Sewing efficiency detection method and system based on lathe worker action analysis, medium and terminal

Abstract

The invention provides a sewing efficiency detection method and system based on lathe worker action analysis, a medium and a terminal. The method comprises the following steps of obtaining a motor stop time point, a thread trimming time point and a motor start time point of a sewing machine; determining a whole action and a sewing action of a lathe worker based on the adjacent motor stop time point and the motor start time point, and obtaining action durations corresponding to the whole action and the sewing action; determining a taking action and a releasing action of a lathe worker based on the adjacent trimming time point and the motor starting time point, and obtaining action duration corresponding to the taking action and the releasing action; and calculating the sewing efficiency of the lathe worker based on the action duration corresponding to the whole action, the sewing action, the taking action and the releasing action. According to the sewing efficiency detection method and system based on lathe worker action analysis, the medium and the terminal, lathe worker action recognition is carried out based on the action data and the image data of the sewing machine, and then accurate sewing efficiency detection is achieved.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and relates to a sewing efficiency detection method, system, medium and terminal based on lathe worker action analysis. Background Art

[0002] In the prior art, Internet of Things sewing equipment has basically replaced ordinary sewing machines, and factories have changed from manual piecework by workers to automatic piecework methods such as using work ticket software, hanging systems, and piecework algorithms. Existing sewing piecework algorithms only rely on the action data of sewing equipment. When there are errors in the acquisition of action data, it will lead to incorrect statistics of the piecework quantity.

[0003] With the development of the Internet of Things system, Internet of Things sewing equipment can provide real-time sewing data of employees. At the same time, with the continuous progress of artificial intelligence technology, especially the increasing maturity of object detection and depth detection technologies, it provides new possibilities for the update of piecework algorithms in the clothing production field. Summary of the Invention

[0004] The purpose of this application is to provide a sewing efficiency detection method, system, medium and terminal based on lathe worker action analysis, which performs lathe worker action recognition based on the action data and image data of the sewing machine, and then realizes accurate sewing efficiency detection.

[0005] In a first aspect, this application provides a sewing efficiency detection method based on lathe worker action analysis, and the method includes the following steps: obtaining the motor stop time point, thread cutting time point and motor start time point of the sewing machine; determining the whole action and sewing action of the lathe worker based on adjacent motor stop time points and motor start time points, and obtaining the action durations corresponding to the whole action and the sewing action; determining the picking action and placing action of the lathe worker based on adjacent thread cutting time points and motor start time points, and obtaining the action durations corresponding to the picking action and the placing action; calculating the sewing efficiency of the lathe worker based on the action durations corresponding to the whole action, the sewing action, the picking action and the placing action.

[0006] In one implementation manner of the first aspect, obtaining the motor stop time point, thread cutting time point and motor start time point of the sewing machine includes the following steps: Obtaining the event data of the sewing machine; the event data includes the event generation time and the event type; Taking the event generation times corresponding to the event types of motor stop, thread cutting and motor start as the motor stop time point, the thread cutting time point and the motor start time point.

[0007] In an implementation of the first aspect, determining the whole action and sewing action of the lathe worker based on adjacent motor stop time points and motor start time points, and obtaining the action durations corresponding to the whole action and the sewing action includes the following steps: Obtain the time difference between adjacent motor stop time points and motor start time points, and use the adjacent motor stop time points and motor start time points as a time stamp array; Select the time stamp arrays with the time difference greater than the preset threshold as the first target time stamp arrays; When it is detected that there is cloth near the sewing needle of the sewing machine, obtain the image of the sewing machine within the time period corresponding to the first target time stamp array, and use the motor start time point of the first target time stamp array as the start time point of the sewing action; the duration between the motor start time point of the first target time stamp array and the next motor stop time point is the action duration of the sewing action; When all the lathe workers are at the workstations in the sewing machine image, the motor stop time point of the first target time stamp array is the start time point of the whole action; the duration between the motor stop time point of the first target time stamp array and the next motor start time point is the duration of the whole action.

[0008] In an implementation of the first aspect, determining the picking action and placing action of the lathe worker based on adjacent thread cutting time points and motor start time points, and obtaining the action durations corresponding to the picking action and the placing action includes the following steps: Obtain the time difference between adjacent motor thread cutting time points and motor start time points, and use the adjacent motor thread cutting time points and motor start time points as a time stamp array; Select the time stamp arrays with the time difference greater than the preset threshold as the second target time stamp arrays; When it is detected that there is no cloth near the sewing needle of the sewing machine, obtain the actual sewing action data of the sewing machine before the time period corresponding to the second target time stamp array; Judge whether the lathe worker has completed sewing a finished product based on the actual sewing action data; When it is determined that the lathe worker has completed sewing a finished product, use the thread cutting time point corresponding to the second target time stamp array as the start time point of the placing action, and use the average value of the thread cutting time point corresponding to the second target time stamp array and the motor start time point as the start time point of the picking action; the duration between the start time point of the placing action and the start time point of the picking action is the action duration of the placing action, and the duration between the start time point of the picking action and the motor start time point corresponding to the second target time stamp array is the action duration of the picking action.

[0009] In an implementation of the first aspect, it further includes detecting whether there is fabric near the sewing needle of the sewing machine; Detecting whether there is fabric near the sewing needle of the sewing machine includes the following steps: Obtain multiple images of the sewing needle area within a target time period; Calculate the difference in pixel values between each image of the sewing needle area and a reference image of the sewing needle, where there is fabric near the sewing needle in the reference image of the sewing needle; When the proportion of pixel points in the image of the sewing needle area whose difference is greater than a preset difference is greater than a first preset proportion, it is determined that there is fabric in the image of the sewing needle area; Among the multiple images of the sewing needle area, when the proportion of images of the sewing needle area where it is determined that there is fabric is greater than a second preset proportion, it is determined that there is fabric near the sewing needle of the sewing machine; otherwise, it is determined that there is no fabric near the sewing needle of the sewing machine.

[0010] In an implementation of the first aspect, calculating the sewing efficiency of a sewing worker based on the action durations corresponding to the alignment action, the sewing action, the picking action, and the placing action includes the following steps: Obtain the reference durations corresponding to the alignment action, the sewing action, the picking action, and the placing action; Calculate the sewing efficiency of the sewing worker based on the action duration and the reference duration, where the sewing efficiency of the sewing worker includes the total sewing efficiency and the efficiency of a single sewing action.

[0011] In a second aspect, the present application provides a sewing efficiency detection system based on the analysis of the actions of a sewing worker. The system includes an acquisition module, a first processing module, a second processing module, and a detection module; The acquisition module is used to obtain the motor stop time point, the thread cutting time point, and the motor start time point of the sewing machine; The first processing module is used to determine the alignment action and the sewing action of the sewing worker based on adjacent motor stop time points and motor start time points, and obtain the action durations corresponding to the alignment action and the sewing action; The second processing module is used to determine the picking action and the placing action of the sewing worker based on adjacent thread cutting time points and motor start time points, and obtain the action durations corresponding to the picking action and the placing action; The detection module is used to calculate the sewing efficiency of the sewing worker based on the action durations corresponding to the alignment action, the sewing action, the picking action, and the placing action.

[0012] In a third aspect, the present application provides a terminal, which includes: a processor and a memory; The memory is used to store a computer program; The processor is used to execute the computer program stored in the memory, so that the terminal executes the above sewing efficiency detection method based on the lathe worker's action analysis.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a terminal, the above sewing efficiency detection method based on the lathe worker's action analysis is implemented.

[0014] In a fifth aspect, the present application provides a sewing efficiency detection system based on the lathe worker's action analysis, including the above terminal and a sewing machine; The sewing machine includes an information acquisition module; The information acquisition module is used to collect the motor stop time point, the thread cutting time point and the motor start time point of the sewing machine, and provide them to the terminal As described above, the sewing efficiency detection method, system, medium and terminal of the present application based on the lathe worker's action analysis have the following beneficial effects.

[0015] (1) Based on the action data and image data of the sewing machine, the lathe worker's action is recognized, and then accurate sewing efficiency detection is realized.

[0016] (2) It avoids the misdetection of sewing efficiency caused by simply relying on the action data of sewing equipment, and effectively improves the accuracy of sewing efficiency detection. Description of the Drawings

[0017] Figure 1 It shows a flowchart of the sewing efficiency detection method based on the lathe worker's action analysis of the present application in an embodiment.

[0018] Figure 2 It shows a schematic diagram of the event data of the present application in an embodiment.

[0019] Figure 3 It shows a schematic diagram of the motor stop time point, the motor thread cutting time point and the motor start time point of the present application in an embodiment.

[0020] Figure 4 It shows a detection schematic diagram of the presence of cloth near the sewing needle of the sewing machine of the present application in an embodiment.

[0021] Figure 5 It shows a sectional view of the reference sewing action data of the present application in an embodiment.

[0022] Figure 6 It shows a sectional view of the number of sewing stitches during thread cutting of the present application in an embodiment.

[0023] Figure 7It shows a segmented feature schematic diagram of the reference sewing motion data in an embodiment of the present application.

[0024] Figure 8 It shows a segmented matching schematic diagram of the reference sewing motion data and the actual sewing motion data in an embodiment of the present application.

[0025] Figure 9 It shows a structural schematic diagram of the sewing efficiency detection system based on the analysis of the actions of the sewing workers in an embodiment of the present application.

[0026] Figure 10 It shows a structural schematic diagram of the terminal in an embodiment of the present application.

[0027] Figure 11 It shows a structural schematic diagram of the sewing efficiency detection system based on the analysis of the actions of the sewing workers in another embodiment of the present application. Detailed implementation manners

[0028] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0029] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0030] In addition, in the present application, descriptions such as "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those skilled in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present application.

[0031] As Figure 1 shown, in an embodiment, the sewing efficiency detection method based on the analysis of the actions of the sewing workers of the present application includes steps S1 - S4.

[0032] Step S1: Obtain the motor stop time point, thread cutting time point, and motor start time point of the sewing machine.

[0033] Specifically, an information acquisition module is provided in the sewing machine of the present application. The information acquisition module is used to acquire the event data of the sewing machine. As Figure 2 shown, the event data includes the event occurrence time, event type, and event parameters. In an embodiment, the event type can be represented by digital numbers such as 0, 1, 2, etc. For example, 2 represents motor start, 3 represents motor stop, and 6 and 7 respectively represent the thread cutting and post-thread cutting actions of the sewing machine. The event parameters represent the parameter information involved in the corresponding event type. For example, for an event with an event type of motor stop, its event parameter is the number of stitches sewn this time. Therefore, obtain the event data of the sewing machine, and use the event generation times corresponding to the event types of motor stop, thread cutting, and motor start as the motor stop time point, the thread cutting time point, and the motor start time point. As Figure 3 shown, according to event types 3, 6, and 2, the corresponding motor stop time point, thread cutting time point, and motor start time point can be obtained.

[0034] Step S2: Determine the whole action and sewing action of the operator based on adjacent motor stop time points and motor start time points, and obtain the action durations corresponding to the whole action and the sewing action.

[0035] Specifically, in an embodiment, determining the whole action and sewing action of the operator based on adjacent motor stop time points and motor start time points, and obtaining the action durations corresponding to the whole action and the sewing action includes the following steps.

[0036] 21) Obtain the time difference between adjacent motor stop time points and motor start time points, and use the adjacent motor stop time points and motor start time points as a time stamp array.

[0037] Specifically, in the present application, the sewing operation of the operator is divided into four actions: picking up the fabric, sewing the fabric, arranging the fabric, and putting down the fabric. Among them, picking up the fabric is the starting process of the sewing operation, indicating going to pick up the fabric to be sewn. Sewing the fabric is the intermediate process of the sewing operation, indicating sewing the fabric. Arranging the fabric is the intermediate process of the sewing operation, indicating arranging the fabric. Putting down the fabric is the ending process of the sewing operation, indicating placing the sewn fabric. Therefore, for a piece of fabric, its sewing operation is in sequence: picking up the fabric, sewing the fabric, arranging the fabric, sewing the fabric... (the number of times of arranging the fabric and sewing the fabric depends on different sewing requirements), putting down the fabric.

[0038] As can be seen from the above, during the sewing process of the sewing machine operator, the actions of aligning the fabric and sewing the fabric are in one-to-one correspondence. Among them, the actions of aligning the fabric all occur at the motor stop time point. At the next motor start time point, the action of sewing the fabric is executed. Therefore, by calculating the time difference between adjacent motor stop time points and motor start time points, within this time difference, the sewing machine operator may align the fabric. At the same time, take the adjacent motor stop time point and motor start time point as a timestamp array. For example, the timestamp array is represented as [motor stop time point, next motor start time point].

[0039] 22) Select the timestamp arrays with the time difference greater than the preset threshold as the first target timestamp arrays.

[0040] Among them, the sewing machine operator may perform the action of aligning the fabric at the motor stop time point, but it is also necessary to consider the time length requirement for aligning the fabric at the same time. If the time length is too short, it may only be a pause in the sewing action and no fabric alignment action is performed. In special cases, sometimes the sewing action time is very short, such as just adjusting the position or direction of the fabric, etc. Therefore, based on the above special cases, it is necessary to set a time threshold for the fabric alignment action. Only when the time difference is greater than the preset threshold, such as 3s, the timestamp array is used as the first target timestamp array.

[0041] 23) When it is detected that there is fabric near the sewing needle of the sewing machine, obtain the sewing machine images within the time period corresponding to the first target timestamp array, and take the motor start time point of the first target timestamp array as the start time point of the sewing action; the time duration between the motor start time point of the first target timestamp array and the next motor stop time point is the action duration of the sewing action.

[0042] Among them, when analyzing the sewing and aligning actions of the sewing machine operator, it is first necessary to detect whether there is fabric near the sewing needle of the sewing machine. Only when there is fabric near the sewing needle, the sewing and aligning actions of the sewing machine operator are identified and analyzed.

[0043] In one embodiment, detecting whether there is fabric near the sewing needle of the sewing machine includes the following steps.

[0044] a) Obtain the target time period, that is, multiple images of the needle area within the time period corresponding to the first target timestamp array.

[0045] Among them, an image acquisition module, such as a camera, is provided on the sewing machine. Based on the camera, multiple images of the needle area within the time period corresponding to the target timestamp array are acquired.

[0046] b) Calculate the difference in pixel values between each image of the needle area and the needle reference image, and there is fabric near the sewing needle in the needle reference image.

[0047] Among them, a reference image of the sewing needle is collected in advance, that is, an image in which there is fabric near the sewing needle. The sewing needle area image and the sewing needle reference image are collected by the camera at the same position. Calculate the difference between the pixel values of the corresponding pixel points of the sewing needle area image and the sewing needle reference image.

[0048] c) When the proportion of pixel points in the sewing needle area image whose difference is greater than the preset difference is greater than the first preset proportion, it is determined that there is fabric in the sewing needle area image.

[0049] Among them, count the proportion of pixel points in the sewing needle area image whose difference is greater than the preset difference. Only when the proportion is greater than the first preset proportion, it is judged that there is fabric in the sewing needle area image.

[0050] d) Among the multiple sewing needle area images, when the proportion of the sewing needle area images in which fabric is determined to exist exceeds the second preset proportion, it is determined that there is fabric near the sewing needle of the sewing machine.

[0051] It should be noted that the values of the preset difference, the first preset proportion, and the second preset proportion can be obtained and updated through multiple learning.

[0052] Among them, for multiple sewing needle area images, count the proportion of the sewing needle area images in which there is fabric. Only when the proportion exceeds the second preset proportion, it is determined that there is fabric near the sewing needle of the sewing machine. As Figure 4 shown, the left side is the sewing needle reference image, and the right side has the sewing needle area image. Through the above analysis, it can be determined that there is fabric near the sewing needle in the right image. When it is detected that there is fabric near the sewing needle of the sewing machine, the motor start time point of the first target timestamp array is taken as the start time point of the sewing action. The duration between the motor start time point and the next motor stop time point of the first target timestamp array is the action duration of the sewing action.

[0053] When it is detected that there is fabric near the sewing needle of the sewing machine, then based on the camera, obtain the sewing machine image within the time period corresponding to the first target timestamp array. The sewing machine image is an image of the sewing machine and its surrounding area.

[0054] 24) When all the sewing workers are at their workstations in the sewing machine image, the motor stop time point of the first target timestamp array is taken as the start time point of the finishing action; the duration between the motor stop time point and the next motor start time point of the first target timestamp array is the duration of the finishing action.

[0055] Among them, when analyzing the overall sewing action of the sewing machine worker, it is also necessary to judge whether the worker is at the workstation, that is, to detect whether the worker is at the workstation in the sewing machine image.

[0056] In one embodiment, detecting whether the sewing worker is at the working station in the sewing machine image includes the following steps.

[0057] a) Perform object detection on the sewing machine image based on an object detection model to detect whether a human face or a human hand is included in the sewing machine image.

[0058] Among them, an object detection model, such as the YOLO model, is used to perform object detection on the sewing machine image to detect whether a human face or a human hand is included therein.

[0059] b) When the human face or the human hand is detected in each sewing machine image, it is determined that the sewing workers in the sewing machine image are all at the working station.

[0060] When the human face or the human hand is detected in each sewing machine image, it is judged that the sewing worker has been at the working station all the time. When there is a situation where the human face or the human hand cannot be detected in each sewing machine image, an abnormality is judged, such as scenarios where the sewing worker leaves the working station to drink water, get fabric, etc. For abnormal situations, they can be marked for subsequent sorting and analysis.

[0061] Therefore, when there is fabric near the sewing needle of the sewing machine and the sewing workers in the sewing machine image are all at the working station, the motor stop time point of the target timestamp array can be determined as the start time point of the whole action. The duration between the motor stop time point and the next motor start time point of the first target timestamp array is the duration of the whole action.

[0062] Step S3: Determine the picking action and the placing action of the sewing worker based on adjacent thread cutting time points and motor start time points, and obtain the action durations corresponding to the picking action and the placing action.

[0063] Specifically, in one embodiment, determining the picking action and the placing action of the sewing worker based on adjacent thread cutting time points and motor start time points, and obtaining the action durations corresponding to the picking action and the placing action include the following steps.

[0064] 31) Obtain the time difference between adjacent motor thread cutting time points and motor start time points, and use the adjacent motor thread cutting time points and motor start time points as a timestamp array.

[0065] 32) Select the timestamp arrays with the time difference greater than a preset threshold as the second target timestamp arrays.

[0066] Among them, during the sewing process of a sewing machine operator, the actions of picking up and placing the fabric are in one-to-one correspondence. Among them, the time points of the fabric-picking and fabric-placing actions occur between the thread-cutting time point and the motor-starting time point. Therefore, calculate the time difference between adjacent thread-cutting time points and motor-starting time points. During this time difference, the sewing machine operator may pick up and place the fabric. At the same time, use the adjacent thread-cutting time point and motor-starting time point as a time stamp array. For example, the time stamp array is expressed as [thread-cutting time point, next motor-starting time point].

[0067] It is possible for the sewing machine operator to pick up and place the fabric between the thread-cutting time point and the motor-starting time point, but the time length requirements of the above actions also need to be considered simultaneously. If the time length is too short, it may only be a pause in the fabric-sewing action, and the actions of picking up and placing the fabric are not carried out. Therefore, based on the above special situation, it is necessary to set the action time threshold for picking up and placing the fabric. Only when the time difference is greater than a preset threshold, such as 3s, can the actions of picking up and placing the fabric be further analyzed. It should be noted that the preset threshold can be obtained and updated through multiple learning processes.

[0068] 33) When it is detected that there is no fabric near the sewing needle of the sewing machine, obtain the actual sewing action data of the sewing machine before the period corresponding to the second target time stamp array.

[0069] Among them, when analyzing the picking and placing actions of the sewing machine operator, it is first necessary to detect whether there is fabric near the sewing needle of the sewing machine. Only when there is no fabric near the sewing needle, can the picking and placing actions of the sewing machine operator be identified and analyzed. In this application, to detect whether there is fabric near the sewing needle of the sewing machine, the foregoing method can be used, and only the target period needs to be set as the period corresponding to the second target time stamp data.

[0070] When it is detected that there is no fabric near the sewing needle of the sewing machine, then obtain the actual sewing action data of the sewing machine before the period corresponding to the second target time stamp array. Among them, the actual sewing action data can be one or a combination of multiple of the number of sewing stitches between adjacent thread-cuttings, the number of times of lifting and pressing the presser foot, and the number of times of starting and stopping the motor.

[0071] 34) Based on the actual sewing action data, determine whether the operator has completed sewing a finished product.

[0072] Among them, determining whether the operator has completed sewing a finished product based on the actual sewing action data includes the following steps.

[0073] a) Obtain the reference sewing action data required for a finished product.

[0074] Taking the number of sewing stitches between adjacent cut lines as an example, the reference sewing action data is obtained. The reference sewing action data can be obtained by manual entry. In this application, the reference sewing action data is constructed according to the number of sewing times required between each cut during the sewing process of a finished product.

[0075] b) Determine whether the actual sewing action data between a certain time point and the cut line time points corresponding to the target time stamp array is consistent with the reference sewing action data.

[0076] Among them, the sewing actions of a finished product are segmented according to different sewing states. For each segment of sewing action data, the segmented action features corresponding to the reference sewing action data and the actual sewing action data are extracted. Determine whether the segmented action features of the reference sewing action data and the segmented action features of the actual sewing action data match one by one; when they match one by one, it is determined that the actual sewing action data and the reference sewing action data are consistent.

[0077] As Figure 5 shown, according to the time difference between the motor stop time point and the motor start time point, the time difference between the cut line time point and the motor start time point, and whether there is fabric near the sewing needle, the sewing data is divided into two segments of data. In the first segment of data, if the time difference is small and there is fabric near the sewing needle, it is the action of sewing the fabric; if the time difference is large and there is fabric near the sewing needle, it may be the action of straightening the fabric or an abnormal action. In the second segment of data, if the time difference is small and there is no fabric near the sewing needle, it is determined as the action of sewing the fabric. When the time difference is large and there is no fabric near the sewing needle, it is determined as the action of placing the fabric. Therefore, it is necessary to segment the sewing action data of a finished product for different sewing actions.

[0078] As Figure 6 shown, the number of cut lines and the number of sewing stitches between cut lines during the sewing process are collected. As Figure 7 shown, the number of sewing times between cut lines is classified, and category characters are used to replace the original number of stitches. Preferably, different stitch number intervals correspond to different categories. For example, 21 stitches and 16 stitches are close to category 0, 91 stitches and 83 stitches are close to category 1, and the remaining two segments of data are classified in the same way. Figure 5The sewing data can be divided into three segments. In the first segment, there are 2 thread - cutting operations with categories 0 and 1. In the second segment, there is 1 thread - cutting operation with category 0. In the third segment, there is 1 thread - cutting operation with category 1. It should be noted that only the sewing needle counts are used for classification here, so classification can be achieved by simply judging the numerical values. For classification that selects more features, classification methods such as clustering or SVM and other machine - learning algorithms can be used. Therefore, classifying the number of sewing operations between thread - cuttings corresponding to each segment of data is used as the segmented action feature of the reference sewing action data and the segmented action feature of the actual sewing action data. Compare each segmented action feature of the reference sewing action data and the actual sewing action data one by one. When they are all the same, it is determined that the actual sewing action data is consistent with the reference sewing action data. As Figure 8 shown, each time a segment of actual sewing action data is taken to match the reference sewing action data to check whether there are features in the same order as the reference sewing action data. For Figure 6 the embodiment, it is to judge whether 0101 appears. The first time, taking the first - segment data does not meet the requirement. The second time, taking the first and second - segment data also does not meet the requirement. The third time, taking the first to third - segment data meets the requirement. At this time, it is determined that the lathe worker has completed one piece. The next time when taking actual sewing action data, it starts from the fourth - segment data and repeats the above operation.

[0079] c) If so, it is determined that the lathe worker has completed sewing one finished product.

[0080] Among them, when it is determined that the actual sewing action data is consistent with the reference sewing action data, it is determined that the lathe worker has completed sewing one finished product.

[0081] 35) When it is determined that the lathe worker has completed sewing one finished product, take the thread - cutting time point corresponding to the second - target time - stamp array as the start time point of the placing action, and take the average value of the thread - cutting time point corresponding to the second - target time - stamp array and the motor - start time point as the start time point of the taking action; take the duration between the start time point of the placing action and the start time point of the taking action as the action duration of the placing action, and take the duration between the start time point of the taking action and the motor - start time point corresponding to the second - target time - stamp array as the action duration of the taking action.

[0082] Step S4: Calculate the sewing efficiency of the lathe worker based on the action durations corresponding to the whole action, the sewing action, the taking action, and the placing action.

[0083] Specifically, after obtaining the action durations corresponding to the whole action, the sewing action, the picking action, and the placing action, the sewing efficiency of the lathe operator can be calculated. The sewing efficiency of the lathe operator includes the total sewing efficiency and the single-action sewing efficiency. For each piece of fabric, the benchmark durations of its corresponding sewing actions are preset. Among them, the sum of the benchmark durations of each sewing action corresponding to a piece of fabric is calculated to obtain the total benchmark duration; the sum of the action durations of each sewing action of the lathe operator for this piece of fabric is calculated to obtain the total action duration; the ratio of the total action duration to the total benchmark duration is calculated as the total sewing efficiency. The ratio of the action duration of a single sewing action of a piece of fabric to the benchmark duration is calculated as the single-action sewing efficiency. By calculating the sewing efficiency of the lathe operator, the efficiency parameters of the lathe operator during the sewing process can be accurately obtained, providing data support for subsequent improvement of sewing efficiency.

[0084] The protection scope of the sewing efficiency detection method based on lathe operator action analysis described in the embodiments of this application is not limited to the execution order of the steps listed in this embodiment. Any scheme achieved by adding or reducing steps of the prior art and replacing steps according to the principles of this application is included in the protection scope of this application.

[0085] The embodiments of this application also provide a sewing efficiency detection system based on lathe operator action analysis. The sewing efficiency detection system based on lathe operator action analysis can implement the sewing efficiency detection method described in this application. However, the implementation devices of the sewing efficiency detection system based on lathe operator action analysis described in this application include but are not limited to the structures of the sewing efficiency detection system based on lathe operator action analysis listed in this embodiment. Any structural deformation and replacement of the prior art made according to the principles of this application are included in the protection scope of this application.

[0086] As Figure 9 shown, in one embodiment, the sewing efficiency detection system based on lathe operator action analysis of this application includes an acquisition module 91, a first processing module 92, a second processing module 93, and a detection module 94.

[0087] The acquisition module 91 is used to acquire the motor stop time point, the thread cutting time point, and the motor start time point of the sewing machine.

[0088] The first processing module 92 is connected to the acquisition module 91 and is used to determine the whole action and the sewing action of the lathe operator based on adjacent motor stop time points and motor start time points, and acquire the action durations corresponding to the whole action and the sewing action.

[0089] The second processing module 93 is connected to the acquisition module 91 and is used to determine the picking action and the placing action of the lathe operator based on adjacent thread cutting time points and motor start time points, and acquire the action durations corresponding to the picking action and the placing action.

[0090] The detection module 94 is connected to the first processing module 92 and the second processing module 93, and is configured to calculate the sewing efficiency of the lathe worker based on the action durations corresponding to the whole action, the sewing action, the picking action, and the placing action.

[0091] Among them, the structures and principles of the acquisition module 91, the first processing module 92, the second processing module 93, and the detection module 94 correspond one by one to the steps in the above sewing efficiency detection method based on the analysis of the lathe worker's actions, so they will not be elaborated here.

[0092] In several embodiments provided in the present application, it should be understood that the disclosed system, device, or method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules / units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of devices or modules or units can be in electrical, mechanical, or other forms.

[0093] The modules / units described as separate components may or may not be physically separated. The components displayed as modules / units may or may not be physical modules, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, in each embodiment of the present application, the various functional modules / units can be integrated in a processing module, or each module / unit can exist physically alone, or two or more modules / units can be integrated in one module / unit.

[0094] Those of ordinary skill in the art should also be able to further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0095] The embodiments of the present application also provide a computer-readable storage medium. Those of ordinary skill in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing a processor through a program. The program can be stored in a computer-readable storage medium. The storage medium is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that integrates one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid-state disk (SSD)), etc.

[0096] The embodiments of the present application also provide a terminal. The terminal includes a processor and a memory.

[0097] The memory is used to store a computer program.

[0098] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disc.

[0099] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the terminal executes the above sewing efficiency detection method based on lathe worker motion analysis.

[0100] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0101] Such as Figure 10As shown, the terminal of the present application is presented in the form of a general-purpose computing device. The components of the terminal may include, but are not limited to: one or more processors or processing units 101, a memory 102, and a bus 103 that connects different system components (including the memory 102 and the processing unit 101).

[0102] The bus 103 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0103] The terminal typically includes a variety of computer system-readable media. These media can be any available media that can be accessed by the terminal, including volatile and non-volatile media, removable and non-removable media.

[0104] The memory 102 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 1021 and / or cache memory 1022. The terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 1023 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 10 not shown, commonly referred to as a "hard disk drive"). Although Figure 10 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 103 through one or more data media interfaces. The memory 102 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present application.

[0105] A program / utility 1024 having a set (at least one) of program modules 10241 may be stored, for example, in the memory 102. Such program modules 10241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 10241 generally execute the functions and / or methods in the embodiments described in the present application.

[0106] The terminal can also communicate with one or more external devices (such as a keyboard, a pointing device, a display, etc.), and can also communicate with one or more devices that enable a user to interact with the terminal, and / or communicate with any device that enables the terminal to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 104. Moreover, the terminal can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 105. As Figure 10 shown, the network adapter 105 communicates with other modules of the terminal through the bus 103. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the terminal, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0107] As Figure 11 shown, in one embodiment, the sewing efficiency detection system based on lathe worker motion analysis of the present application includes the above-mentioned terminal 111 and sewing machine 112.

[0108] The sewing machine 112 includes an information collection module.

[0109] The information collection module is used to collect the motor stop time point, the thread cutting time point, and the motor start time point of the sewing machine 112, and provide them to the terminal 111.

[0110] It should be noted that the terminal 111 can be set on the sewing machine 112 for local processing; or it can be set in the cloud for cloud processing. When the terminal 111 is set in the cloud, one terminal can simultaneously detect the sewing efficiency of lathe workers for multiple sewing machines.

[0111] The above embodiments are only illustrative of the principles and effects of the present application, and are not used to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present application should still be covered by the claims of the present application.

Claims

1. A sewing efficiency detection method based on lathe operator motion analysis, characterized in that The method includes the following steps: Obtain the motor stop time point, thread cutting time point, and motor start time point of the sewing machine; Based on the adjacent motor stop time point and motor start time point, determine the whole action and sewing action of the sewing worker, and obtain the action duration corresponding to the whole action and the sewing action; Based on the adjacent thread cutting time point and motor start time point, determine the picking action and placing action of the sewing worker, and obtain the action duration corresponding to the picking action and the placing action; Calculate the sewing efficiency of the sewing worker based on the action durations corresponding to the whole action, the sewing action, the picking action, and the placing action.

2. The sewing efficiency detection method based on lathe worker motion analysis according to claim 1, characterized in that Obtaining the motor stop time point, thread cutting time point, and motor start time point of the sewing machine includes the following steps: Obtain the event data of the sewing machine; the event data includes the event generation time and the event type; Use the event generation times corresponding to the motor stop, thread cutting, and motor start event types as the motor stop time point, the thread cutting time point, and the motor start time point.

3. The sewing efficiency detection method based on lathe worker motion analysis according to claim 1, characterized in that, Based on the adjacent motor stop time point and motor start time point, determining the whole action and sewing action of the sewing worker, and obtaining the action duration corresponding to the whole action and the sewing action includes the following steps: Obtain the time difference between the adjacent motor stop time point and motor start time point, and use the adjacent motor stop time point and motor start time point as a time stamp array; Select the time stamp array with the time difference greater than the preset threshold as the first target time stamp array; When it is detected that there is cloth near the sewing needle of the sewing machine, obtain the sewing machine image within the time period corresponding to the first target time stamp array, and use the motor start time point of the first target time stamp array as the start time point of the sewing action; the duration between the motor start time point of the first target time stamp array and the next motor stop time point is the action duration of the sewing action; When all sewing workers are at their workstations in the sewing machine image, the motor stop time point of the first target time stamp array is the start time point of the whole action; the duration between the motor stop time point of the first target time stamp array and the next motor start time point is the duration of the whole action.

4. The sewing efficiency detection method based on lathe worker motion analysis according to claim 1, wherein, Based on the adjacent thread cutting time point and motor start time point, determining the picking action and placing action of the sewing worker, and obtaining the action duration corresponding to the picking action and the placing action includes the following steps: Obtain the time difference between the adjacent motor thread cutting time point and motor start time point, and use the adjacent motor thread cutting time point and motor start time point as a time stamp array; Select the time stamp array with the time difference greater than the preset threshold as the second target time stamp array; When it is detected that there is no cloth near the sewing needle of the sewing machine, obtain the actual sewing action data of the sewing machine before the time period corresponding to the second target time stamp array; Based on the actual sewing action data, determine whether the sewing worker has completed sewing a finished product; When it is determined that the lathe worker has completed the sewing of a finished product, the thread cutting time point corresponding to the second target time stamp array is used as the start time point of the placing action, and the average value of the thread cutting time point corresponding to the second target time stamp array and the motor starting time point is used as the start time point of the picking action; the duration between the start time point of the placing action and the start time point of the picking action is used as the action duration of the placing action, and the duration between the start time point of the picking action and the motor starting time point corresponding to the second target time stamp array is used as the action duration of the picking action.

5. The sewing efficiency detection method based on lathe worker motion analysis according to claim 3 or 4, characterized in that It further includes detecting whether there is fabric near the sewing needle of the sewing machine; Detecting whether there is fabric near the sewing needle of the sewing machine includes the following steps: Obtain multiple sewing needle area images within a target time period; Calculate the difference in pixel values between each sewing needle area image and the sewing needle reference image, where there is fabric near the sewing needle in the sewing needle reference image; When the proportion of pixel points in the sewing needle area image where the difference is greater than a preset difference is greater than a first preset proportion, it is determined that there is fabric in the sewing needle area image; Among the multiple sewing needle area images, when the proportion of sewing needle area images determined to have fabric is greater than a second preset proportion, it is determined that there is fabric near the sewing needle of the sewing machine; otherwise, it is determined that there is no fabric near the sewing needle of the sewing machine.

6. The sewing efficiency detection method based on lathe worker motion analysis according to claim 1, wherein Calculating the sewing efficiency of the lathe worker based on the action durations corresponding to the whole action, the sewing action, the picking action, and the placing action includes the following steps: Obtain the reference durations corresponding to the whole action, the sewing action, the picking action, and the placing action; Calculate the sewing efficiency of the lathe worker based on the action duration and the reference duration, and the sewing efficiency of the lathe worker includes the total sewing efficiency and the sewing single-action efficiency.

7. A sewing efficiency detection system based on lathe worker motion analysis, characterized in that, The system includes an acquisition module, a first processing module, a second processing module, and a detection module; The acquisition module is used to acquire the motor stop time point, the thread cutting time point, and the motor starting time point of the sewing machine; The first processing module is used to determine the whole action and the sewing action of the lathe worker based on adjacent motor stop time points and motor starting time points, and obtain the action durations corresponding to the whole action and the sewing action; The second processing module is used to determine the picking action and the placing action of the lathe worker based on adjacent thread cutting time points and motor starting time points, and obtain the action durations corresponding to the picking action and the placing action; The detection module is used to calculate the sewing efficiency of the lathe worker based on the action durations corresponding to the whole action, the sewing action, the picking action, and the placing action.

8. A terminal, characterized in that, The terminal includes: a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory, so that the terminal executes the sewing efficiency detection method based on lathe worker action analysis according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the terminal, it implements the sewing efficiency detection method based on lathe worker action analysis according to any one of claims 1 to 6.

10. A sewing efficiency detection system based on lathe worker motion analysis, characterized in that, It includes the terminal according to claim 8 and a sewing machine; The sewing machine includes an information collection module; The information acquisition module is used to acquire the motor stop time point, the thread cutting time point, and the motor start time point of the sewing machine, and provide them to the terminal.

Images