Employee skill level analysis method and system based on similar processes, and medium

Abstract

The invention provides an employee skill level analysis method and system based on similar processes and a medium, and the method comprises the steps: obtaining event data during the sewing operation of an employee, the event data at least comprising event time, event type and event parameters; recognizing array data based on the event data, wherein the array data at least comprises an action sequence, a needle number array and a man-hour array; determining whether the sewing operation process is a similar process based on the action sequence, and extracting the sewing operation process determined to be the similar process as a target process; and based on the target process, a corresponding man-hour array is extracted for analysis and processing so as to determine the skill level of the employee, and the skill level of the employee comprises the stability of the sewing operation of the employee. According to the method, the problem that the actual sewing skill cannot be effectively identified due to many and miscellaneous factory procedures is solved through similar procedure judgment, and the skill level of the employees in the similar procedures of the factory is evaluated, so that the skill level of the employees can be scientifically judged.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, system and medium for analyzing employee skill levels based on similar processes. Background Art

[0002] At present, IoT sewing equipment has basically replaced ordinary sewing machines. With the development of IoT systems, IoT sewing equipment can provide employees with real-time sewing data.

[0003] Currently, garment factories have numerous and complex processes. Many employees are assigned different styles or process names during production, but their actual sewing performance is almost identical. As a result, the skill levels of many employees cannot be compared. As a result, managers have no data to base subsequent production adjustments on, relying only on experience and daily observation, resulting in low production efficiency. Therefore, the need to quickly and accurately analyze the sewing skill levels of employees in similar processes is becoming increasingly important. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, system and medium for analyzing employee skill levels based on similar processes, so as to solve the problem of analyzing employee skill levels based on similar processes.

[0005] In a first aspect, the present application provides a method for analyzing employee skill levels based on similar processes, the method comprising:

[0006] Acquire event data of employees during sewing operations, wherein the event data includes at least event time, event type, and event parameters;

[0007] Identifying array data based on the event data, the array data at least including an action sequence, a stitch number array, and a working time array;

[0008] determining whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process determined to be a similar process is extracted as a target process;

[0009] Based on the target process, a corresponding man-hour array is extracted and analyzed to determine the skill level of the employee.

[0010] In a possible implementation of the present application, the acquisition of event data during employee sewing operations specifically includes:

[0011] Based on the IoT sewing equipment, statistical data of employees’ sewing operations is obtained, including:

[0012] Obtaining the event time based on the time format data in the statistical data;

[0013] The event type is obtained by matching a preset table based on the characteristic data in the statistical data, wherein the event type at least includes motor start, motor stop, presser foot lifting action, and presser foot releasing action;

[0014] The target data is identified based on the target value in the feature data to obtain the event parameters, wherein the event parameters include the number of sewing stitches.

[0015] In a possible implementation of the present application, identifying array data based on the event data specifically includes:

[0016] Extracting feature values ​​in sequence based on feature data in the event type to obtain the action sequence;

[0017] Obtain the working hour array based on the action sequence combined with the event time according to natural time statistics;

[0018] The needle number array is obtained by extracting needle values ​​based on the target data corresponding to the action sequence.

[0019] In a possible implementation of the present application, the determining whether the sewing operation process is a similar process based on the action sequence specifically includes:

[0020] Based on the array data, a support vector machine is used to perform classification processing to obtain stable parameters, wherein the stable parameters at least include a stable action sequence, a stable number of stitches, and a stable working time;

[0021] Similar processes are judged based on the stable action sequences corresponding to the sewing operations of different employees, where:

[0022] Calculate the target distance of the stable action sequence using a preset similarity algorithm;

[0023] Based on the comparison between the target distance and the preset similarity distance, when the target distance is smaller than the preset similarity distance, it indicates that the operation process of the current employee during the sewing operation is a similar process.

[0024] In a possible implementation of the present application, the calculation of the target distance of the stable action sequence using a preset similarity algorithm specifically includes:

[0025] Obtain stable action sequences of different employees during sewing operations as comparison sequences;

[0026] Continuously removing duplicates from target event types based on the comparison sequence to obtain a standardized sequence, wherein the target event types at least include a presser foot lifting action and a presser foot lowering action;

[0027] The Levenshtein algorithm is used as the preset similarity algorithm to calculate the distance range of the standardized sequence to obtain the target distance.

[0028] In a possible implementation of the present application, extracting the corresponding work hour array based on the target process and performing analysis and processing to determine the employee's skill level specifically includes:

[0029] Extracting a corresponding working hour array based on the target process as total working hour data;

[0030] Perform multiple data elimination on the total working hours data to obtain elimination parameters;

[0031] Calculating the target difference between the total working hours data and the elimination parameter;

[0032] The employee skill level is obtained by calculating the ratio of the target difference to the total working hours data, wherein the employee skill level includes the stability of the employee's sewing operation.

[0033] In a possible implementation of the present application, the multiple data elimination process is performed on the total working hours data to obtain the elimination parameters, specifically including:

[0034] The rejection parameters include at least first rejection data, second rejection data and third rejection data, wherein,

[0035] Performing a first elimination on the total working hour data based on a normal distribution to obtain first processed data, wherein the amount eliminated for the first time is the first eliminated data;

[0036] Performing a second elimination on the first processed data based on median elimination to obtain second processed data, wherein the amount eliminated for the second time is the second eliminated data;

[0037] The second processed data is eliminated for a third time based on the normal distribution to obtain third processed data, wherein the number eliminated for the third time is the third eliminated data.

[0038] In a second aspect, the present application provides a system for analyzing employee skill levels based on similar processes, the system comprising:

[0039] An acquisition module is used to acquire event data of employees during sewing operations, wherein the event data at least includes event time, event type, and event parameters;

[0040] an identification module, configured to identify array data based on the event data, the array data comprising at least an action sequence, a stitch number array, and a working hour array;

[0041] a judgment module, configured to judge whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process judged to be a similar process is extracted as a target process;

[0042] The analysis module is used to extract the corresponding working hour array based on the target process and perform analysis and processing to determine the employee's skill level.

[0043] In a third aspect, the present application provides a computer-readable storage medium as described above, on which a computer program is stored, and when the program is executed by a processor, the method for analyzing employee skill levels based on similar processes is implemented.

[0044] In a fourth aspect, the present application provides an electronic device as described above, comprising: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to load and execute the computer program so that the electronic device executes the employee skill level analysis method based on similar processes.

[0045] As described above, the employee skill level analysis method, system and medium based on similar processes of the present invention solve the problem that the factory has many and complicated processes and cannot effectively identify actual sewing skills through similar process judgment, and thereby evaluate the skill level of employees in similar processes in the factory, and can scientifically determine the employee skill level. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Shown is a scenario application diagram of an embodiment of the employee skill level analysis method based on similar processes of the present invention;

[0047] Figure 2 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0048] Figure 3 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0049] Figure 4 A schematic diagram showing the production of event data in an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0050] Figure 5 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0051] Figure 6 Shown is a schematic diagram of statistical data in an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0052] Figure 7 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0053] Figure 8 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0054] Figure 9 Shown is a schematic diagram of an example of similar processes in an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0055] Figure 10 Shown is a schematic diagram of an example of similar processes in an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0056] Figure 11 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0057] Figure 12 Shown is a schematic diagram of employee working hours data in an embodiment of the employee skill level analysis method based on similar processes of the present invention;

[0058] Figure 13 Shown is a schematic diagram of the method steps of an embodiment of the method for analyzing employee skill levels based on similar processes of the present invention;

[0059] Figure 14 Shown is a broken line diagram of employee skill levels in an embodiment of the employee skill level analysis method based on similar processes of the present invention;

[0060] Figure 15 Shown is a schematic structural diagram of an embodiment of the employee skill level analysis system based on similar processes of the present invention;

[0061] Figure 16 Shown is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0062] Component number description

[0063] Steps S202 to S208

[0064] Steps S302 to S308

[0065] Steps S502 to S506

[0066] Steps S702 to S708

[0067] Steps S802 to S806

[0068] Steps S1102 to S1108

[0069] Steps S1302 to S1306

[0070] 150 Employee skill level analysis system based on similar processes

[0071] 151 Get Module

[0072] 152 Identification Module

[0073] 153 Judgment Module

[0074] 154 Analysis Module DETAILED DESCRIPTION

[0075] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0076] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0077] In order to quickly and accurately analyze the sewing skill levels of employees in similar processes, this application designs a method based on similar process identification, and uses this as a basis to analyze the skill levels of employees, wherein reference Figure 1, which is a scenario application diagram of the employee skill level analysis method based on similar processes described in this application. For sewing workers, different employees have different processes for completing the same piece of clothing. Therefore, it is necessary to obtain the corresponding processes for similar process identification and combine multiple elimination operations to obtain the stability of the employees' sewing, so as to distinguish the employees based on the stability. The higher the stability, the better the corresponding skill level of the employee. For example, if employees A / B / C are calculated to be "80%", "60%" and 55% respectively, then their skill levels are excellent, good and poor respectively. The employee's skill level is identified by ranking between employees with similar processes instead of the size of the data obtained. Furthermore, when allocating business, the factory manager can allocate production processes according to the adaptability of different employees, thereby ensuring the reliable quality of clothes produced by sewing production operations.

[0078] Specifically, see Figure 2 In one embodiment of the invention, the employee skill level analysis method based on similar processes of the present invention includes the following steps:

[0079] Step S202, obtaining event data of the employee during sewing operation, wherein the event data at least includes event time, event type and event parameters;

[0080] Step S204, identifying array data based on the event data, wherein the array data at least includes an action sequence, a stitch number array, and a working hour array;

[0081] Step S206, judging whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process judged to be a similar process is extracted as a target process;

[0082] Step S208 : extracting the corresponding man-hour array based on the target process and performing analysis and processing to determine the employee's skill level.

[0083] It should be noted that, in this embodiment, the event data of employees' sewing operations are obtained, such as Figure 3 As shown, the specific steps include:

[0084] Step S302, obtaining statistical data of employees' sewing operations based on the IoT sewing equipment;

[0085] Step S304, obtaining the event time based on the time format data in the statistical data;

[0086] Step S306, obtaining the event type based on matching the characteristic data in the statistical data with a preset table;

[0087] Correction S308: identifying target data based on the target value in the feature data to obtain the event parameter.

[0088] Specifically, the event data described in this application relies on the acquisition module of the IoT sewing equipment to provide, for example, the data of each completed piece is obtained through a metronome or piece counting algorithm, etc., wherein the event data used in this application is the technical basis of the existing prior art and is not the innovation of this application. After obtaining the statistical data of the employees' sewing operations based on the IoT sewing equipment, the statistical data can be analyzed to obtain the event time, event type and event parameters, specifically, such as Figure 4 As shown, it shows a production schematic diagram of event data, wherein the time format data in the specific statistical data of the event time, such as "2021-11-02 14:25:48.665", correspondingly, the characteristic data after the time format data corresponds to the event type, and matching the preset table can obtain different meanings, wherein the characteristic data is the numerical value after the time format data, and the value range is "0-10", and accordingly, the event type "0-10" represents various actions or states of the sewing machine, for example: "0" represents device shutdown, "1" represents device startup, "2" represents motor start, "3" represents motor stop, "4" represents presser foot lift, "5" represents presser foot lowering, "6" represents Feng sewing machine thread trimming (overlock sewing, i.e. front trimming), "7" represents sewing machine back trimming (applicable to overlock sewing), "8" represents electronic control meter, "9" represents reinforcement seam, "10" represents stitch adjustment, further, refer to Figure 4 The target value in the characteristic data corresponds to the event parameter. Specifically, the target value is "3". Accordingly, the number after the target value "3" corresponds to the event parameter, which also corresponds to the specific number of sewing needles.

[0089] Furthermore, in one embodiment of the invention, Figure 5 As shown, identifying array data based on the event data specifically includes the following steps:

[0090] Step S502: extracting feature values ​​in sequence based on the feature data in the event type to obtain the action sequence;

[0091] Step S504, obtaining the working hours array based on the action sequence and the event time according to natural time statistics;

[0092] Step S506 , extracting needle values ​​based on the target data corresponding to the action sequence to obtain the needle number array.

[0093] It should be noted that the above embodiment describes that the event data specifically includes event time, event type and event parameters. In this embodiment, accordingly, the event time corresponds to a working hour array, the event type corresponds to an action sequence, and the event parameter corresponds to a stitch number array. Specifically, based on the feature data in the event type, feature values ​​are extracted in sequence to obtain the action sequence, and based on the action sequence combined with the event time, the working hour array is obtained according to natural time statistics, and based on the target data corresponding to the action sequence, stitch values ​​are extracted to obtain the stitch number array. Figure 6 , showing the statistical data of an employee completing a piece of clothing. The sequence "1459239645" represents the action sequence of an employee sewing a piece of clothing. The specific actions are: "start the machine, lift the presser foot, lower the presser foot, sew, start the motor, stop the motor, sew, and trim the thread." The target value "3" shows that the number of stitches is "60," and the total working time is "13" seconds. Therefore, statistics can be performed on the data of each piece of clothing for a period of time or on a day to obtain the action sequence, stitch number array, and working time array.

[0094] Furthermore, in one embodiment of the invention, Figure 7 As shown, judging whether the sewing operation process is a similar process based on the action sequence specifically includes the following steps:

[0095] Step S702: performing classification processing based on the array data using a support vector machine to obtain stable parameters, wherein the stable parameters at least include a stable action sequence, a stable number of stitches, and a stable working time;

[0096] Step S704, performing similar process determination based on the stable action sequences corresponding to the sewing operations of different employees;

[0097] Step S706, calculating the target distance of the stable action sequence using a preset similarity algorithm;

[0098] Step S708 : comparing the target distance with a preset similarity distance. When the target distance is smaller than the preset similarity distance, it indicates that the sewing process of the current employee is a similar process.

[0099] It should be noted that, in this embodiment, when an employee completes a piece of clothing, the corresponding array data respectively correspond to the three features of the action, number of stitches and working hours for completing a piece of clothing. The support vector machine can be used to classify the array data of the employee's sewing operation according to these three features to obtain the process characteristics of the current employee. Specifically, the support vector machine is used to perform classification processing based on the array data to obtain stable parameters, wherein the stable parameters at least include a stable action sequence, a stable number of stitches and a stable working hours. Then, similar processes are judged based on the stable action sequences corresponding to the sewing operations of different employees. Specifically, a preset similarity algorithm is used to calculate the target distance of the stable action sequence, and then based on the target distance, the target distance is calculated. The target distance is compared with the preset similarity distance, wherein, when the target distance is less than the preset similarity distance, it indicates that the operation process of the current employee in the sewing operation is a similar process. Among them, it is worth mentioning that for the number of stitches and working hours of the process characteristics in the sewing operation, since they are greatly affected by the size (for example, in the same process, the number of stitches required for clothes of size M is "200", so the working hours are longer, and the number of stitches corresponding to clothes of size L is only "80", so the working hours are shorter), the judgment of similar processes is mainly carried out through the action sequence. For example, if the actions of the process sequence such as fixing sewing, lifting and lowering the presser foot, and thread cutting are the same, and the motor start and stop actions are similar, then these processes are judged to be similar processes.

[0100] Specifically, refer to Figure 8 , using the preset similarity algorithm to calculate the target distance of the stable action sequence, specifically including the following steps:

[0101] Step S802, obtaining stable action sequences of different employees during sewing operations as comparison sequences;

[0102] Step S804: performing continuous deduplication on target event types based on the comparison sequence to obtain a standardized sequence, wherein the target event types at least include a presser foot lifting action and a presser foot lowering action;

[0103] Step S806: Using the Levenshtein algorithm as the preset similarity algorithm to calculate the distance range of the standardized sequence to obtain the target distance.

[0104] It should be noted that, in this embodiment, how to calculate the target distance of the stable action sequence is specifically described, wherein the Levenshetein algorithm is used as the preset similarity algorithm for calculation, and Levenshetein, Levenshtein distance, also known as Levenshtein distance, is a kind of edit distance, which refers to the minimum number of editing operations required to convert one string into another. In this embodiment, it is used as an application, and the specific algorithm content is not repeated. Among them, the stable action sequences of different employees during sewing operations are obtained as comparison sequences. Assume that the two stable action sequences are " 459239645" and "45923239645", and the target event type is continuously deduplicated based on the comparison sequence to obtain a standardized sequence, wherein the target event type at least includes a presser foot lifting action and a presser foot lowering action. Specifically, in actual operation, redundant "2" and "3" in the sequence are removed to eliminate the continuous presser foot lifting data, and the Levenshtein distance of the standardized sequence is obtained, wherein the preset similarity distance is "3", that is, when the Levenshtein distance is less than "3", it can be determined that the operation process of the current employee's sewing operation is a similar process.

[0105] Specifically, refer to Figure 9 , which is a schematic diagram of similar process examples. The action sequence of the process on the left is "459239645", and the action sequence of the process on the right is "45923239645". Lifting and lowering the presser foot, fixing sewing, and thread cutting are all the same. The process on the right has only one more motor start and stop than the process on the left. Therefore, these two processes are similar processes (the actual sewing operation on the right may be because the individual is used to stepping on the sewing machine twice when sewing the edge and only once on the left. It may also be that the left side is a straight edge and the right side is slightly curved, but the employee on the right only needs a little adjustment to complete it compared with the employee on the left).

[0106] Specifically, refer to Figure 10, which shows an example diagram of similar processes. The action sequence of the process on the left is "459239645", the action sequence of the middle process is "45459239645", and the action sequence of the process on the right is "4592345239645". Although the middle process has an additional presser foot lifting and lowering operation, it actually has no effect on the process. (In actual sewing, this is manifested by different employee habits or improper adjustment of the presser foot the first time, which causes the employee to lift the presser foot multiple times in a row). Therefore, the continuous presser foot lifting and lowering operation is only recorded once. Therefore, the left process and the middle process are similar processes (or the same process). However, the data on the right also has an additional presser foot lifting operation, but it does not occur continuously. Therefore, the left process and the right process are not similar processes. (In actual sewing, the employee lifts the presser foot for the first time, starts sewing, completes a section of sewing, and then lifts and lowers the presser foot to adjust the fabric before sewing again. Therefore, the process is definitely different from that of lifting the presser foot once).

[0107] Furthermore, in one embodiment of the invention, Figure 11 As shown, based on the target process, the corresponding working hour array is extracted and analyzed to determine the employee's skill level, which specifically includes the following steps:

[0108] Step S1102, extracting a corresponding working hour array based on the target process as total working hour data;

[0109] Step S1104, performing multiple data elimination processing on the total working hours data to obtain elimination parameters;

[0110] Step S1106, calculating the target difference between the total working hours data and the elimination parameter;

[0111] Step S1108: Calculate the ratio of the target difference to the total working hours data to obtain the employee skill level, wherein the employee skill level includes the stability of the employee's sewing operation.

[0112] It should be noted that, in this embodiment, similar process judgment is performed on the factory employee data. If the processes of some employees are judged to be similar, the skills of these employees are compared uniformly. Figure 12Since most of the employee working hour data are stable and within a certain distribution range, a small amount of deviations are large and conform to the normal distribution. Therefore, the normal distribution can be used for elimination. Specifically, first, the corresponding working hour array is extracted based on the target process to obtain the total working hour data, denoted as N, and then the total working hour data is subjected to multiple data elimination processing to obtain the elimination parameters, wherein the elimination parameters at least include the first elimination data n1, the second elimination data n2 and the third elimination data n3, and the target difference between the total working hour data and the elimination parameters is calculated, wherein the target difference specifically includes the total working hour data minus the first elimination data, the second elimination data and the third elimination data in sequence, that is, calculating (N-n1-n2-n3), and finally calculating the ratio of the target difference to the total working hour data to obtain the employee skill level, that is, calculating (N-n1-n2-n3) / N, which corresponds to the stability of the employee's sewing operation, wherein the higher the stability, the better the employee's skill level.

[0113] Specifically, refer to Figure 13 , multiple data elimination processing is performed on the total working hours data to obtain elimination parameters, which specifically includes the following steps:

[0114] Step S1302: performing a first elimination on the total working hours data based on a normal distribution to obtain first processed data, wherein the amount eliminated for the first time is the first eliminated data;

[0115] Step S1304: performing a second elimination on the first processed data based on median elimination to obtain second processed data, wherein the amount eliminated for the second time is the second eliminated data;

[0116] Step S1306: performing a third elimination on the second processed data based on normal distribution to obtain third processed data, wherein the number eliminated for the third time is the third eliminated data.

[0117] It should be noted that, in this embodiment, the elimination parameters include at least the first elimination data, the second elimination data, and the third elimination data. Specifically, the total working hour data is eliminated for the first time based on the normal distribution to obtain the first processed data, wherein the number of the first elimination is the first elimination data n1, that is, the root mean square and standard deviation of the working hour data are calculated, and only the data of [root mean square - standard deviation, root mean square + standard deviation] is retained, that is, Figure 12The range shown by "68%" in the result is not completely eliminated). However, if the data is eliminated only by normal distribution, incomplete elimination will occur. For example, if the root mean square of a set of data is calculated to be "50" and the standard deviation is "40", then the data from "10" to "90" will be retained. The actual reason for this problem is that some large data in the original working hour array are not eliminated by normal distribution (for example, [40,40,40,40,40,70,70,80], the root mean square is calculated to be "55.0", the standard deviation is "16.6", and the sum is "71.6", resulting in "70" being unable to be eliminated). Therefore, the first processed data can be eliminated for the second time based on median elimination to obtain the second processed data, where the number of data eliminated in the second time is the number of data eliminated in the second time. Specifically, add a elimination method using the median, take the median of the array after elimination through normal distribution, retain the data that is smaller than the median + standard deviation, eliminate the rest and record the number of eliminations (continue with the above example, after sorting the array, the median is "40", "40+16.6" is "56.6", so "70" will also be eliminated), finally, it is still necessary to perform a third elimination on the second processed data based on the normal distribution to obtain the third processed data, where the number of the third elimination is the third elimination data, that is, after the second elimination, continue to add another normal distribution elimination (that is, after eliminating "70", the data distribution will be more concentrated, so the standard deviation becomes smaller, resulting in a smaller range when performing normal distribution elimination again, and more unstable data can be eliminated).

[0118] In addition, it is worth mentioning that in actual production operations, the sewing of a certain style in the factory generally takes multiple days, so the issue of employee skill updates will also be involved. For example, on the first day, the skills of employees A / B / C are "80%, 60%, 55%" respectively, and on the second day, the skills of employees A / B / C are "85%, 90%, 55%" respectively. Then, on the second day, the skill level of employee B is stronger than that of employee A. Similarly, the skill level of employees will also change in the subsequent production process. Therefore, in actual application, in addition to calculating the skill level at the end of each day's production, the application will also perform skill level analysis on all data of the employee's current style when the employee changes styles (that is, use the data of multiple days of production of the style for skill level analysis), and finally obtain the employee's skill level line chart and the employee's skill level for the corresponding style, such as Figure 14 As shown, it is a line diagram showing the skill levels of employees. Factory managers can allocate production processes based on the chart and the skill levels of employees for different styles.

[0119] An embodiment of the present application also provides an employee skill level analysis system based on similar processes, which can implement the employee skill level analysis method based on similar processes described in the present application. However, the implementation device of the employee skill level analysis method based on similar processes described in the present application includes but is not limited to the structure of the employee skill level analysis system based on similar processes listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0120] See also Figure 15 In one embodiment, this embodiment provides a system 150 for analyzing employee skill levels based on similar processes, the system comprising:

[0121] An acquisition module 151 is used to acquire event data of an employee during sewing operations, wherein the event data includes at least event time, event type, and event parameters;

[0122] an identification module 152 for identifying array data based on the event data, the array data including at least an action sequence, a stitch number array, and a working hour array;

[0123] a judgment module 153 for judging whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process judged to be a similar process is extracted as a target process;

[0124] The analysis module 154 is used to extract the corresponding working hour array based on the target process and perform analysis and processing to determine the employee's skill level.

[0125] Since the specific implementation of this embodiment corresponds to the aforementioned method embodiment, the same details will not be repeated here, and those skilled in the art should also understand that Figure 15 The division of the various modules in the embodiment is merely a division of logical functions. In actual implementation, all or part of the modules can be integrated into one or more physical entities, and all of these modules can be implemented in the form of software called by processing elements, or all of them can be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware.

[0126] See Figure 16 This embodiment provides an electronic device. Specifically, the electronic device includes at least: a memory and a processor connected via a bus, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to perform all or part of the steps in the aforementioned method embodiment.

[0127] In summary, the present invention solves the problem that there are many and complicated factory processes and actual sewing skills cannot be effectively identified by judging similar processes, and thereby evaluates the skill levels of employees in similar processes in the factory, and can scientifically determine the skill levels of employees.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0129] The modules / units described as separate components may or may not be physically separate, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into a processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0130] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0131] The embodiment of the present application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state drive, a magnetic tape, a floppy disk, an 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 includes one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid-state drive (SSD)), etc.

[0132] The embodiment of the present application may also provide a computer program product, the computer program product including one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method.

[0133] When the computer program product is executed by a computer, the computer executes the method described in the above method embodiment. The computer program product can be a software installation package. When the above method is needed, the computer program product can be downloaded and executed on the computer.

[0134] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0135] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A method for analyzing employee skill levels based on similar processes, characterized in that: include: Acquire event data of employees during sewing operations, wherein the event data includes at least event time, event type, and event parameters; Identifying array data based on the event data, the array data at least including an action sequence, a stitch number array, and a working time array; determining whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process determined to be a similar process is extracted as a target process; Based on the target process, a corresponding man-hour array is extracted and analyzed to determine the skill level of the employee.

2. The method for analyzing employee skill levels based on similar processes according to claim 1, characterized in that: The event data of employees' sewing operations are obtained, specifically including: Based on the IoT sewing equipment, statistical data of employees’ sewing operations is obtained, including: Obtaining the event time based on the time format data in the statistical data; The event type is obtained by matching a preset table based on the characteristic data in the statistical data, wherein the event type at least includes motor start, motor stop, presser foot lifting action, and presser foot releasing action; The target data is identified based on the target value in the feature data to obtain the event parameters, wherein the event parameters include the number of sewing stitches.

3. The method for analyzing employee skill levels based on similar processes according to claim 2, characterized in that: The identifying array data based on the event data specifically includes: Extracting feature values ​​in sequence based on feature data in the event type to obtain the action sequence; Obtain the working hour array based on the action sequence combined with the event time according to natural time statistics; The needle number array is obtained by extracting needle values ​​based on the target data corresponding to the action sequence.

4. The method for analyzing employee skill levels based on similar processes according to claim 3 is characterized in that: The determining whether the sewing operation process is a similar process based on the action sequence specifically includes: Based on the array data, a support vector machine is used to perform classification processing to obtain stable parameters, wherein the stable parameters at least include a stable action sequence, a stable number of stitches, and a stable working time; Similar processes are judged based on the stable action sequences corresponding to the sewing operations of different employees, where: Calculate the target distance of the stable action sequence using a preset similarity algorithm; Based on the comparison between the target distance and the preset similarity distance, when the target distance is smaller than the preset similarity distance, it indicates that the operation process of the current employee during the sewing operation is a similar process.

5. The method for analyzing employee skill levels based on similar processes according to claim 4, characterized in that: The method of calculating the target distance of the stable action sequence using a preset similarity algorithm specifically includes: Obtain stable action sequences of different employees during sewing operations as comparison sequences; Continuously removing duplicates from target event types based on the comparison sequence to obtain a standardized sequence, wherein the target event types at least include a presser foot lifting action and a presser foot lowering action; The Levenshtein algorithm is used as the preset similarity algorithm to calculate the distance range of the standardized sequence to obtain the target distance.

6. The method for analyzing employee skill levels based on similar processes according to claim 5, characterized in that: The step of extracting the corresponding working hour array based on the target process and performing analysis and processing to determine the employee's skill level specifically includes: Extracting a corresponding working hour array based on the target process as total working hour data; Perform multiple data elimination on the total working hours data to obtain elimination parameters; Calculating the target difference between the total working hours data and the elimination parameter; The employee skill level is obtained by calculating the ratio of the target difference to the total working hours data, wherein the employee skill level includes the stability of the employee's sewing operation.

7. The method for analyzing employee skill levels based on similar processes according to claim 6, characterized in that: The multiple data elimination process on the total working hours data to obtain the elimination parameters specifically includes: The elimination parameters include at least first elimination data, second elimination data, and third elimination data, wherein the first processing data is obtained by performing the first elimination on the total working hours data based on the normal distribution, wherein the number of the first elimination is the first elimination data; Performing a second elimination on the first processed data based on median elimination to obtain second processed data, wherein the amount eliminated for the second time is the second eliminated data; The second processed data is eliminated for a third time based on the normal distribution to obtain third processed data, wherein the number eliminated for the third time is the third eliminated data.

8. A system for analyzing employee skill levels based on similar processes, characterized in that: include: and an acquisition module for acquiring event data of employees during sewing operations, wherein the event data at least includes event time, event type, and event parameters; an identification module, configured to identify array data based on the event data, the array data comprising at least an action sequence, a stitch number array, and a working hour array; a judgment module, configured to judge whether the sewing operation process is a similar process based on the action sequence, wherein the sewing operation process judged to be a similar process is extracted as a target process; The analysis module is used to extract the corresponding working hour array based on the target process and perform analysis and processing to determine the employee's skill level.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for analyzing employee skill levels based on similar processes as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes: a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the employee skill level analysis method based on similar processes as described in any one of claims 1 to 7.

Images