Performance prism based customized training plan generation method for operation and maintenance personnel

Abstract

The application discloses a kind of customized training plan generation methods for operation and maintenance personnel based on performance prism, which comprises the following steps: collecting multi-source heterogeneous demand data of operation and maintenance personnel on multiple platforms, and combining Carnot model and importance performance analysis model for fusion processing, extracting key technology theme through cluster analysis, drawing core training intention and decomposing into key measurement indicators, collecting employee daily operation and maintenance behavior data and calculating ability membership degree vector, combining post demand information, calculating target ability information to be enhanced, generating training content using intelligent workflow engine according to target ability information and key measurement indicators, generating hybrid training plan combining online and offline according to employee historical schedule, issuing the plan to terminal and setting task reminders, which can ensure that training is executed on time, improve training coverage and completion rate, and realize the intelligentization, customization and high efficiency of operation and maintenance personnel training from demand analysis, capability assessment, content generation to plan execution.

Description

Technical Field

[0001] This invention relates to the fields of intelligent manufacturing and human resource management technology, and in particular to a method for generating customized training plans for operation and maintenance personnel based on performance prisms. Background Technology

[0002] As manufacturing production lines transform towards digitalization and intelligence, these lines deeply integrate technologies such as machinery, industrial IoT, machine vision, data platforms, and artificial intelligence. The objects of maintenance are evolving into complex cyber-physical systems, and faults are becoming more hidden and complex. This places demands on maintenance personnel to possess composite skills spanning mechanics, electrical engineering, software, networking, and data analysis. Highly skilled maintenance personnel have become a key support for digital transformation.

[0003] Currently, the training of relevant talents mainly adopts three types of technical solutions: first, online training and knowledge base platforms based on learning management systems to realize course on-demand, progress tracking and examination management; second, immersive skills training systems based on virtual reality or augmented reality to provide highly simulated operation training and real-world guidance; and third, personalized course recommendation systems based on big data and learning analysis to achieve content recommendation through learning behavior data. All of the above solutions use digital means to improve the convenience and experience of training.

[0004] However, in existing solutions, the course content of learning management systems is difficult to connect with the needs of the production site, the mode is one-way and rigid, the evaluation system is one-sided and lacks incentive mechanisms; training systems based on virtual reality or augmented reality only focus on operational proficiency, which cannot form a closed loop with real production performance, and the content iteration cost is high and the response is slow; personalized recommendation systems are limited to the learning interaction layer, the recommendation logic is superficial, and they are isolated from production management and performance systems. Ultimately, the traditional training system is unable to meet the needs of digital production lines for precise, efficient, sustainable, and quantifiable training results for multi-skilled operation and maintenance personnel. Summary of the Invention

[0005] This invention provides a method for generating customized training plans for operations and maintenance personnel based on performance prisms, in order to solve the problems of low accuracy, low efficiency, low sustainability, and unquantifiable training results for operations and maintenance personnel.

[0006] According to one aspect of the present invention, a method for generating customized training plans for operations and maintenance personnel based on a performance prism is provided, comprising: Multi-source heterogeneous requirement data for operations and maintenance personnel is collected from multiple information platforms. The multi-source heterogeneous requirement data is then fused and processed using the Kano model and the importance performance analysis model to generate a standardized requirement list. Key technology themes were extracted from the standardized requirements list through cluster analysis, core training intentions were drawn based on the key technology themes, and the core training intentions were decomposed into multiple key metrics. Collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, and obtain the capability membership vector of the target employees based on the multi-source behavioral data. Based on the capability membership vector and the job requirements information of the target position, the target capability information that the target employee needs to enhance when undertaking the tasks of the target position is calculated. Based on the target capability information and key performance indicators, the intelligent workflow engine generates target training content that matches the target employees. Based on the target employees' historical schedule information and target training content, a hybrid target training plan is generated that matches the target employees. The target training plan contains multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline. The hybrid target training plan is distributed to the terminal devices held by the target employees, and matching task reminders are set on the terminal devices according to the target training plan.

[0007] According to another aspect of the present invention, a device for generating customized training plans for operations and maintenance personnel based on a performance prism is provided, comprising: The data fusion module is used to collect multi-source heterogeneous requirement data for operation and maintenance personnel from multiple information platforms, and to fuse the multi-source heterogeneous requirement data through the Kano model and the importance performance analysis model to generate a standardized requirement list. The intent decomposition module is used to extract key technical topics from the standardized requirements list through cluster analysis, draw core training intents based on key technical topics, and decompose the core training intents into multiple key metrics. The membership vector module is used to collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, and to obtain the capability membership vector of the target employees based on the multi-source behavioral data. The capability information module is used to calculate the target capability information that the target employee needs to enhance when undertaking the target job task, based on the capability membership vector and the job requirement information of the target position. The training content module is used to generate target training content that matches the target employees based on the target capability information and key performance indicators through an intelligent workflow engine. The training plan module is used to generate a hybrid target training plan that matches the target employees based on their historical schedule information and target training content. The target training plan contains multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline. The plan distribution module is used to distribute the hybrid target training plan to the terminal devices held by the target employees, and set matching task reminders on the terminal devices according to the target training plan.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the performance prism-based customized training plan generation method for operations and maintenance personnel as described in any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the method for generating customized training plans for operation and maintenance personnel based on performance prisms as described in any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the method as described in any embodiment of the present invention.

[0011] The technical solution of this invention collects multi-source heterogeneous demand data from operations and maintenance personnel across multiple platforms, and integrates it with the Kano model and importance performance analysis model for fusion processing. This enables the accurate extraction of real training needs and the formation of a standardized demand list, avoiding a disconnect between training and actual needs. Furthermore, cluster analysis extracts key technical themes, maps core training intentions, and decomposes them into key performance indicators, making training objectives clearer, more quantifiable, and more implementable. Collecting daily operations and maintenance behavior data from employees and calculating capability membership vectors, combined with job requirement information, calculates the target capability information that needs to be enhanced, enabling an objective and comprehensive identification of employee skill enhancement needs. The system targets and improves the accuracy of assessments by replacing subjective evaluations with target competency information and key performance indicators. Based on this information and key metrics, a smart workflow engine generates matching training content, enabling personalized and dynamic optimization of training materials and improving training efficiency. Furthermore, by integrating employee historical schedules, a blended online and offline training plan is generated, adapting to employee work rhythms and enhancing training sustainability. Distributing the plan to terminals and setting task reminders ensures timely training execution, improves training coverage and completion rates, and achieves intelligent, customized, and efficient end-to-end training for operations and maintenance personnel, from needs analysis and competency assessment to content generation and plan execution.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of a method for generating customized training plans for operations and maintenance personnel based on a performance prism, according to Embodiment 1 of the present invention. Figure 2 This is a flowchart of another method for generating customized training plans for operation and maintenance personnel based on performance prisms according to Embodiment 2 of the present invention; Figure 3 This is a flowchart of another method for generating customized training plans for operation and maintenance personnel based on performance prisms, according to Embodiment 3 of the present invention. Figure 4 This is a schematic diagram of a device for generating customized training plans for operation and maintenance personnel based on a performance prism, according to Embodiment 4 of the present invention. Figure 5 This is a schematic diagram of the structure of an electronic device that implements the method for generating customized training plans for maintenance personnel based on performance prisms, as described in this embodiment of the invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] Example 1 Figure 1 This is a flowchart of a method for generating customized training plans for operations and maintenance personnel based on performance prisms, provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of generating customized training plans for operations and maintenance personnel. The method can be executed by a device for generating customized training plans for operations and maintenance personnel based on performance prisms. This device can be implemented in hardware and / or software and is generally configured in electronic devices.

[0018] In this embodiment of the invention, the performance prism can be specifically understood as: a comprehensive performance management framework. It takes the diverse needs of implementing entities such as enterprises (pursuing industrial development and financial value), workshops (pursuing production stability and efficiency), work teams (pursuing production stability and efficiency), and employees (pursuing personal growth and rewards) as its starting point. It ensures that training accurately aligns with the business needs of production line operation and maintenance, optimizes the entire process from needs assessment and capability evaluation to training plan generation and incentive fulfillment, and conducts systematic training around dimensions such as mechanical structure and transmission operation and maintenance capabilities, electrical control and system debugging capabilities, industrial software and program application capabilities, industrial network and equipment interconnection and communication capabilities, and production data collection, analysis, and fault discovery capabilities required for intelligent production line operation and maintenance. Through an incentive mechanism based on points, it motivates all parties to participate in training, achieving a deep integration of talent cultivation with business development and the needs of all parties, thereby constructing a systematic and closed-loop operation and maintenance talent training system.

[0019] like Figure 1 As shown, the method includes: S110. Collect multi-source heterogeneous requirement data for operation and maintenance personnel from multiple information platforms, and use the Kano model and importance performance analysis model to fuse and process the multi-source heterogeneous requirement data to generate a standardized requirement list.

[0020] In this embodiment of the invention, multiple information platforms can be specifically understood as various business systems supporting production, operation and maintenance, inspection, and learning activities, such as manufacturing execution systems, mobile inspection applications, and learning management platforms. Multi-source heterogeneous requirement data can be specifically understood as data related to the skills, training, and positions of operation and maintenance personnel, which comes from different sources, has different structures, and is of different types, including structured data and unstructured text-based requirements.

[0021] The Kano model can be understood as an analytical model used to classify needs and assign type weights, distinguishing the importance and value attributes of needs. The importance-performance analysis model can be understood as a model that assesses the importance and satisfaction of needs, divides them into quadrants, and determines quadrant weights to achieve need prioritization analysis. A standardized needs list can be understood as a standardized needs document that has been uniformly quantified and prioritized, and can be directly used for subsequent training planning.

[0022] Specifically, as part of the demand identification process, multi-source heterogeneous demand data related to operations and maintenance personnel is collected from various information platforms. For example, multi-source heterogeneous demand data corresponding to four types of implementing entities—enterprises, workshops, work teams, and employees—is collected. The Kano model is used to classify each demand and determine its type weight. Simultaneously, the Importance Performance Analysis (IPA) model is used to assess the importance and satisfaction of demands and determine quadrant weights. The results of both models are then combined to calculate a comprehensive priority index. For example, the classification results and satisfaction scores of each demand can be obtained through questionnaires, on-site surveys, etc. The Kano model is used to classify demands into basic, expected, and exciting categories, assigning corresponding preset weights to each. Simultaneously, based on the Importance Performance Analysis model, the same demand is scored for importance and current performance, categorized into different quadrants such as key improvement and maintenance, and assigned quadrant weights. The type weights and quadrant weights are then weighted and summed to obtain a comprehensive priority index representing the urgency of the demand. Demands are then ranked according to this index, ultimately forming a standardized demand list.

[0023] It can also generate dynamic feedback by collecting information such as new problems on the production site, employee skill feedback, and changes in equipment operation and maintenance data in real time, and add, remove or update the weight of the requirement items according to the preset cycle, so as to achieve continuous iterative optimization of the requirement list, thereby generating a standardized requirement list that can accurately reflect the actual needs of all parties and can be dynamically updated, thus establishing a clear implementation basis and guidance for subsequent training intent construction, capability assessment and training plan generation.

[0024] Optionally, based on the above embodiments, collecting multi-source heterogeneous demand data for operations and maintenance personnel from multiple information platforms may include: Structured data such as overall equipment efficiency, failure rate, and maintenance man-hours are obtained from the Manufacturing Execution System via the Application Programming Interface (API); production meeting minutes are parsed using optical character recognition (OCR) and natural language processing (NLP) algorithms to extract problem-related requirements; team skill assistance requests are obtained from the mobile inspection application; employee course search volume, completion rate, and course rating data are exported from the learning management platform; and the above data are integrated with the requirements to form multi-source heterogeneous requirement data.

[0025] Specifically, structured data such as overall equipment efficiency, failure rate, and maintenance hours are obtained from the Manufacturing Execution System via the application programming interface (API). Optical character recognition (OCR) and natural language processing (NLP) algorithms are used to parse production meeting minutes to extract problem-related requirements. Unstructured texts such as corporate development plans and team performance dashboards can also be analyzed for entity recognition and sentiment analysis to extract key requirements. For example, redundant information is removed through text extraction and preprocessing, and named entity recognition algorithms are used to locate core entities such as skill gaps, equipment problems, training expectations, and capacity bottlenecks. Sentiment analysis is combined to distinguish the urgency and intensity of attention of the requirements, thereby extracting key requirements related to skills improvement and training.

[0026] The process involves collecting survey data for the Kano model and importance-performance analysis model through a questionnaire system, obtaining work order-type requests for team skills assistance from mobile inspection applications, and exporting course-related data such as employee course search volume, completion rate, and course rating data from the learning management platform. These diverse data and requests from various sources and in different formats are then cleaned, normalized, and integrated to form multi-source heterogeneous requirement data for subsequent analysis. For example, data cleaning operations such as deduplication, error correction, and missing item completion are performed on equipment operation data, text requests, work order information, and learning behavior data. Data formats, units, and labeling rules are then standardized to achieve normalization and regularization. Finally, the data is matched and aggregated according to training requirement themes to form multi-source heterogeneous requirement data with a unified structure, complete sources, and direct applicability to model analysis.

[0027] By collecting structured equipment data, text-based problem requirements, team skill requirements, and employee learning behavior data from multiple information platforms such as the Manufacturing Execution System, production meeting minutes, mobile inspection applications, and learning management platforms, and integrating and processing this multi-source heterogeneous information, we can comprehensively cover the current status of equipment operation, actual on-site problems, team skill gaps, and employee learning preferences. This achieves diversification and three-dimensionality of training needs sources, avoiding the one-sidedness and subjectivity brought about by a single data source, and laying a data foundation for subsequent accurate needs analysis and standardized list construction.

[0028] Optionally, based on the above embodiments, the multi-source heterogeneous demand data can be fused using the Carnot model and the importance performance analysis model to generate a standardized demand list, which may include: The Karnaugh model is used to classify various types of heterogeneous demand data and determine the corresponding type weights. The importance and satisfaction of each type of heterogeneous demand data are evaluated, and an importance performance analysis matrix is ​​drawn based on the evaluation results. The quadrant weights corresponding to the importance performance analysis matrix are determined. Based on the types and type weights classified by the Karnaugh model, the quadrant weights corresponding to the importance performance analysis matrix, and the evaluation results, the comprehensive priority index of each type of heterogeneous demand data is calculated. The various types of heterogeneous demand data are prioritized according to the comprehensive priority index to generate a standardized demand list.

[0029] In this embodiment of the invention, the comprehensive priority index can be specifically understood as: multiplying the type weight, quadrant weight, and importance score to obtain a quantitative priority value.

[0030] Specifically, the Kano model is used to determine the type of various heterogeneous demands from multiple sources and to assign corresponding type weights. For example, through the Kano questionnaire survey, various demands are divided into basic, expected, exciting, indifferent, and reverse types, and corresponding weights are assigned to each category.

[0031] At the same time, importance and satisfaction assessments are conducted for each requirement, and an importance performance analysis matrix is ​​constructed based on the results to determine quadrant weights. For example, importance and satisfaction scores are conducted for each requirement, and an IPA quadrant diagram is drawn accordingly, which is divided into quadrants such as key improvement, continue to maintain, low priority and possible over-emphasis, and corresponding weights are set for each.

[0032] The comprehensive priority index for each requirement is calculated by combining the Kano type weight, IPA quadrant weight, and importance score. Finally, the requirements are sorted in descending order according to the calculated comprehensive priority index to form a standardized requirement list that can directly support the subsequent decomposition of training intentions and capability assessment.

[0033] In a specific example, for each requirement, determine its Kano model category and corresponding category weight W. K IPA quadrant assignment and corresponding quadrant weight W IPA And obtain the importance score for this requirement. i Then substitute the above three parameters into the comprehensive priority index model P. i =W K (Category i )×W IPA (Quadrant i Importance i Perform a series of multiplication operations.

[0034] Typically, the Carnot category weights can be set as follows: basic requirement W K(Category1) = 0.4, expected demand W K (Category2) = 0.3, Excitement-type demand W K (Category3) = 0.2, undifferentiated demand W K (Category4) = 0.1, reverse demand W K (Category5) = -0.5.

[0035] The IPA quadrant weights can be set as follows: Weight W for the key improvement quadrant. IPA (Quadrant1)=1.0, continue to maintain quadrant weight W IPA (Quadrant2) = 0.7, weight W of the lower priority quadrant IPA (Quadrant3) = 0.3, possibly indicating excessive quadrant weighting W. IPA (Quadrant4) = 0.5.

[0036] The comprehensive priority index value of each requirement is calculated one by one, and this value is used as a quantitative basis for prioritizing requirements.

[0037] By combining the Kano model to categorize and assign weights to requirements, and using an importance performance analysis model to assess the importance and satisfaction of requirements and determine quadrant weights, and then integrating the two weights with the importance score to calculate a comprehensive priority index, we can achieve quantitative analysis and scientific ranking of multi-source heterogeneous requirements. This avoids the arbitrariness and bias caused by relying on subjective experience to determine the priority of requirements, making the generated standardized requirement list more in line with actual production and skills improvement needs. It provides an objective and reliable basis for subsequent training goal setting and training content planning, and effectively improves the standardization and accuracy of training requirements analysis.

[0038] S120. Extract key technology themes from the standardized requirements list through cluster analysis, draw core training intentions based on key technology themes, and decompose the core training intentions into multiple key metrics.

[0039] In this embodiment of the invention, the key technology theme can be specifically understood as: core technology areas extracted through clustering that represent the overall training needs, such as equipment fault management and data operation and maintenance capability improvement. The core training intent can be specifically understood as: the overall training objectives and development direction formed based on the key technology theme, clearly defining the core problems to be solved and the goals to be achieved through training. Key measurement indicators can be specifically understood as: quantifying the training intent into measurable and assessable indicators used to measure training effectiveness.

[0040] Specifically, cluster analysis is used to summarize and aggregate various requirements in the standardized requirements list, extracting representative key technology themes. Then, the overall core training intent is outlined and drawn up around these key technology themes. For example, based on the key technology themes obtained from cluster analysis, text association mining, theme weight calculation, and technology path association algorithms are used to automatically match and logically aggregate the scattered technical requirements with equipment operation and maintenance scenarios, job competency requirements, and production business objectives. This constructs the causal relationships and hierarchical structure between various technical themes, forming an overall training objective system for improving the capabilities of digital intelligent production line operation and maintenance personnel. This generates a structured and communicable overall core training intent.

[0041] In a specific example, a training implementation framework with multi-level logical connections and a focus on training value output is constructed. This framework takes quantifiable benefits such as improved overall equipment efficiency and reduced operation and maintenance costs as its top-level objectives. It uses the needs of enterprise production and operation, the practical demands of work teams, and the expectations of employee skill development as the intermediary. It uses the entire process, including needs assessment, capability evaluation, training execution, and effect feedback, as the process guarantee. It is based on the improvement of multi-dimensional composite skills such as mechanical, electrical, software, network, and data skills. According to the hierarchical correspondence, the training objectives are broken down into key performance indicators that are quantifiable, verifiable, and traceable, such as the improvement rate of equipment operation and maintenance indicators, the rate of filling skill gaps, the completion rate of training tasks, and the extent of employee capability improvement. This makes the training strategy clear, systematic, and measurable.

[0042] The macro-level training intentions are broken down layer by layer into multiple quantifiable, traceable, and assessable key metrics, realizing the decoding process from needs analysis to the clarification and quantification of training objectives.

[0043] S130. Collect multi-source behavioral data of the target employee in daily operation and maintenance work within a set period, and obtain the capability membership vector of the target employee based on the multi-source behavioral data.

[0044] In this embodiment of the invention, multi-source behavioral data can be specifically understood as: daily operation and maintenance records, fault handling time, work order completion quality, equipment parameter adjustment records, anomaly handling cases, and learning records, etc., which are objective process data. The capability membership vector can be specifically understood as: a quantitative expression vector of an employee's various capability levels obtained through fuzzy comprehensive evaluation.

[0045] S140. Based on the capability membership vector and the job requirements information of the target position, calculate the target capability information that the target employee needs to enhance when undertaking the target position task.

[0046] In this embodiment of the invention, job requirement information can be specifically understood as: the capability standards and threshold requirements for the target position in dimensions such as mechanics, electrical engineering, software, networking, and data. Target capability information can be specifically understood as: the capability gaps and areas for improvement that exist between the employee and the job requirements, obtained after capability quantification.

[0047] Specifically, multi-source behavioral data generated by target employees in their daily operations are collected within a set period. After normalization and index mapping of this data, the ability membership vector representing the employee's various ability levels is calculated through the evaluation model. Then, the vector is compared and the difference is calculated item by item with the preset target job ability requirements information to determine the specific target ability information that the target employee needs to strengthen and improve in order to be competent in the job tasks.

[0048] In a specific example, as a capability quantification step, an evaluation model covering dimensions such as value creation, task implementation, process optimization, technology application, and learning innovation is pre-constructed. The entropy weight method can be used to objectively assign weights to each dimension and lower-level indicators to replace subjective judgment. Within a set period, multi-source behavioral data such as operation logs, fault handling records, work order execution data, and skills assessment results of target employees are collected. The gray comprehensive evaluation method can be used to quantify, fuse, and map the multi-source data to obtain a dynamically updated multi-dimensional capability membership vector. Then, based on the capability membership vector and the job requirements information of the target position, the target capability information that the target employee needs to enhance when undertaking the target job tasks is calculated, forming a quantitative capability profile that can intuitively reflect the employee's capability level.

[0049] S150. Based on the target capability information and key performance indicators, generate target training content that matches the target employees through the intelligent workflow engine.

[0050] In this embodiment of the invention, the intelligent workflow engine can be specifically understood as: a process automation processing module built based on a rule engine and task orchestration algorithm. By loading preset capability matching rules, training resource library mapping relationships, time-series scheduling logic and constraints, it realizes the fully automated execution of the entire process from requirement input to task generation, resource allocation, and plan orchestration. It can dynamically call corresponding algorithms to complete content matching and plan generation based on input data. For example, it can dynamically call collaborative filtering algorithms, text similarity algorithms, genetic algorithms, or constraint satisfaction problem solving algorithms based on input data. It performs feature matching for capability shortcomings and training content, and optimizes the scheduling of training periods and resource conflicts, thereby automatically completing the intelligent generation of personalized training content recommendations and hybrid training plans, and outputting standardized and personalized execution solutions without manual intervention.

[0051] S160. Based on the target employees' historical schedule information and target training content, generate a hybrid target training plan that matches the target employees.

[0052] The target training plan includes multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline.

[0053] In this embodiment of the invention, the hybrid target training plan can be specifically understood as: a personalized training arrangement that integrates online learning resources with offline practical training and adapts to employees' individual schedules. A training item can be specifically understood as: the smallest execution unit that includes specific training time, training content, and whether it is online or offline.

[0054] S170. Distribute the hybrid target training plan to the terminal devices held by the target employees, and set matching task reminders on the terminal devices according to the target training plan.

[0055] In this embodiment of the invention, the task reminder can be specifically understood as: an execution prompt sent to the employee's terminal and automatically triggered according to the training plan.

[0056] Specifically, based on the target employee's information on skills to be improved (i.e., target skills information) and established key performance indicators, a smart workflow engine is used to generate personalized training content that is suitable for the employee. For example, the smart workflow engine breaks down the employee's information on skills to be improved and key performance indicators into fine-grained skills tags, performs similarity matching in the training resource library through content retrieval algorithms, and then filters out courses, practical projects and training tasks that correspond to skills gaps and indicator requirements based on a rule engine. At the same time, the depth of content and training intensity are automatically configured according to the degree of skills gaps, and finally a set of personalized training content that is highly adapted to the employee's skills improvement path is generated.

[0057] By combining employees' historical schedule information with the aforementioned training content, a hybrid target training plan containing multiple training items is planned and generated. For example, an intelligent workflow engine can be used to read employees' historical schedule data on free time periods, work task distribution, and time preferences. A time-series planning algorithm is then used to break down and arrange the generated personalized training content, assigning each item to a corresponding free time period and marking it as online or offline training. At the same time, constraints are applied to optimize the training duration, sequence, and interval, forming a hybrid target training plan consisting of multiple training items that include training time, single content, and training type.

[0058] The training plan was distributed to the terminal devices of employees, and corresponding task reminders were set on the terminals according to the planned schedule to ensure that the training tasks were carried out in sequence.

[0059] The technical solution of this invention collects multi-source heterogeneous demand data from operations and maintenance personnel across multiple platforms, and integrates it with the Kano model and importance performance analysis model for fusion processing. This enables the accurate extraction of real training needs and the formation of a standardized demand list, avoiding a disconnect between training and actual needs. Furthermore, cluster analysis extracts key technical themes, maps core training intentions, and decomposes them into key performance indicators, making training objectives clearer, more quantifiable, and more implementable. Collecting daily operations and maintenance behavior data from employees and calculating capability membership vectors, combined with job requirement information, calculates the target capability information that needs to be enhanced, enabling an objective and comprehensive identification of employee skill enhancement needs. The system targets and improves the accuracy of assessments by replacing subjective evaluations with target competency information and key performance indicators. Based on this information and key metrics, a smart workflow engine generates matching training content, enabling personalized and dynamic optimization of training materials and improving training efficiency. Furthermore, by integrating employee historical schedules, a blended online and offline training plan is generated, adapting to employee work rhythms and enhancing training sustainability. Distributing the plan to terminals and setting task reminders ensures timely training execution, improves training coverage and completion rates, and achieves intelligent, customized, and efficient end-to-end training for operations and maintenance personnel, from needs analysis and competency assessment to content generation and plan execution.

[0060] Example 2 Figure 2 This is a flowchart of another method for generating customized training plans for operations and maintenance personnel based on performance prisms, provided in Embodiment 2 of the present invention. This embodiment is a refinement of the step "obtaining the capability membership vector of the target employee based on the multi-source behavioral data" in the above embodiment. Figure 2 As shown, the method includes: S210. Collect multi-source heterogeneous requirement data for operation and maintenance personnel from multiple information platforms, and integrate the multi-source heterogeneous requirement data through the Kano model and the importance performance analysis model to generate a standardized requirement list.

[0061] S220. Extract key technology themes from the standardized requirements list through cluster analysis, draw core training intentions based on key technology themes, and decompose the core training intentions into multiple key metrics.

[0062] S230. Collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, normalize the multi-source behavioral data, and map it to the membership level of the corresponding capability indicators in the pre-built capability assessment model.

[0063] In this embodiment of the invention, the capability assessment model can be specifically understood as a pre-constructed quantitative evaluation system containing multiple capability dimensions and sub-indicators. The membership level can be specifically understood as mapping standardized data to the degree of membership corresponding to a fuzzy evaluation citation set (such as excellent, good, satisfactory, and needing improvement).

[0064] S240. Based on the membership level, perform fuzzy comprehensive evaluation calculation layer by layer to obtain the capability membership vector corresponding to the target employee.

[0065] In this embodiment of the invention, the fuzzy comprehensive evaluation calculation can be understood as follows: based on fuzzy mathematics theory, combined with index weights and membership matrices, the overall capability evaluation result is obtained by synthesizing layer by layer.

[0066] Specifically, the collected multi-source behavioral data of target employees is normalized to unify data of different types and scales into a comparable standard value range. Then, the processed data is mapped one by one to the membership level of each corresponding capability indicator in the pre-constructed capability assessment model to construct a basic fuzzy evaluation matrix. Based on the set indicator weights, the fuzzy comprehensive evaluation method is used to carry out layer-by-layer calculation and synthesis. For example, the membership degree of each capability sub-indicator obtained after normalization is weighted and summed with the set indicator weights to complete the layer-by-layer synthesis calculation of fuzzy comprehensive evaluation.

[0067] The final output is a capability membership vector that comprehensively represents the capability levels of the target employees across all dimensions.

[0068] In a specific example, a quantitative evaluation is implemented based on a five-dimensional capability model encompassing value creation, task implementation, process optimization, technology application, and learning and innovation. The weight vectors of each dimension and its sub-indicators are determined through expert scoring and the Analytic Hierarchy Process (AHP). The sub-indicators of the five-dimensional capability model can be: Value creation capability includes troubleshooting efficiency, the value of improvement proposals, and cost-saving contributions; Task implementation capability includes the completion rate of related tasks and the degree of promotion and application of new technologies; Process optimization capability includes the number of Standard Operating Procedure (SOP) optimization suggestions and the cross-process collaborative problem-solving rate; Technology application capability includes proficiency in operating multi-device systems, the level of data analysis tool usage, and the ability to apply predictive algorithms; Learning and innovation capability includes the speed of acquiring new knowledge, the degree of knowledge sharing, and the number of creative solutions.

[0069] Within a set period, multi-dimensional practical and learning evaluation data are collected, including average fault repair time, SOP compliance, equipment debugging proficiency, and new technology learning hours. This data is standardized and mapped to a set of comments (excellent, good, satisfactory, and needing improvement) to construct a fuzzy evaluation matrix. In addition to using the classic fuzzy synthesis operator, a weighted average operator can be selected to improve evaluation accuracy. The fuzzy comprehensive evaluation model is used to calculate the capability membership vector, which is then converted into a percentage score and a dynamic capability profile in radar chart form is generated. At the same time, the capability gap vector is determined by the difference calculation with the target position capability standard vector. In addition to direct numerical comparison, gap clustering algorithms can be combined to automatically identify capability shortcomings, thereby accurately locating the direction of employee capability improvement.

[0070] S250. Based on the capability membership vector and the job requirements information of the target position, calculate the target capability information that the target employee needs to enhance when undertaking the target position task.

[0071] S260. Based on the target capability information and key performance indicators, generate target training content that matches the target employees through the intelligent workflow engine.

[0072] S270. Generate a hybrid target training plan that matches the target employees based on their historical schedule information and target training content.

[0073] The target training plan includes multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline.

[0074] S280. Distribute the hybrid target training plan to the terminal devices held by the target employees, and set matching task reminders on the terminal devices according to the target training plan.

[0075] The technical solution of this invention collects multi-source heterogeneous demand data from maintenance personnel across multiple platforms and integrates it with the Kano model and importance performance analysis model. This allows for the accurate extraction of real training needs and the formation of a standardized demand list, preventing training from becoming disconnected from actual needs. Furthermore, cluster analysis extracts key technical themes, maps core training intentions, and decomposes them into key performance indicators, making training objectives clearer, more quantifiable, and more implementable. By collecting daily maintenance behavior data from employees and normalizing the multi-source behavior data of target employees, mapping it to the membership level of corresponding capability indicators in a pre-built capability assessment model, and then performing fuzzy comprehensive evaluation calculations layer by layer based on these membership levels to obtain capability membership vectors, a data-driven and objective quantitative assessment of employee capabilities can be achieved. This avoids bias and one-sidedness caused by subjective human judgment. Simultaneously, relying on standardized models and calculation logic improves the consistency and reliability of capability evaluation results, providing data support for the subsequent accurate identification of employee capability gaps. Based on capability membership vectors and job requirements for target positions, the system calculates the enhanced target capabilities required for employees to perform tasks in those positions. Using this target capability information and key performance indicators, a smart workflow engine generates matching training content, enabling personalized and dynamic optimization of training content and improving training efficiency. Furthermore, by integrating employee historical schedules, a hybrid online and offline training plan is generated, adapting to employee work rhythms and enhancing training sustainability. Distributing the plan to terminals and setting task reminders ensures timely training execution, improves training coverage and completion rates, and achieves intelligent, customized, and efficient end-to-end training for operations and maintenance personnel, from needs analysis, capability assessment, content generation to plan execution.

[0076] Example 3 Figure 3 This is a flowchart illustrating another method for generating customized training plans for operations and maintenance personnel based on a performance prism, as provided in Embodiment 3 of the present invention. This embodiment is a refinement of the step described in the above embodiment: "Generating target training content matching the target employees through an intelligent workflow engine based on the target capability information and key performance indicators." Figure 3 As shown, the method includes: S310. Collect multi-source heterogeneous requirement data for operation and maintenance personnel from multiple information platforms, and use the Kano model and importance performance analysis model to fuse and process the multi-source heterogeneous requirement data to generate a standardized requirement list.

[0077] S320. Extract key technology themes from the standardized requirements list through cluster analysis, draw core training intentions based on key technology themes, and decompose the core training intentions into multiple key metrics.

[0078] S330. Collect multi-source behavioral data of the target employee in daily operation and maintenance work within a set period, and obtain the target employee's capability membership vector based on the multi-source behavioral data.

[0079] S340. Based on the capability membership vector and the job requirements information of the target position, calculate the target capability information that the target employee needs to enhance when undertaking the target position task.

[0080] S350. Based on the target capability information and key performance indicators, the training process parameters are dynamically adjusted using an intelligent workflow engine based on reinforcement learning algorithms to generate target training content that matches the target employees.

[0081] In this embodiment of the invention, the reinforcement learning algorithm can be specifically understood as a machine learning method that autonomously optimizes decision-making strategies with the goal of maximizing rewards through interaction between the agent and the environment and iterative trial and error. The training process parameters can be specifically understood as adjustable variables including the ratio of theoretical to practical learning hours, the order of teaching content, task difficulty, resource allocation methods, and training models. The target training content can be specifically understood as a combination of training resources such as courses, practical projects, and training tasks that are personalized to address employees' skill gaps.

[0082] Specifically, the system takes the target employee's skill gap information (i.e. target skill information) and the established key performance indicators as inputs, and relies on an intelligent workflow engine with built-in reinforcement learning algorithms to dynamically adjust process parameters such as training content combination, learning time allocation, and task difficulty in real time. Through continuous learning and feedback on the training process, the matching strategy is continuously optimized, and finally personalized target training content that is adapted to the employee's skill improvement needs is generated.

[0083] In a specific example, using target capability information and multi-dimensional key metrics as input, the optimization unit of the intelligent workflow engine is used as a reinforcement learning agent. The state space is constructed by combining the employee's five-dimensional capability score, learning behavior sequence, training resource usage, and production equipment status. The action space is defined by process decisions such as adjusting the ratio of theoretical to practical learning hours, optimizing the content learning order, and configuring the difficulty of practical tasks. Iterative learning is carried out using a reward function that is a weighted combination of the employee's overall capability improvement value and the business performance improvement values ​​such as the improvement of overall equipment effectiveness (OEE) and the reduction of mean time to repair (MTTR). For example, the reward function R can be designed as R = αΔCapability + βΔPerformance, where α and β are weight coefficients, ΔCapability is the capability improvement value, and ΔPerformance is the associated business performance improvement value.

[0084] The intelligent agent continuously updates the policy network through offline simulation of historical logs or online pilot interaction. In addition to using conventional value iterative optimization, it can also combine deep Q-networks to improve decision-making accuracy in complex states, thereby dynamically optimizing training process parameters and strategies, and adaptively generating personalized target training content that fits the characteristics of employees' abilities and takes into account both ability improvement and business output.

[0085] S360: Generate a hybrid target training plan that matches the target employees based on their historical schedule information and target training content.

[0086] The target training plan includes multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline.

[0087] Optionally, based on the above embodiments, a hybrid target training plan matching the target employees can be generated according to their historical schedule information and target training content. This plan may include: Based on the target training content, match and allocate online learning resources and offline practice resources for the target employees; based on the target employees' historical schedule information, generate a hybrid target training plan that matches the target employees according to the execution order of online learning first and offline practice later.

[0088] In this embodiment of the invention, historical schedule information can be specifically understood as: the target employee's work arrangements, free time periods, task distribution, time preferences and other related schedule data over a past period.

[0089] Online learning resources can be understood as learning formats that do not require in-person participation, such as micro-lessons, online courses, online tests, and knowledge base materials. Offline practical resources can be understood as hands-on resources that require in-person participation, such as mentor guidance, equipment operation, on-site troubleshooting, and team collaboration practice.

[0090] Specifically, based on the generated target training content, an intelligent workflow engine is used to match online learning resources and offline practice resources that meet the needs of employee skill enhancement, completing the scheduling and integration of the two types of resources. Then, the historical schedule information of the target employees is retrieved to analyze their work free time and task distribution patterns. Following the execution order of online learning first and offline practice later, online courses and offline practical tasks are reasonably arranged to the corresponding free time, clarifying the specific time, content and type of each training, and finally generating a hybrid target training plan that matches the employee's schedule and skill enhancement needs.

[0091] In a specific example, using the target training content and employees' historical schedule information as input, an intelligent workflow engine matches online learning resources (such as micro-courses on knowledge summary and sharing, and advanced courses on equipment system analysis) and offline practical resources (such as mentorship and on-site troubleshooting tasks) that are suitable for employees' skill gaps and strategic priorities in the training resource map. The interval between online and offline content is flexibly adjusted according to the employees' schedule tightness. At the same time, based on the time preferences in the employees' historical schedule, online courses are scheduled to fragmented free time periods, and offline practical tasks are scheduled to concentrated free time periods. The specific time, single content, and online or offline type of each training item are clearly defined. Finally, a hybrid target training plan that takes into account skill improvement, strategic implementation, and schedule adaptation is generated. The resource scheduling and schedule arrangement strategies can be dynamically adjusted based on actual implementation feedback.

[0092] By rationally planning training time based on employees' historical schedule information and simultaneously allocating and matching online learning and offline practice resources according to the needs of capacity building, conflicts between training and daily work can be effectively avoided, improving the feasibility and reliability of employee participation in training. At the same time, by adopting the order of online theoretical learning followed by offline practical training, the training plan not only conforms to the laws of cognition and the logic of skill development, but also achieves a close connection between theoretical knowledge and practical application, thereby improving training efficiency and capacity transformation effect, making blended training more targeted and feasible.

[0093] S370. Distribute the hybrid target training plan to the terminal devices held by the target employees, and set matching task reminders on the terminal devices according to the target training plan.

[0094] Furthermore, based on the above embodiments, the method for generating customized training plans for operations and maintenance personnel based on performance prisms may further include: During the training process according to the target training plan, the training participation and task completion behaviors of target employees and relevant stakeholders are quantitatively recorded, converted into standard points and stored in the corresponding points account; when the points in the points account reach the preset conditions, the matching incentive process is triggered.

[0095] In this embodiment of the invention, the relevant parties can be specifically understood as: enterprises, workshops or work groups, target employees, and other entities participating in the training ecosystem. Participation behavior and task completion behavior can be specifically understood as: quantifiable behaviors such as employee training duration, course learning progress, task submission status, work group organization and cooperation, and enterprise resource investment.

[0096] Standard points can be understood as a quantified value that unifies various contribution behaviors, used to fairly measure participation and contribution. Points accounts can be understood as digital accounts used to store the corresponding points of each party, supporting accumulation, querying, and trigger condition judgment. Preset conditions can be understood as incentive trigger rules such as point thresholds and completion indicators pre-configured by the system. Incentive processes can be understood as the reward distribution process that automatically starts after the points target is met, including both material and non-material incentives.

[0097] Specifically, as part of the contribution management process, a multi-entity contribution behavior quantification system is constructed based on the performance prism framework. Throughout the entire training process according to the target training plan, the training participation and task completion status of target employees and relevant entities such as enterprises and work teams are quantitatively recorded. All kinds of behaviors are uniformly converted into standard points and stored in the corresponding point accounts. For example, multi-dimensional behavioral data such as employee learning completion rate, task delivery quality, work team collaboration, and enterprise resource investment are automatically collected. Through a unified conversion rule, the contributions of all parties are converted into standard points and stored in the corresponding contribution point accounts in real time.

[0098] The system monitors the changes in points for each account in real time. In addition to using fixed threshold triggers, it can also combine tiered point rules and dynamic adjustment mechanisms. When the point value reaches the preset trigger conditions, the corresponding incentive process will be automatically started, thereby achieving positive guidance for training participation behavior.

[0099] Optionally, based on the above embodiments, during the training process, the resources invested by the enterprise, the practical tasks provided by the workshop and work group, the mentor guidance hours, the learning time of employees, and the knowledge cases submitted are uniformly quantified. According to the incentive rules, various behaviors are converted into corresponding contribution points. A centralized database with audit logs or blockchain technology is used to record the points account in an immutable manner. According to the preset condition judgment rules, the system automatically triggers the incentive redemption process when the user's points reach the specified threshold, and completes the matching and distribution of incentives such as training resources, promotion points, performance bonuses, or honorary awards.

[0100] By quantifying and scoring the participation and task completion of employees and related stakeholders in training, measurable, traceable, and fair evaluation of training contributions can be achieved. Combined with preset scoring conditions, the incentive process can be automatically triggered, which can effectively mobilize the initiative and enthusiasm of all parties to participate in training. At the same time, by relying on the performance prism framework to build a correspondence between contribution and incentive, a complete closed loop of training implementation, contribution recording, and incentive feedback can be formed, thereby improving the training execution rate and sustainability, and ensuring the long-term stable implementation of customized training programs.

[0101] In a specific example, taking the intelligent production line operation and maintenance team of a large cigarette factory's cigarette making and packaging workshop as the application target, the implementation is carried out in five steps based on the performance prism model: demand identification, training intent decoding, capability quantification, process execution optimization, and contribution management. A standardized demand list is formed through multi-source data collection and KANO and IPA analysis. Cluster analysis is used to extract key technical themes from the standardized demand list. Based on the key technical themes, core training intents are drawn and decomposed into multiple key measurement indicators. A five-dimensional capability assessment model is constructed using AHP and fuzzy comprehensive evaluation methods to generate accurate capability profiles of employees and identify capability gaps. Personalized hybrid training plans are arranged and training strategies are dynamically optimized by an intelligent workflow engine that integrates reinforcement learning algorithms. Positive incentives for multiple participating entities are achieved through contribution quantification points and intelligent incentive rules, ultimately forming a closed loop for sustainable operation and maintenance talent training.

[0102] In a specific example, a customized training plan generation system for operations and maintenance personnel based on a performance prism can be deployed on a private cloud containerized microservice architecture. It consists of a data platform, a group of business microservices, front-end applications, and a security and operations module. The data platform enables unified storage and service invocation of multi-source heterogeneous data. The business microservices group covers requirements identification, training intent decoding, capability quantification, process execution optimization, and contribution management services. The front-end applications are configured with employee mobile applications and a management platform to meet practical and control needs, providing personalized interactive interfaces for users with different roles. Coupled with a unified authentication and monitoring alarm mechanism to ensure the system's secure and stable operation, it can fully support the intelligent execution of the entire process from requirements analysis, plan formulation, capability assessment to training scheduling and contribution incentives.

[0103] The technical solution of this invention collects multi-source heterogeneous demand data from operations and maintenance personnel across multiple platforms and integrates it with the Kano model and importance performance analysis model. This allows for the accurate extraction of real training needs and the formation of a standardized demand list, preventing training from becoming disconnected from actual needs. Based on this, cluster analysis extracts key technical themes, maps core training intentions, and decomposes them into key performance indicators, making training objectives clearer, quantifiable, and implementable. Collecting daily operations and maintenance behavior data from employees and calculating capability membership vectors, combined with job requirement information, calculates the target capability information that needs to be enhanced. This objectively and comprehensively identifies the target capabilities that employees need to enhance, replacing subjective evaluations and improving assessment accuracy. By using the capability information and key performance indicators required by target employees as a basis, and employing an intelligent workflow engine equipped with reinforcement learning algorithms to dynamically adjust training process parameters, this achieves precise matching of training content with individual capability gaps and core job requirements. This avoids the resource waste and inefficiency problems associated with traditional uniform training models. Furthermore, the algorithm allows for continuous iteration and optimization of training strategies, making training content more targeted and dynamically adaptable, improving the efficiency and effectiveness of skills enhancement for operations and maintenance personnel. Furthermore, by combining employees' historical schedules to generate hybrid online and offline training plans, the training can be adapted to employees' work rhythm and improve training sustainability. Distributing the plans to terminals and setting task reminders can ensure that training is executed on time, improve training coverage and completion rate, and realize the intelligent, customized and efficient end-to-end process of training for operations and maintenance personnel, from needs analysis, capability assessment, content generation to plan execution.

[0104] Example 4 Figure 4 This is a schematic diagram of a device for generating customized training plans for operations and maintenance personnel based on a performance prism, as provided in Embodiment 4 of the present invention. Figure 4 As shown, the device includes: a data fusion module 410, an intent decomposition module 420, a membership vector module 430, a capability information module 440, a training content module 450, a training plan module 460, and a plan distribution module 470, wherein: The data fusion module 410 is used to collect multi-source heterogeneous demand data for operation and maintenance personnel from multiple information platforms, and to fuse the multi-source heterogeneous demand data through the Kano model and the importance performance analysis model to generate a standardized demand list. The intent decomposition module 420 is used to extract key technical themes from the standardized requirements list through cluster analysis, draw core training intents based on key technical themes, and decompose the core training intents into multiple key metrics. The membership vector module 430 is used to collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, and to obtain the capability membership vector of the target employees based on the multi-source behavioral data. The capability information module 440 is used to calculate the target capability information that the target employee needs to enhance when undertaking the target job task based on the capability membership vector and the job requirement information of the target position. The training content module 450 is used to generate target training content that matches the target employees based on the target capability information and key performance indicators through an intelligent workflow engine. The training plan module 460 is used to generate a hybrid target training plan that matches the target employees based on their historical schedule information and target training content. The target training plan contains multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline. The plan distribution module 470 is used to distribute the hybrid target training plan to the terminal devices held by the target employees, and set matching task reminders on the terminal devices according to the target training plan.

[0105] The technical solution of this invention collects multi-source heterogeneous demand data from operations and maintenance personnel across multiple platforms, and integrates it with the Kano model and importance performance analysis model for fusion processing. This enables the accurate extraction of real training needs and the formation of a standardized demand list, avoiding a disconnect between training and actual needs. Furthermore, cluster analysis extracts key technical themes, maps core training intentions, and decomposes them into key performance indicators, making training objectives clearer, more quantifiable, and more implementable. Collecting daily operations and maintenance behavior data from employees and calculating capability membership vectors, combined with job requirement information, calculates the target capability information that needs to be enhanced, enabling an objective and comprehensive identification of employee skill enhancement needs. The system targets and improves the accuracy of assessments by replacing subjective evaluations with target competency information and key performance indicators. Based on this information and key metrics, a smart workflow engine generates matching training content, enabling personalized and dynamic optimization of training materials and improving training efficiency. Furthermore, by integrating employee historical schedules, a blended online and offline training plan is generated, adapting to employee work rhythms and enhancing training sustainability. Distributing the plan to terminals and setting task reminders ensures timely training execution, improves training coverage and completion rates, and achieves intelligent, customized, and efficient end-to-end training for operations and maintenance personnel, from needs analysis and competency assessment to content generation and plan execution.

[0106] Based on the above embodiments, the data fusion module 410 is specifically used for: Structured data such as overall equipment efficiency, failure rate, and maintenance man-hours are obtained from the Manufacturing Execution System via the Application Programming Interface (API); production meeting minutes are parsed using optical character recognition (OCR) and natural language processing (NLP) algorithms to extract problem-related requirements; team skill assistance requests are obtained from the mobile inspection application; employee course search volume, completion rate, and course rating data are exported from the learning management platform; and the above data are integrated with the requirements to form multi-source heterogeneous requirement data.

[0107] Based on the above embodiments, the data fusion module 410 is further configured to: The Karnaugh model is used to classify various types of heterogeneous demand data and determine the corresponding type weights. The importance and satisfaction of each type of heterogeneous demand data are evaluated, and an importance performance analysis matrix is ​​drawn based on the evaluation results. The quadrant weights corresponding to the importance performance analysis matrix are determined. Based on the types and type weights classified by the Karnaugh model, the quadrant weights corresponding to the importance performance analysis matrix, and the evaluation results, the comprehensive priority index of each type of heterogeneous demand data is calculated. The various types of heterogeneous demand data are prioritized according to the comprehensive priority index to generate a standardized demand list.

[0108] Based on the above embodiments, the membership vector module 430 is specifically used for: Multi-source behavioral data is normalized and mapped to the membership level of the corresponding capability indicators in the pre-built capability assessment model; based on the membership level, fuzzy comprehensive evaluation calculation is performed layer by layer to obtain the capability membership vector corresponding to the target employee.

[0109] Based on the above embodiments, the cultivation content module 450 is specifically used for: Based on the target competency information and key performance indicators, the training process parameters are dynamically adjusted by an intelligent workflow engine based on reinforcement learning algorithms to generate target training content that matches the target employees.

[0110] Based on the above embodiments, the training plan module 460 is specifically used for: Based on the target training content, match and allocate online learning resources and offline practice resources for the target employees; based on the target employees' historical schedule information, generate a hybrid target training plan that matches the target employees according to the execution order of online learning first and offline practice later.

[0111] Furthermore, based on the above embodiments, the device for generating customized training plans for operations and maintenance personnel based on performance prisms may further include: a quantitative scoring module and an incentive triggering module, wherein: The quantitative scoring module is used to quantitatively record the training participation and task completion behaviors of target employees and relevant stakeholders during the training process in accordance with the target training plan, convert them into standard points and store them in the corresponding points account; The incentive trigger module is used to trigger a matching incentive process when the points in the points account reach a preset condition.

[0112] The customized training plan generation device for operation and maintenance personnel based on performance prism provided in this embodiment of the invention can execute the customized training plan generation method for operation and maintenance personnel based on performance prism provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0114] Example 5 Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0115] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0117] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for generating customized training plans for operations personnel based on performance prisms, i.e.: Multi-source heterogeneous requirement data for operations and maintenance personnel is collected from multiple information platforms. The multi-source heterogeneous requirement data is then fused and processed using the Kano model and the importance performance analysis model to generate a standardized requirement list. Key technology themes were extracted from the standardized requirements list through cluster analysis, core training intentions were drawn based on the key technology themes, and the core training intentions were decomposed into multiple key metrics. Collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, and obtain the capability membership vector of the target employees based on the multi-source behavioral data. Based on the capability membership vector and the job requirements information of the target position, the target capability information that the target employee needs to enhance when undertaking the tasks of the target position is calculated. Based on the target capability information and key performance indicators, the intelligent workflow engine generates target training content that matches the target employees. Based on the target employees' historical schedule information and target training content, a hybrid target training plan is generated that matches the target employees. The target training plan contains multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline. The hybrid target training plan is distributed to the terminal devices held by the target employees, and matching task reminders are set on the terminal devices according to the target training plan.

[0118] In some embodiments, the performance prism-based method for generating customized training plans for operations and maintenance personnel can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the performance prism-based method for generating customized training plans for operations and maintenance personnel described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the performance prism-based method for generating customized training plans for operations and maintenance personnel by any other suitable means (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0124] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating customized training plans for operations and maintenance personnel based on performance prisms, characterized in that, include: Multi-source heterogeneous requirement data for operations and maintenance personnel is collected from multiple information platforms. The multi-source heterogeneous requirement data is then fused and processed using the Kano model and the importance performance analysis model to generate a standardized requirement list. Key technology themes were extracted from the standardized requirements list through cluster analysis, core training intentions were drawn based on the key technology themes, and the core training intentions were decomposed into multiple key metrics. Collect multi-source behavioral data of target employees in their daily operation and maintenance work within a set period, and obtain the capability membership vector of the target employees based on the multi-source behavioral data. Based on the capability membership vector and the job requirements information of the target position, the target capability information that the target employee needs to enhance when undertaking the tasks of the target position is calculated. Based on the target capability information and key performance indicators, the intelligent workflow engine generates target training content that matches the target employees. Based on the target employees' historical schedule information and target training content, a hybrid target training plan is generated that matches the target employees. The target training plan contains multiple training items, each of which includes the training time, content of a single training session, and training type, which can be online or offline. The hybrid target training plan is distributed to the terminal devices held by the target employees, and matching task reminders are set on the terminal devices according to the target training plan.

2. The method according to claim 1, characterized in that, Collect multi-source, heterogeneous demand data for operations and maintenance personnel from multiple information platforms, including: Structured data such as overall equipment efficiency, failure rate, and maintenance man-hours are obtained from the Manufacturing Execution System via the application programming interface (API). Utilize optical character recognition and natural language processing algorithms to parse production meeting minutes and extract problem-related requirements; Obtain work order-type requests for team skills assistance from mobile inspection applications; Export employee course search volume, completion rate, and course rating data from the learning management platform; The above data is integrated with the requirements to form multi-source heterogeneous requirement data.

3. The method according to claim 1, characterized in that, By fusing multi-source heterogeneous demand data using the Carnot model and importance performance analysis model, a standardized demand list is generated, including: The Kano model is used to classify the types of various multi-source heterogeneous demand data and determine the corresponding type weights; Assess the importance and satisfaction of various multi-source heterogeneous demand data, draw an importance performance analysis matrix based on the assessment results, and determine the quadrant weights corresponding to the importance performance analysis matrix. Based on the types and type weights of the Carnot model, the quadrant weights corresponding to the importance performance analysis matrix, and the evaluation results, the comprehensive priority index of various multi-source heterogeneous demand data is calculated. The various heterogeneous demand data from multiple sources are prioritized according to a comprehensive priority index to generate a standardized demand list.

4. The method according to claim 1, characterized in that, Based on the multi-source behavioral data, the capability membership vector of the target employee is obtained, including: Multi-source behavioral data is normalized and mapped to the membership level of the corresponding capability indicators in a pre-built capability assessment model; Based on the membership level, the fuzzy comprehensive evaluation calculation is completed layer by layer to obtain the capability membership vector corresponding to the target employee.

5. The method according to claim 1, characterized in that, Based on the target competency information and key performance indicators, the intelligent workflow engine generates target training content that matches the target employees, including: Based on the target competency information and key performance indicators, the training process parameters are dynamically adjusted by an intelligent workflow engine based on reinforcement learning algorithms to generate target training content that matches the target employees.

6. The method according to claim 1, characterized in that, Based on the target employees' historical schedule information and the target training content, generate a hybrid target training plan that matches the target employees, including: Based on the target training content, match and allocate online learning resources and offline practice resources for the target employees; Based on the target employees' historical schedule information, and following the execution sequence of online learning followed by offline practice, a hybrid target training plan matching the target employees is generated.

7. The method according to claim 1, characterized in that, Also includes: During the training process in accordance with the target training plan, the training participation and task completion behaviors of the target employees and relevant stakeholders are quantitatively recorded, converted into standard points, and stored in the corresponding points account. When the points in the points account reach the preset conditions, the matching incentive process is triggered.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for generating customized training plans for operations and maintenance personnel based on performance prisms as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for generating customized training plans for operations and maintenance personnel based on performance prisms, as described in any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method for generating customized training plans for operations and maintenance personnel based on performance prisms according to any one of claims 1-7.

Images