Method and device for intelligent matching of employee skills with sewing processes, equipment and medium

Abstract

The application provides an intelligent matching method, device, equipment and medium for employee skills and sewing processes. The method comprises the following steps: decomposing sewing skills into a plurality of first atomic operation dimensions; performing quantitative processing on multi-source data in the employee sewing operation process based on the plurality of first atomic operation dimensions to obtain an employee skill vector; decomposing each sewing process into a plurality of second atomic operation dimensions which are the same as the sewing skills; determining a process capability requirement vector corresponding to the plurality of second atomic operation dimensions; performing similarity calculation on the employee skill vector and the process requirement vector based on a preset multi-priority principle to determine a matching degree; and determining a matching result of the employee and the corresponding sewing process based on the matching degree. The application innovatively proposes an atomic decomposition idea, realizes granular fine management of employee skills and process requirements, establishes a one-to-one correspondence between the employee skill vector and the process requirement vector based on atomic decomposition, and realizes intelligent matching.

Description

Technical Field

[0001] This application belongs to the field of data processing technology and relates to a method, device, equipment and medium for intelligent matching of employee skills and sewing processes. Background Technology

[0002] The garment manufacturing industry is a typical labor-intensive industry. As a core production process, the rationality of personnel scheduling and process allocation directly affects production efficiency, product yield, and manufacturing costs. Currently, the industry's personnel allocation for sewing processes mainly relies on traditional manual management models, where team leaders subjectively allocate personnel based on their personal experience. Existing technical solutions have significant limitations in practical application: First, the skills evaluation system lacks objective quantitative standards. Second,

[0003] Third, the personnel-job matching strategy is simplistic and inefficient. Fourth, the value of production data is not fully explored. Furthermore, the IoT-based garment production management systems that have emerged in recent years still struggle to address the aforementioned technical pain points due to a lack of video capture and in-depth analysis methods for operational actions.

[0004] Therefore, how to achieve true intelligent matching of employees with corresponding work processes has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and medium for intelligent matching of employee skills with sewing processes, to achieve true intelligent matching of employees with corresponding processes.

[0006] In a first aspect, this application provides an intelligent matching method for employee skills and sewing processes. The method includes: decomposing sewing skills into multiple first atomic-level operational dimensions, each of which is an indivisible operational capability unit; quantifying multi-source data in the employee's sewing process based on the multiple first atomic-level operational dimensions to obtain an employee skill vector; and decomposing each sewing process into multiple second atomic-level operational dimensions identical to the sewing skill.

[0007] Determine multiple process capability requirement vectors corresponding to the second atomic-level operation dimensions; based on a preset multi-priority principle, calculate the similarity between the employee skill vector and the process requirement vector to determine the matching degree; based on the matching degree, determine the matching result between the employee and the corresponding sewing process.

[0008] This application innovatively proposes an atomic-level decomposition concept, breaking down complex sewing manual operations into indivisible, quantifiable minimum units. This breaks the ambiguity of traditional holistic quantification and achieves granular, refined management of employee skills and process requirements. Based on atomic decomposition, a one-to-one correspondence between employee skill vectors and process requirement vectors is established. This bidirectional mapping mechanism transforms the abstract person-job matching into a computable mathematical problem, laying a solid mathematical model foundation for intelligent matching. Addressing the limitations of traditional matching methods, a composite priority algorithm combining capability access, strength maximization, weakness avoidance, and efficiency optimization is proposed. This algorithm not only solves the one-sidedness of single-dimensional quantification but also maximizes employee value while ensuring production baseline through multi-level constraints, achieving a balance between the scientific nature of person-job matching and production efficiency.

[0009] In one implementation of the first aspect, the step of quantifying multi-source data during an employee's sewing operation based on multiple first atomic-level operation dimensions to obtain an employee skill vector includes: setting corresponding quantitative indicators and scoring rules for each first atomic-level operation dimension; collecting multi-source data during the employee's sewing operation; calculating the employee's individual score for each first atomic-level operation dimension based on the multi-source data, the quantitative indicators, and the scoring rules; and obtaining the employee skill vector based on each individual score and its corresponding weight.

[0010] In one implementation of the first aspect, determining the process capability requirement vectors corresponding to multiple second atomic-level operation dimensions includes: setting a preset requirement score and a weight score for each second atomic-level operation dimension corresponding to a sewing process; and performing a weighted calculation on each preset requirement score and the weight score corresponding to the preset requirement score to obtain the process capability requirement vectors corresponding to all second atomic-level operation dimensions.

[0011] In one implementation of the first aspect, determining the matching result between the employee and the corresponding sewing process based on the matching degree includes: if the matching degree is greater than a first matching threshold, the matching result between the employee and the corresponding sewing process is a first-level match; if the matching degree is greater than a second matching threshold and less than or equal to the first matching threshold, the matching result between the employee and the corresponding sewing process is a second-level match; if the matching degree is greater than a third matching threshold and less than or equal to the preset second matching threshold, the matching result between the employee and the corresponding sewing process is a third-level match; if the matching degree is less than or equal to the preset third matching threshold, the matching result between the employee and the corresponding sewing process is a mismatch.

[0012] In one implementation of the first aspect, the preset multi-priority principles include: the capability admission principle: the employee's score in each item of all the first atomic-level operation dimensions is greater than or equal to the preset requirement score required for the corresponding sewing process; the strength maximization principle: employees are preferentially assigned to the sewing process pointed to by the core strength label in the employee's skill vector; the weakness avoidance principle: employees are avoided being assigned to the sewing process pointed to by the weakness label in the employee's skill vector; and the efficiency optimization principle: under the premise of meeting quality requirements, employees with the highest predicted production efficiency are preferentially assigned.

[0013] In one implementation of the first aspect, the multiple first atomic-level operation dimensions include: straight-line trajectory stability, curve trajectory smoothness, sharp corner processing accuracy, speed control stability, single-point alignment accuracy, multi-point synchronous alignment, arc alignment accuracy, thin material tension control, thick material penetration capability, thick-thin transition processing, asynchronous action coordination, and dynamic gesture adjustment.

[0014] In one implementation of the first aspect, the collection of multi-source data during the employee's sewing operation includes: collecting sewing trajectory coordinates, sewing speed, start and stop times, number of needle breaks, and stitch density from sewing machine sensors; collecting video of the employee's hand movements from a workstation camera to extract the time difference of the employee's movements, the number of pauses, and the frequency and amplitude of gesture adjustments during the sewing operation; collecting quality inspection data, including the number of reworks, reasons for reworks, number of scraps, and defect types; and collecting basic employee information, including seniority and historical process records.

[0015] Secondly, this application provides an intelligent matching device for employee skills and sewing processes. The device includes: a first decomposition module for decomposing sewing skills into multiple first atomic-level operational dimensions, each of which is an indivisible operational capability unit; an employee skill vector determination module for quantifying multi-source data during the employee's sewing operation based on the multiple first atomic-level operational dimensions to obtain an employee skill vector; a second decomposition module for decomposing each sewing process into multiple second atomic-level operational dimensions identical to the sewing skill; a process capability requirement vector determination module for determining process capability requirement vectors corresponding to the multiple second atomic-level operational dimensions; a matching degree determination module for calculating the similarity between the employee skill vector and the process requirement vector based on a preset multi-priority principle to determine the matching degree; and a matching result determination module for determining the matching result between the employee and the corresponding sewing process based on the matching degree.

[0016] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the intelligent matching method for employee skills and sewing processes as described in any of the first aspects of this application.

[0017] Fourthly, embodiments of this application provide an electronic device, the electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, which, when the computer program is invoked, executes the intelligent matching method for employee skills and sewing processes as described in any one of the first aspects of this application.

[0018] As described above, the intelligent matching method, apparatus, equipment, and medium for employee skills and sewing processes described in this application have the following beneficial effects:

[0019] 1) It innovatively proposes the concept of atomic-level decomposition, breaking down complex sewing manual operations into indivisible and quantifiable minimum units. This breaks the ambiguity of traditional overall quantification and achieves granular and refined management of employee skills and process requirements. Based on atomic decomposition, a one-to-one correspondence between employee skill vectors and process requirement vectors is established. This two-way mapping mechanism transforms the abstract person-job matching into a computable mathematical problem, laying a solid mathematical model foundation for intelligent matching. Addressing the limitations of traditional matching methods, a composite priority algorithm combining capability access, strength maximization, weakness avoidance, and efficiency optimization is proposed. This algorithm not only solves the one-sidedness of single-dimensional quantification but also maximizes employee value while ensuring production baseline through multi-level constraints, achieving a unity of scientific person-job matching and production efficiency.

[0020] 2) By setting clear quantitative indicators and scoring rules for atomic-level operational dimensions and calculating based on multi-source data, this method changes the traditional scoring model that relies on the subjective experience of team leaders. It effectively avoids quantitative biases caused by interpersonal relationships, visual errors, and other factors, ensuring the fairness of the quantitative results and increasing employee acceptance of the assessment results. This method refines the score to each individual item in each atomic dimension. This highly granular quantitative approach can accurately pinpoint employees' strengths and weaknesses in specific operational dimensions, providing precise data support for subsequent gap-avoidance matching strategies and targeted skills training. By introducing a weighting mechanism to integrate multiple scores into an employee skill vector, it transforms difficult-to-measure manual skills into computer-processable numerical vectors. This step completes the transformation from physical world behavioral characteristics to digital world mathematical expressions, enabling employee skills to be directly mathematically manipulated with process requirement vectors (such as similarity calculations). This lays the core data foundation for subsequent automated and intelligent person-job matching.

[0021] 3) By setting clear preset requirement scores for each second atomic-level operation dimension, the traditional process requirements, which rely on verbal descriptions or experience-based judgments, are transformed into precise numerical indicators. This establishes a unified quantitative standard for processes, eliminates the ambiguity of process definitions, and lays a standard foundation for subsequent digital management. The introduction of a weighted scoring mechanism can flexibly reflect the differences in importance of different atomic operation dimensions in a specific process. Through weighted calculation, the generated process capability requirement vector can accurately highlight the pain points and difficulties of the process. The "process capability requirement vector" generated in this step is isomorphic to the "employee skill vector" generated in the previous step in mathematical space. By abstracting both "people" and "jobs" into vectors, the system can directly perform quantitative comparisons using mathematical methods such as similarity matching. This transforms the complex problem of matching people and jobs into a programmable and computable mathematical problem, which is an indispensable prerequisite for achieving intelligent scheduling and precise matching. Attached Figure Description

[0022] Figure 1A The flowchart shown is a method for intelligently matching employee skills with sewing processes provided in an embodiment of this application.

[0023] Figure 1B This diagram illustrates factory test data corresponding to the intelligent matching method between employee skills and sewing processes provided in this application embodiment.

[0024] Figure 2 The flowchart shown is for determining employee skill vectors according to an embodiment of this application.

[0025] Figure 3 The flowchart shown is a process capability requirement vector determination provided in an embodiment of this application.

[0026] Figure 4 The flowchart shown is a result of determining the matching of employees with corresponding sewing processes, as provided in an embodiment of this application.

[0027] Figure 5 The diagram shown is a structural diagram of an intelligent matching device for employee skills and sewing processes provided in an embodiment of this application.

[0028] Figure 6 The diagram shown is a structural diagram of an electronic device provided in an embodiment of this application.

[0029] Component designation explanation

[0030] S11~S16 step 55 Match Determination Module S21~S24 step 56 Matching result determination module S31~S32 step 60 electronic devices S41~S44 step 61 processor 50 Intelligent matching device for employee skills and sewing processes 62 Non-volatile storage media 51 First Disassembly Module 63 System bus 52 Employee Skill Vector Determination Module 64 Internal memory 53 Second disassembly module 65 Network interface 54 Process Capability Requirements Vector Determination Module Detailed Implementation

[0031] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0032] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0033] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0034] like Figure 1A As shown in the flowchart, this application embodiment provides a method for intelligently matching employee skills with sewing processes. Figure 1A As shown, the intelligent matching method for employee skills and sewing processes provided in this application embodiment includes the following steps S11 to S16.

[0035] S11 breaks down sewing skills into multiple first-atomic-level operational dimensions.

[0036] Each of the first atomic-level operation dimensions is an indivisible unit of operation capability.

[0037] In some embodiments, the plurality of first atomic-level operation dimensions include: straight-line trajectory stability, curve trajectory smoothness, sharp corner processing accuracy, speed control stability, single-point alignment accuracy, multi-point synchronous alignment, arc alignment accuracy, thin material tension control, thick material penetration capability, thick-thin transition processing, asynchronous action coordination, and dynamic gesture adjustment.

[0038] For example, atomic-level operational dimensions can be added or removed depending on the product characteristics of different factories. For instance, for a denim garment factory, a dimension of "multi-layer fabric sewing capability" can be added; for an underwear factory, a dimension of "elastic fabric handling capability" can be added.

[0039] It should be noted that the aforementioned first atomic-level operation dimension includes 12 dimensions. In practical applications, any other suitable number of first atomic-level operation dimensions can be determined based on requirements, and this application does not impose any restrictions on this.

[0040] S12, quantify the multi-source data of the employee sewing operation process based on multiple first atomic-level operation dimensions to obtain the employee skill vector.

[0041] S13, each sewing process is broken down into multiple second atomic-level operational dimensions that are the same as the sewing skill.

[0042] Among them, several second-atomic-level operation dimensions include straight-line trajectory stability, curve trajectory smoothness, sharp corner handling accuracy, speed control stability, single-point alignment accuracy, multi-point synchronous alignment, arc alignment accuracy, thin material tension control, thick material penetration ability, thick-thin transition processing, asynchronous action coordination, and dynamic gesture adjustment.

[0043] S14, determine the process capability requirement vectors corresponding to multiple second atomic-level operation dimensions.

[0044] S15, based on the preset multi-priority principle, perform similarity calculation on the employee skill vector and the process requirement vector to determine the matching degree.

[0045] For example, machine learning algorithms can be used instead of linear weighted matching algorithms. By training models with historical production data, the production efficiency and quality of employees in specific processes can be predicted, thus achieving more accurate matching.

[0046] In some embodiments, the preset multi-priority principles include: capability admission principle: the employee's score in each item of all the first atomic-level operation dimensions is greater than or equal to the preset requirement score required for the corresponding sewing process; strength maximization principle: employees are preferentially assigned to the sewing process pointed to by the core strength label in the employee skill vector; weakness avoidance principle: employees are avoided being assigned to the sewing process pointed to by the weakness label in the employee skill vector; efficiency optimization principle: under the premise of meeting quality requirements, employees with the highest predicted production efficiency are preferentially assigned.

[0047] Based on a preset multi-priority principle, similarity calculation and matching degree are performed on the employee skill vector and the process requirement vector, specifically including:

[0048] S501 Admission Validation: Extract the minimum admission threshold corresponding to each atomic operation dimension in the process requirement vector; traverse each dimension of the employee skill vector, and if the employee's score in any dimension is less than the minimum admission threshold of the corresponding dimension, then directly determine that the employee does not match the current process.

[0049] S502 Vector Weighting Processing: For employees who pass the admission verification, the employee skill vector and the process full score standard vector are weighted and transformed using the weight coefficients corresponding to each atomic dimension of the process, respectively, to obtain the weighted employee vector and the weighted process ideal vector.

[0050] S503 Calculate basic similarity: Use the cosine similarity algorithm to calculate the basic similarity between the weighted employee vector and the weighted process ideal vector.

[0051] S504 introduces a multi-level priority correction coefficient: the first correction coefficient is generated based on the rules of maximizing strengths and avoiding weaknesses; the second correction coefficient is generated based on the employee's historical process capacity data; the basic similarity is multiplied by the first correction coefficient and the second correction coefficient in turn to obtain the final similarity.

[0052] S505 generates matching score: converts the final similarity into a percentage matching score and divides the matching level according to a preset threshold.

[0053] For example, employee skill profiles are automatically generated based on employee skill vectors. Vector elements with a score greater than or equal to 4.5 are marked as core strengths, while vector elements with a score less than or equal to 2.5 are marked as weaknesses.

[0054] It should be noted that the scores of 4.5 and 2.5 listed in the above examples are merely illustrative. In actual applications, any appropriate value can be selected as the basis for determining the core strengths and weaknesses labels based on specific application requirements. This application does not impose any restrictions on this.

[0055] Please see Figure 1B , Figure 1B This diagram illustrates factory test data corresponding to the intelligent matching method between employee skills and sewing processes provided in this application embodiment. Figure 1B As can be seen, the matching method provided in this application embodiment has greatly improved matching efficiency: it achieves accurate matching between employee strengths and process requirements, resulting in a 37% increase in output and a 31% increase in quality.

[0056] S16, Based on the matching degree, determine the matching result between the employee and the corresponding sewing process.

[0057] This application provides an intelligent matching method for employee skills and sewing processes. In this method, the concept of atomic-level decomposition is innovatively proposed, which deconstructs complex manual sewing operations into the smallest indivisible and quantifiable units. This breaks the ambiguity of traditional overall quantification and realizes granular and refined management of employee skills and process requirements. Based on atomic decomposition, a one-to-one correspondence between employee skill vectors and process requirement vectors is established.

[0058] Specifically, the atomic dimension set comprises 12 indivisible sewing operation units: (a1) straight trajectory stability, (a2) curve trajectory smoothness, (a3) ​​sharp corner handling accuracy, (a4) speed control stability, (a5) single-point alignment accuracy, (a6) multi-point synchronous alignment, (a7) arc alignment accuracy, (a8) thin material tension control, (a9) thick material penetration ability, (a10) thick-thin transition processing, (a11) asynchronous action coordination, and (a12) dynamic gesture adjustment.

[0059] Process breakdown: The process is broken down into 12 atomic dimensions (may only involve a part of them), such as a1:5, a3:2, a6:4. Employee skills are based on historical production records, and a skill matrix of 12 atomic dimensions is generated to achieve one-to-one correspondence.

[0060] Employee skills conversion: This two-way mapping mechanism transforms the abstract human-job matching into a computable mathematical problem, laying a solid mathematical model foundation for intelligent matching. In response to the limitations of traditional matching methods, a composite priority algorithm of ability access + strength maximization + weakness avoidance + efficiency optimization is proposed. This algorithm not only solves the one-sidedness of single-dimensional quantification, but also maximizes the value of employees while ensuring the bottom line of production through multi-level constraints, realizing the unity of scientific human-job matching and production efficiency.

[0061] like Figure 2 As shown in the figure, this application embodiment provides a flowchart for determining employee skill vectors, such as... Figure 2 As shown, the method for determining employee skill vectors provided in this application embodiment includes the following steps S21 to S24.

[0062] S21, set corresponding quantitative indicators and scoring rules for each of the first atomic-level operation dimensions.

[0063] Specifically, please refer to Table 1 below: Table 1 sets the corresponding quantitative indicators and scoring rules for each first atomic level operation dimension.

[0064]

[0065]

[0066] Please refer to Table 2 below: Table 2 shows the scoring rules for the stability of straight-line trajectories.

[0067] Score grading Maximum vertical offset offline point ratio Judgment Explanation 5 points (optimal) <0.3mm <2% The seam is flush with the baseline line. 4 points (Good) 0.3~0.8mm 2%~5% A minor pin misalignment does not affect the appearance. 3 points (Pass) 0.8~1.5mm 5%~10% Minor deviation, no obvious defects in the finished product. 2 points (poor) 1.5~2.0mm 10%~18% The offset is visible to the naked eye; some products need to be reworked. 1 point (Very poor) ≥2.0mm ≥18% Significant deformation, high risk of mass scrapping

[0068] Please refer to Table 3 below: Table 3 shows the scoring rules for the smoothness of the curve trajectory.

[0069] Score grading Number of inflection points / 100m Average profile deviation Curvature fluctuation coefficient Judgment Explanation 5 points (optimal) 1 <0.3mm <0.08 The curve is smooth and jitter-free, with no geometric defects. 4 points (Good) 1~2 0.3~0.7mm 0.08~0.15 Very few slight inflection points, visually smooth 3 points (Pass) 2~3 0.7~1.2mm 0.15~0.25 Minor curvature fluctuations, no obvious defects in the finished product. 2 points (poor) 3~5 1.2~1.8mm 0.25~0.40 Multiple forming inflection points, fabric wrinkling and curling 1 point (Very poor) >5 >1.8mm >0.40 The curve is shaking violently, and the seam is severely deformed, requiring repair.

[0070] Please refer to Table 4 below: Table 4 shows the scoring rules for the accuracy of sharp corner processing.

[0071] Score grading Angular error Vertex offset Vertex trajectory overlap width Judgment Explanation 5 points <3° <0.4mm <0.2mm The sharp corners are neat and regular, with no extra lines at the apex. 4 points 3°~7° 0.4~0.8mm 0.2~0.5mm Slight angular deviation does not affect the appearance. 3 points 7°~12° 0.8~1.3mm 0.5~1.0mm Minor angle deviation, acceptable and no rework required. 2 points 12°~15° 1.3~1.8mm 1.0~1.6mm The sharp corners were slightly deformed, and some products needed to be reworked and repaired. 1 point >15° >1.8mm >1.6mm The sharp corners are completely deformed, the outline is ruined, and it is unusable.

[0072] It should be noted that the above-mentioned 1-5 point scoring system can be calibrated based on the actual production data of the factory, or a 1-10 point system or a percentage system can be used. This application does not impose any restrictions on this.

[0073] S22 collects multi-source data during the employee's sewing operation.

[0074] In some embodiments, the collection of multi-source data during the employee's sewing operation includes: collecting sewing trajectory coordinates, sewing speed, start and stop times, number of needle breaks, and stitch density from sewing machine sensors; collecting video of the employee's hand movements from a workstation camera to extract the time difference of movements, number of pauses, frequency and amplitude of gesture adjustments during the employee's sewing operation; collecting quality inspection data, including the number of reworks, reasons for reworks, number of scraps, and defect types; and collecting basic employee information, including length of service and historical process records.

[0075] For example, the sewing trajectory coordinate points include the sampling frequency (where the sampling frequency is ≥10Hz).

[0076] For example, in addition to sewing machine sensors and workstation cameras, wearable devices (such as smart bracelets and data gloves) can also be used to collect employee motion data to improve the accuracy of motion data.

[0077] S23, calculate the employee's individual score for each of the first atomic-level operation dimensions based on the multi-source data, the quantitative indicators, and the scoring rules.

[0078] For example, individual scores are calculated based on the average performance of employees' historical data from 300 or 400 or more similar processes, under the constraints of quantitative indicators and scoring rules.

[0079] It should be noted that the values ​​of 300 or 400 listed in the above examples are merely illustrative and will not be elaborated upon further in this application.

[0080] S24. Based on each item score and the item weight corresponding to each item score, obtain the employee skill vector.

[0081] For example, multiplying the individual score and the individual weight yields a vector element of one of the corresponding dimensions of the first atomic-level operation dimension. Combining all vector elements yields the employee skill vector.

[0082] It should be noted that the weight of each item can be adjusted according to the type of products produced by the factory, and this application does not impose any restrictions on this.

[0083] It should be noted that this application is the first to achieve atomic-level quantitative quantification of sewing workers' skills, eliminating subjective judgment errors and greatly improving the accuracy of quantification.

[0084] This application provides a method for determining employee skill vectors. This method, by setting clear quantitative indicators and scoring rules for atomic-level operational dimensions and calculating based on multi-source data, changes the traditional model that relies on the subjective experience of team leaders for scoring. This effectively avoids quantitative biases caused by interpersonal relationships, visual errors, and other factors, ensuring the fairness of the quantitative results and improving employee acceptance of the assessment results. This method not only provides an overall score but also refines it to individual scores for each atomic dimension. This highly granular quantitative approach can accurately pinpoint employees' strengths and weaknesses in specific operational dimensions, providing precise data support for subsequent gap-avoidance matching strategies and targeted skills training. By introducing a weighting mechanism to integrate multiple scores into an employee skill vector, it transforms difficult-to-measure manual skills into computer-processable numerical vectors. This step completes the conversion from physical world behavioral characteristics to digital world mathematical expressions, enabling employee skills to be directly mathematically manipulated with process requirement vectors (such as similarity calculations), laying a core data foundation for subsequent automated and intelligent person-job matching.

[0085] like Figure 3 As shown in the figure, this application provides a flowchart for determining the process capability requirement vector, as follows: Figure 3 As shown, the method for determining the process capability requirement vector provided in this application embodiment includes the following steps S31 to S32.

[0086] S31, set the preset requirement score and weight score required for the corresponding sewing process for each of the second atomic-level operation dimensions.

[0087] For example, the preset required score can be the minimum required score or the maximum required score, and this application does not limit it.

[0088] It should be noted that the preset requirement score and weight score can be reasonably determined based on the specific sewing situation in the actual sewing process application scenario, and this application does not impose any restrictions on this.

[0089] S32, perform a weighted calculation on each of the preset requirement scores and the corresponding weight scores to obtain the process capability requirement vector corresponding to all the second atomic-level operation dimensions.

[0090] For example, each preset requirement score and the corresponding weight score are weighted and calculated to obtain process capability requirement vector elements. All process capability requirement vector elements corresponding to the second atomic level operation dimension are combined to obtain the process capability requirement vector.

[0091] As shown in Table 2, Table 2 is an example of typical process capacity requirements.

[0092] Process Name Straight trajectory stability Curve trajectory smoothness Sharp corner processing precision Multi-point synchronous alignment radian alignment accuracy Thin material tension control Difficulty of process grade Straight side seam of trousers 5 1 1 1 1 2 2.3 C patch pocket sewing 4 3 4 3 2 3 3.2 B Suit collar sewing 2 5 5 5 5 4 4.2 A

[0093] The grades are: D (<2.0 points), C (2.0-3.0 points), B (3.0-4.0 points), and A (≥4.0 points).

[0094] The process difficulty score is calculated as: minimum capability requirement score × weight score.

[0095] This application provides a method for determining process capability requirement vectors. In this method, by setting explicit preset requirement scores for each second atomic-level operation dimension, the process requirements, traditionally relying on verbal descriptions or experience-based judgments, are transformed into precise numerical indicators. This establishes a unified process quantification standard, eliminates the ambiguity of process definitions, and lays a standard foundation for subsequent digital management. The introduction of a weighted scoring mechanism flexibly reflects the differences in importance of different atomic operation dimensions within a specific process. Through weighted calculation, the generated process capability requirement vector accurately highlights the pain points and difficulties of that process. The "process capability requirement vector" generated in this step is mathematically isomorphic to the "employee skill vector" generated in the preceding steps. By abstracting both "person" and "job" into vectors, the system can directly perform quantitative comparisons using mathematical methods such as similarity matching. This transforms the complex person-job matching problem into a programmable and computable mathematical problem, an indispensable prerequisite for achieving intelligent scheduling and precise matching.

[0096] like Figure 4 As shown in the figure, this application embodiment provides a flowchart for determining the matching result between employees and corresponding sewing processes, as follows: Figure 4 As shown, the method for determining the matching result between an employee and the corresponding sewing process provided in this application embodiment includes the following steps S41 to S44.

[0097] S41, if the matching degree is greater than the first matching threshold, then the matching result between the employee and the corresponding sewing process is the first level of matching.

[0098] For example, the first matching threshold can be 90%, 85%, etc., and the first level of matching is a perfect match (the employee's strengths are highly compatible with the process requirements).

[0099] S42, if the matching degree is greater than the second matching threshold and less than or equal to the first matching threshold, then the matching result between the employee and the corresponding sewing process is the second level matching.

[0100] For example, the second matching threshold can be 75%, 70%, etc., and the second level of matching is a good match (employees can complete the process with high quality).

[0101] S43, if the matching degree is greater than the third matching threshold and less than or equal to the preset second matching threshold, then the matching result between the employee and the corresponding sewing process is the third level matching.

[0102] For example, the third matching threshold can be 65%, 60%, etc., and the third level of matching is basic matching (employees can complete the process, but the quality / efficiency is average).

[0103] S44, if the matching degree is less than or equal to the preset third matching threshold, then the matching result between the employee and the corresponding sewing process is a mismatch.

[0104] For example, if the matching degree is less than or equal to the preset third matching threshold, the matching result between the employee and the corresponding sewing process is a mismatch, that is, the employee is not competent for the process.

[0105] This application provides a method for determining the matching result between employees and corresponding sewing processes. In this method, the matching result is divided into four levels: "first-level matching, second-level matching, third-level matching, and no matching" through multiple thresholds such as first, second, and third. This multi-level division can more finely characterize the compatibility between employees and processes, avoiding the blanket judgment of employees with similar abilities as "matched" or "unmatched", and providing richer decision-making information for subsequent production scheduling. Different matching levels correspond to different production strategies, and differentiated production scheduling strategies provide a clear basis for decision-making.

[0106] Managers can develop differentiated production scheduling, training, and incentive strategies based on the results of the rating system, ensuring quality and efficiency while also taking into account employee growth. By adopting a multi-threshold, multi-level mechanism, a buffer zone can be created between strict control and flexible staffing. Managers can flexibly adjust the thresholds according to factors such as the urgency of orders and the overall level of the workforce, thereby achieving a balance between capacity, quality, and personnel development.

[0107] It should be noted that the system output and application module corresponding to this application is also used to output the following results and apply them to production management: individual employee skill profiles and comprehensive skill levels, atomic-level capability requirements and difficulty levels of all processes, employee-process matching degree matrix and optimal allocation scheme, production line scheduling suggestions and production line balancing optimization schemes, personalized employee skill enhancement training plans, and product quality risk warnings based on matching degree.

[0108] It should be noted that the intelligent matching method of employee skills and sewing processes in this application can quickly identify employee potential, avoid underutilizing talent, and provide new employees with a clear skill development path.

[0109] It should be noted that the system can be deployed as a local server system or a cloud service system, supporting collaborative management across multiple factories. The atomic-level disassembly method and matching algorithm of this application can be directly extended to other sewing industries such as bags, footwear, and home textiles, which will not be elaborated upon further in this application.

[0110] The scope of protection for the intelligent matching method of employee skills and sewing process described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0111] This application also provides an intelligent matching device for employee skills and sewing processes. The intelligent matching device for employee skills and sewing processes can implement the intelligent matching method for employee skills and sewing processes described in this application. However, the implementation device for the intelligent matching method for employee skills and sewing processes described in this application includes, but is not limited to, the structure of the intelligent matching device for employee skills and sewing processes listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0112] like Figure 5 As shown, in one embodiment, the intelligent matching device 50 for employee skills and sewing processes of this application includes a first disassembly module 51, an employee skill vector determination module 52, a second disassembly module 53, a process capability requirement vector determination module 54, a matching degree determination module 55, and a matching result determination module 56.

[0113] The first decomposition module 51 is used to decompose sewing skills into multiple first atomic-level operation dimensions, each of which is an indivisible operation capability unit.

[0114] The employee skill vector determination module 52 is used to quantify the multi-source data of the employee sewing operation process based on multiple first atomic-level operation dimensions to obtain the employee skill vector.

[0115] The second decomposition module 53 is used to decompose each sewing process into multiple second atomic-level operational dimensions that are the same as the sewing skill.

[0116] The process capability requirement vector determination module 54 is used to determine the process capability requirement vectors corresponding to multiple second atomic-level operation dimensions.

[0117] The matching degree determination module 55 is used to calculate the similarity between the employee skill vector and the process requirement vector based on a preset multi-priority principle, and determine the matching degree.

[0118] The matching result determination module 56 is used to determine the matching result between the employee and the corresponding sewing process based on the matching degree.

[0119] The structure and principle of the first decomposition module 51, the employee skill vector determination module 52, the second decomposition module 53, the process capability requirement vector determination module 54, the matching degree determination module 55, and the matching result determination module 56 correspond one-to-one with the steps in the above-mentioned intelligent matching method of employee skills and sewing process, so they will not be described in detail here.

[0120] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0121] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0122] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] This application also provides an electronic device. Figure 6 The diagram shown is a structural schematic of an electronic device 60 in one embodiment of this application. The intelligent matching method between employee skills and sewing processes provided in this embodiment can be applied to... Figure 6 The electronic device shown is 60, but it is not limited to this. For example... Figure 6 As shown, the electronic device 60 includes a processor 61, a memory, a system bus 63, and a network interface 65. The memory may include a non-volatile storage medium 62 and internal memory 64.

[0124] The non-volatile storage medium 62 can store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the intelligent matching methods for employee skills and sewing processes provided in the embodiments of this application.

[0125] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0126] The internal memory 64 provides an environment for the execution of a computer program in a non-volatile storage medium. When the computer program is executed by the processor, it enables the processor to execute any of the intelligent matching methods for employee skills and sewing processes provided in the embodiments of this application.

[0127] This network interface 65 is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0128] It should be understood that processor 61 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, the general-purpose processor can be a microprocessor or any conventional processor.

[0129] The electronic device 60 in this application embodiment may include terminal devices such as tablet computers, laptop computers, mobile phones, supercomputers, and smart wearable devices. It can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0130] For example, electronic devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, computers, laptops, handheld communication devices, handheld computing devices, and / or other devices for communicating over wireless systems, as well as next-generation communication systems, such as mobile terminals in 5G networks, mobile terminals in future evolved Public Land Mobile Networks (PLMNs), or mobile terminals in future evolved Non-terrestrial Networks (NTNs).

[0131] This application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which 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 disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

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

[0133] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, 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 each have their own emphasis. For parts of a process or structure that are not described in detail, 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. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for intelligently matching employee skills with sewing processes, characterized in that, The method includes: Sewing skills are broken down into multiple first-atomic-level operational dimensions, each of which is an indivisible operational capability unit. Based on multiple first atomic-level operation dimensions, the multi-source data in the employee sewing operation process is quantified to obtain the employee skill vector; Each sewing process is broken down into multiple second-atomic-level operational dimensions, which are the same as the sewing skill described above; Determine the process capability requirement vectors corresponding to multiple second-level atomic operation dimensions; Based on a preset multi-priority principle, the similarity between the employee skill vector and the process requirement vector is calculated to determine the matching degree. Based on the matching degree, the matching result between the employee and the corresponding sewing process is determined.

2. The method according to claim 1, characterized in that, The process of quantifying multi-source data during employee sewing operations based on multiple first atomic-level operation dimensions to obtain employee skill vectors includes: Set corresponding quantitative indicators and scoring rules for each of the first atomic-level operation dimensions; Collect multi-source data during employee sewing operations; Based on the multi-source data, the quantitative indicators, and the scoring rules, calculate the individual score for each employee in each of the first atomic-level operation dimensions; An employee skill vector is obtained based on each individual score and the corresponding individual weight.

3. The method according to claim 1, characterized in that, The step of determining the process capability requirement vector corresponding to multiple second atomic-level operation dimensions includes: Set the preset requirement score and weight score for each of the second atomic-level operation dimensions to correspond to the sewing process; The preset requirement scores and their corresponding weight scores are weighted and calculated to obtain the process capability requirement vector corresponding to all second atomic-level operation dimensions.

4. The method according to claim 1, characterized in that, The process of determining the matching result between employees and corresponding sewing processes based on the matching degree includes: If the matching degree is greater than the first matching threshold, the matching result between the employee and the corresponding sewing process is a first-level matching. If the matching degree is greater than the second matching threshold and less than or equal to the first matching threshold, then the matching result between the employee and the corresponding sewing process is a second-level matching. If the matching degree is greater than the third matching threshold and less than or equal to the preset second matching threshold, then the matching result between the employee and the corresponding sewing process is a third-level matching. If the matching degree is less than or equal to the preset third matching threshold, then the matching result between the employee and the corresponding sewing process is a mismatch.

5. The method according to claim 1, characterized in that, The preset multi-priority principle includes: Capability Admission Principle: An employee's score in each item of all first atomic-level operational dimensions is greater than or equal to the preset requirement score for the corresponding sewing process; The principle of maximizing strengths: Prioritize assigning employees to the sewing process indicated by the core strength tag in the employee's skill vector; Shortcoming avoidance principle: Avoid assigning employees to sewing processes that are indicated by the shortcoming label in the employee's skill vector; Efficiency Optimization Principle: Under the premise of meeting quality requirements, priority should be given to assigning tasks to employees with the highest predicted production efficiency.

6. The method according to claim 1, characterized in that, The first atomic-level operation dimensions include: straight trajectory stability, curve trajectory smoothness, sharp corner processing accuracy, speed control stability, single-point alignment accuracy, multi-point synchronous alignment, arc alignment accuracy, thin material tension control, thick material penetration capability, thick-thin transition processing, asynchronous action coordination, and dynamic gesture adjustment.

7. The method according to claim 2, characterized in that, The collection of multi-source data during the employee sewing process includes: Data such as sewing trajectory coordinates, sewing speed, start / stop time, number of needle breaks, and stitch density are collected from the sewing machine's sensors. Videos of employees' hand movements are captured from workstation cameras to extract the time difference of movements, number of pauses, frequency and amplitude of hand gesture adjustments during the sewing process; Collect quality inspection data, including the number of reworks, reasons for reworks, number of scraps, and defect types; Collect basic employee information, including length of service and historical work process records.

8. An intelligent matching device for employee skills and sewing processes, characterized in that, The device includes: The first decomposition module is used to decompose sewing skills into multiple first atomic-level operation dimensions, each of which is an indivisible operation capability unit. The employee skill vector determination module is used to quantify multi-source data in the employee sewing operation process based on multiple first atomic-level operation dimensions to obtain the employee skill vector. The second decomposition module is used to decompose each sewing process into multiple second atomic-level operational dimensions that are the same as the sewing skill. The process capability requirement vector determination module is used to determine the process capability requirement vectors corresponding to multiple second atomic-level operation dimensions. The matching degree determination module is used to calculate the similarity between the employee skill vector and the process requirement vector based on a preset multi-priority principle, and determine the matching degree. The matching result determination module is used to determine the matching result between the employee and the corresponding sewing process based on the matching degree.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes: A memory that stores a computer program; The processor, which is communicatively connected to the memory, executes the method of any one of claims 1 to 7 when the computer program is invoked.

Images