert model, focusing only on the state where the route time trouble has occurred this time.
[0073] In the example shown in Fig. 6, the display flow line setting unit 104 is set to display a flow line image 123 of the target worker in a state where a problem has occurred in the past, and flow line images 125-127 of the target worker in a state where a problem has occurred among current flow line images 124-127 of the target worker. In this case, the user can compare the situation when the current trouble has occurred with the situation when the trouble has occurred in the past for the target worker. This allows the user to determine, for example, whether the trouble that has occurred this time is unique or has occurred before.
[0074] 7, the display flow line setting unit 104 is set to display current flow line images 124 to 127 of a target worker (beginner). In this case, the user can examine the work status of a specific worker who is, for example, a beginner.
[0075] When it is set so that only a part of the current flow line images 124 to 127 of the target worker is displayed, the flow line images 124 to 127 are displayed in an interrupted state.
[0076] Furthermore, on the map screen 101, a video play button 128 is displayed on the work site map 121. The video play button 128 is displayed near the section in which the trouble occurred on the flow line images 123, 125 to 127. The video play button 128 is displayed in a form (e.g., color or pattern) similar to the flow line images 123, 125 to 127 including the section in which the trouble occurred. This allows the user to easily understand which of the flow line images 123, 125 to 127 the video play button 128 relates to.
[0077] When the user operates the video playback button 128, the screen transitions to a video timeline screen 201 (see FIG. 9, etc.).
[0078] Next, a description will be given of the video timeline screen 201 displayed on the user terminal 4. Figures 9, 10, 11, and 12 are explanatory diagrams showing the video timeline screen 201.
[0079] The video timeline screen 201 is provided with a video display section 202. The video display section 202 displays a video 203 captured by the camera 1. The video display section 202 also has a playback operation section 204. The playback operation section 204 allows the user to perform operations related to the playback of the video 203. This allows the user to check the actual work status in detail.
[0080] Here, the playback period of the video 203 differs depending on the detected event (time trouble or route trouble). That is, in the case of a time trouble, a threshold set based on the required time for each section in the movement line of the expert model is compared with the elapsed time of the target worker, and the point when the elapsed time of the target worker exceeds the threshold is set as a reference time, and a range of a predetermined time (for example, 30 seconds, 1 minute) around the reference time is set as the playback period. On the other hand, in the case of a route trouble, a point when the movement line of the target worker is separated from the movement line of the expert model by a predetermined distance or more is set as a reference time, and a range of a predetermined time around the reference time is set as the playback period. Also, in the case of a route time trouble, when the playback period related to the time trouble and the playback period related to the route trouble overlap, the combined period of the two playback periods is set as the playback period. Specifically, the playback period is from the start time of the playback period related to the event (time trouble or route trouble) detected earlier to the end time of the playback period related to the event detected later.
[0081] Furthermore, the video timeline screen 201 is provided with a timeline display section 205. The timeline display section 205 displays a timeline chart 211 (visualized image) that expresses the work status of the worker on a time axis. The timeline display section 205 is also provided with tabs 212, 213 for "time" and "route."
[0082] 9, 10, and 11 show an example in which the user operates the "Time" tab 212. In this case, a time-based timeline chart 211 is displayed. That is, in the timeline chart 211, a bar 221 is drawn that indicates the period during which the worker stays in each work section (e.g., A to C).
[0083] 12 shows an example in which the user operates the "route" tab 213. In this case, a timeline chart 211 based on distance is displayed. That is, in the timeline chart 211, a bar 221 is drawn that indicates the state in which the worker is moving in each work section (e.g., A to C).
[0084] The example shown in Fig. 9 is a case where a transition has been made from the map screen 101 shown in Fig. 4 and Fig. 5. In this case, since the movement line of a specific worker and the movement line of the expert model have been selected on the map screen 101 shown in Fig. 4 and Fig. 5, on the video timeline screen 201, the two video display sections 202 display videos 203 relating to the specific worker (ID=15) and the expert model, respectively, and the timeline display section 205 displays a timeline chart 211 relating to the specific worker and the expert model, respectively. This allows the user to consider the working status of a specific worker, for example, a beginner, while comparing it with the expert model.
[0085] In addition, the video display unit 202 of the expert model displays a video 203 of an expert that was previously photographed. At this time, among the experts who are located close to the target worker, that is, the experts who are assumed to be performing the same work as the target worker, the latest video or one designated in advance by the work manager is selected, and the video 203 of the expert is played back.
[0086] The example shown in FIG. 10 is a case where a transition is made from the map screen 101 shown in FIG. 6. In this case, since the flow lines of the specific worker at the time of the current and past trouble occurrences are selected on the map screen 101 shown in FIG. 6, the video timeline screen 201 displays the current and past video 203 of the specific worker in the two video display sections 202, and displays the current and past timeline chart 211 of the specific worker in the timeline display section 205. This allows the user to compare in detail the work situation of a specific worker, for example a beginner, at the time of the past and present trouble occurrences, and to consider the progress of the worker. In addition, the user can check the health condition of the worker by comparing in detail the work situation of a specific worker, for example a senior, at the time of the past and present trouble occurrences.
[0087] The examples shown in Figures 11 and 12 are the case of transition from the map screen 101 shown in Figure 7. In this case, since the current flow line of a specific worker has been selected on the map screen 101 shown in Figure 7, the video timeline screen 201 displays the current video 203 of the specific worker in the video display section 202, and displays the current timeline chart 211 of the specific worker in the timeline display section 205.
[0088] 11 is an example of a timeline chart 211 based on time, in which a bar 221 is drawn to represent the period during which a worker stays in each work section (e.g., A to C). On the other hand, the example of FIG 12 is an example of a timeline chart 211 based on distance, in which a bar 221 is drawn to represent the state in which a worker moves through each work section. This allows the user to check in detail the work status of a particular worker, for example a beginner, and to consider the work status of the particular worker.
[0089] Note that the examples shown in Figures 9, 10, and 11 are for a timeline chart 211 based on time, but if the user operates the "Route" tab 213, a distance-based timeline chart 211 as shown in Figure 12 will be displayed with the same display conditions.
[0090] Next, a description will be given of the worker-specific graph screen 301 and the day-specific graph screen 401 displayed on the user terminal. FIG.
[0091] 13(A), a graph 302 showing the work time (travel time) of each worker and the work time of the expert model is displayed on the worker-specific graph screen 301. This allows the user to compare the work time of each worker and the work time of the expert model with each other.
[0092] As shown in FIG. 13(B), the daily graph screen 401 displays a graph 402 showing the daily work time and the work time of the expert model. This allows the user to compare the daily work time and the work time of the expert model with each other. In particular, the work time for each work section is expressed as a stacked graph. This allows the user to understand the work time for each work section.
[0093] Furthermore, the daily graph screen 401 is provided with a target period designation section 403. When the user operates the target period designation section 403, a pull-down menu relating to the target period (e.g., one week, one month, etc.) is displayed. The user can select the target period from the pull-down menu.
[0094] Next, a description will be given of transitions between the video timeline screen 201, the worker-specific graph screen 301, and the day graph screen 401 displayed on the user terminal 4. Fig. 14 is an explanatory diagram showing transitions between the video timeline screen 201, the worker-specific graph screen 301, and the day graph screen 401.
[0095] Meanwhile, the video timeline screen 201 (see FIG. 9, etc.) is provided with a video icon 501 and a worker-specific graph icon 502. When the user operates the worker-specific graph icon 502, the screen transitions to the worker-specific graph screen 301 (see FIG. 13(A)).
[0096] The worker-specific graph screen 301 (see FIG. 13(A)) is provided with a video icon 501 and a daily graph icon 503. When the user operates the daily graph icon 503, the screen transitions to the daily graph screen 401 (see FIG. 13(B)).
[0097] The daily graph screen 401 (see FIG. 13(B)) is provided with a video icon 501 and a worker-specific graph icon 502. When the user operates the video icon 501, the screen transitions to the video timeline screen 201 (see FIG. 9). When the user performs an operation to select a date, the screen transitions to the video timeline screen 201 (see FIG. 9) related to the selected date. Note that instead of the icons 501 to 503, the video timeline screen 201, worker-specific graph screen 301, and daily graph screen 401 may be switched by selecting a display tab corresponding to each screen.
[0098] As described above, the embodiments have been described as examples of the technology disclosed in this application. However, the technology in this disclosure is not limited to these, and can be applied to embodiments in which modifications, substitutions, additions, omissions, etc. are made. In addition, it is also possible to combine the components described in the above embodiments to create new embodiments. [Industrial Applicability]
[0099] The work analysis device and work analysis method of the present invention have the effect of allowing a user to easily grasp the overall status of a work task, even if the work is complex and involves moving between multiple work areas, and are useful as a work analysis device and work analysis method that output analytical information regarding a worker's work status based on video footage of the worker working. [Explanation of symbols]
[0100] 1: Camera 2: Recorder 3: Server (work analysis device) 4: User terminal 33: Processor 101: Map screen 102: Display condition setting section 103: Map display section 104: Display flow line setting section 121:Workplace Map 122: Image of movement of expert model 123: Image of the subject's movement during past trouble occurrences 124: Image of the subject's normal movement pattern 125: Image of the subject's movement during the current trouble occurrence 126: Image of the subject's route when trouble occurred 127: Image of the subject's route and time of trouble 128: Video playback button 201: Video timeline screen 202: Video display unit 203:Video 204: Playback operation section 205: Timeline display section 211: Timeline chart 301: Graph screen by worker 302: Graph 401: Daily graph screen 402:Graph
Claims
1. A work analysis device that executes a process of outputting analysis information regarding a work situation of a worker based on a video of the worker's work, the process comprising: The processor, acquiring movement line information representing a work status of a target worker based on the video of a series of work performed by the worker, including movement between a plurality of work sections; comparing the movement line information of the target worker with movement line information of an expert model, and determining whether or not there is an improvement factor in the work of the target worker based on the degree of deviation between the two; A work analysis device characterized in that display information including a flow line image that visualizes the improvement elements is generated as the analysis information.
2. The processor, The work analysis device according to claim 1 , wherein the movement line image relating to a target worker is superimposed on a work area map including a plurality of work sections.
3. The processor, 3. The work analysis device according to claim 2, wherein the flow line image relating to the expert model is superimposed on the work area map in addition to the flow line image relating to the target worker.
4. The processor, The work analysis device according to claim 2 , wherein a flow line image visualizing the improvement factors occurring in the past is superimposed on the work area map.
5. The processor, The work analysis device according to claim 1 , wherein the presence or absence of the improvement factors is determined with respect to at least one of a time and a route.
6. The processor, The work analysis device according to claim 1, characterized in that an operation unit that instructs playback of the video relating to the period in which the improvement element is included generates the display information arranged in the vicinity of a section on the traffic line image related to the improvement element.
7. A work analysis method for outputting analysis information on a work status of a worker based on a video of the worker's work, the method comprising: acquiring movement line information representing a work status of a target worker based on the video of a series of work performed by the worker, including movement between a plurality of work sections; comparing the movement line information of the target worker with movement line information of an expert model, and determining whether or not there is an improvement factor in the work of the target worker based on the degree of deviation between the two; A work analysis method, comprising: generating display information including a flow line image that visualizes the improvement elements as the analysis information.
Citation Information
Patent Citations
Operation analyzing device and operation analyzing method
WO2021131552A1
