Personnel scheduling method and device and computer storage medium

Abstract

The invention discloses a personnel scheduling method and device and a computer storage medium, and relates to the technical field of after-sales service management, and the method comprises the steps: calculating a device maintenance demand in a future preset period according to the received device use data and work order historical data; extracting the equipment information of each piece of equipment and the fault probability corresponding to the equipment from the equipment maintenance demand; target equipment with the fault probability reaching a fault threshold value is screened, and equipment maintenance tasks are generated based on the equipment information of the target equipment, so that the personnel demand quantity corresponding to all the equipment maintenance tasks is determined; identifying a description text of the equipment maintenance task, and determining skill requirements in the equipment maintenance task; and according to skill requirements in the equipment maintenance task, screening an adaptive personnel set meeting the personnel demand from the personnel skill library, thereby generating a personnel scheduling scheme of the equipment maintenance task. According to the invention, the adaptability of equipment maintenance tasks and personnel skills is ensured, and the response efficiency of after-sales service is improved.

Description

Technical Field

[0001] The present application relates to the technical field of after-sales service management, and in particular to a personnel scheduling method, equipment and computer storage medium. Background Art

[0002] When planning their after-sales service teams, companies usually rely on traditional experience. However, traditional experience is too subjective and is limited by the cognitive limitations and historical experience of decision makers. Since traditional experience cannot deeply explore the correlation between after-sales service-related data and related factors such as customer demand fluctuations, equipment failure mode changes, work order characteristics, and service personnel traits, companies are unable to accurately predict the demand for after-sales services when facing ever-changing customer needs and market environments, which leads to deviations between personnel scheduling and actual demand, causing service delays and affecting service efficiency. Summary of the invention

[0003] The main purpose of this application is to provide a personnel scheduling method, device and computer storage medium, aiming to solve the technical problem of low service efficiency caused by unreasonable scheduling of after-sales service personnel.

[0004] To achieve the above objectives, an embodiment of the present application provides a personnel scheduling method, which includes: Calculate the equipment maintenance requirements within the future preset period based on the received equipment usage data and work order history data; Extracting device information of each device and the corresponding failure probability of the device from the device maintenance requirements; Screening target devices whose failure probability reaches or exceeds a failure threshold, and generating device maintenance tasks based on device information of the target devices; Based on the equipment maintenance tasks, determining the number of personnel required for all the equipment maintenance tasks; Identify the description text of the equipment maintenance task and determine the skill requirements of the equipment maintenance task; According to the skill requirements of the equipment maintenance task and the demand for personnel, a set of suitable personnel is obtained by screening from a personnel skill library; Based on the set of adapted personnel, a personnel scheduling plan for the equipment maintenance task is generated.

[0005] In one embodiment, the step of calculating the equipment maintenance requirements within a future preset period based on the received equipment usage data and work order history data includes: Performing feature extraction on the device usage data and the work order history data to obtain a device usage feature data set and a work order feature data set; Obtaining a correlation matrix between the equipment usage dataset and the work order feature dataset; Based on the correlation matrix, the equipment maintenance demand within a future preset period is predicted.

[0006] In one embodiment, the step of selecting a set of suitable personnel from a personnel skill library according to the skill requirements and the personnel demand in the equipment maintenance task includes: Traversing the personnel skill library, matching each personnel's skills with each of the skill requirements, and obtaining a matching result; According to the matching results, personnel who meet the personnel demand and have the skill requirements are screened out to generate a set of suitable personnel.

[0007] In one embodiment, the step of screening out personnel who meet the personnel demand and have the skill requirements according to the matching results and generating a set of suitable personnel includes: Counting the occurrence frequency of each skill requirement in the equipment maintenance task, and calculating the frequency ratio of each skill requirement in all skill requirements; Determine the number of pre-allocated personnel corresponding to each skill requirement according to the personnel demand and the frequency ratio; Based on the number of pre-assigned personnel corresponding to each of the skill requirements, the set of suitable personnel is obtained by screening.

[0008] In one embodiment, the step of screening the target devices whose failure probability reaches or exceeds the failure threshold and generating the device maintenance task based on the device information of the target devices includes: Extracting the device type and fault type of the target device according to the device information of each target device; Based on the device type and the fault type, a corresponding device maintenance task template is selected, and a device maintenance task is generated in combination with the device information of the target device.

[0009] In one embodiment, the step of determining the number of personnel required for all the equipment maintenance tasks based on the equipment maintenance tasks includes: Determining a processing level of the equipment maintenance task according to the equipment type and the fault type in the equipment maintenance task; The personnel requirements corresponding to all the equipment maintenance tasks are determined according to the preset benchmark personnel requirements of the processing level.

[0010] In one embodiment, the step of generating a personnel scheduling scheme for the equipment maintenance task based on the set of adapted personnel includes: Constructing a task directed graph according to the task identifier of each of the equipment maintenance tasks; Marking each person in the set of suitable persons with a number; Construct a personnel task adaptation matrix and assign values ​​according to the degree of adaptation of each personnel's skills to the skill requirements corresponding to the equipment maintenance task; Starting from the starting node of the task directed graph, according to the personnel task adaptation matrix, a set of prepared personnel who can perform the equipment maintenance task is screened for each node in turn; Calculate and select the personnel with the shortest total time to perform the equipment maintenance task, record the execution order and the time schedule of the equipment maintenance task, recursively complete the personnel allocation of all the equipment maintenance tasks, and generate a personnel scheduling plan.

[0011] In one embodiment, the step of constructing a personnel task adaptation matrix and assigning values ​​according to the degree of adaptation between each personnel's skills and the skill requirements corresponding to the equipment maintenance task further includes: Construct a multi-dimensional personnel task adaptation matrix and calculate the regional adaptation value according to the geographical location of the equipment maintenance task and the current location of the personnel; Determine the time adaptability by combining the available working hours of the personnel and the estimated time window of the equipment maintenance task; The regional adaptation value and / or the time adaptation degree are added to the personnel task adaptation matrix according to preset weights, and the comprehensive adaptation score of the personnel task adaptation matrix is ​​updated.

[0012] An embodiment of the present application also provides a personnel scheduling device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the personnel scheduling method described above.

[0013] An embodiment of the present application also provides a computer storage medium, which is a computer-readable storage medium. A computer program is stored on the computer storage medium. When the computer program is executed by a processor, the steps of the personnel scheduling method described above are implemented.

[0014] The embodiment of the present application discloses a personnel scheduling method, which calculates the equipment maintenance demand within a preset period in the future according to the received equipment usage data and work order history data; extracts the equipment information of each equipment and the corresponding failure probability of the equipment from the equipment maintenance demand; screens the target equipment whose failure probability reaches or exceeds the failure threshold, and generates equipment maintenance tasks based on the equipment information of the target equipment; determines the personnel demand corresponding to all the equipment maintenance tasks based on the equipment maintenance tasks; identifies the description text of the equipment maintenance tasks and determines the skill requirements in the equipment maintenance tasks; selects a set of adapted personnel from a personnel skill library according to the skill requirements in the equipment maintenance tasks and the personnel demand; generates a personnel scheduling plan for the equipment maintenance tasks based on the adapted personnel set. The present application predicts the equipment maintenance demand within a preset period in the future, and extracts the skill requirements in the equipment maintenance demand and matches them with the personnel skill library to ensure the adaptability of the maintenance tasks and personnel skills. On this basis, a personnel scheduling plan is generated in combination with the equipment maintenance demand and the adapted personnel set, which improves the response speed and execution efficiency of after-sales service. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of a first embodiment of a personnel scheduling method involved in an embodiment of the present application; Figure 2 This is a flow chart of a second embodiment of a personnel dispatching method according to an embodiment of the present application; Figure 3 This is a flow chart of a third embodiment of a personnel dispatching method according to an embodiment of the present application; Figure 4 This is a schematic diagram of the structure of the personnel dispatching equipment for this applicant.

[0016] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] When planning their after-sales service teams, companies usually rely on traditional experience and statistical methods. However, traditional experience is too subjective and is limited by the cognitive limitations of decision makers, making it difficult to cope with complex and ever-changing after-sales service scenarios. Statistical methods mainly summarize and analyze historical data, such as the number of services or workload within a historical period, without deeply exploring the correlation between these data and related factors such as fluctuations in after-sales service demand, changes in equipment failure modes, work order characteristics, and service personnel traits.

[0019] As a result, companies are unable to use these methods to accurately predict the demand for after-sales services, resulting in a deviation between staff scheduling and actual demand. This deviation is specifically manifested in vacancies or mismatches in service personnel for related after-sales services, causing service delays and thus affecting service efficiency.

[0020] In order to solve the above defects existing in the related art, the embodiment of the present application proposes a personnel scheduling method, which calculates the equipment maintenance demand within the future preset period according to the received equipment usage data and work order history data; extracts the equipment information of each device and the corresponding failure probability of the device from the equipment maintenance demand; screens the target device whose failure probability reaches or exceeds the failure threshold, and generates equipment maintenance tasks based on the equipment information of the target device; determines the personnel demand corresponding to all the equipment maintenance tasks based on the equipment maintenance tasks; identifies the description text of the equipment maintenance tasks and determines the skill requirements in the equipment maintenance tasks; selects a set of adapted personnel from the personnel skill library according to the skill requirements in the equipment maintenance tasks and the personnel demand; generates a personnel scheduling plan for the equipment maintenance tasks based on the adapted personnel set. The present application predicts the equipment maintenance demand within the future preset period, and ensures the adaptability of the maintenance tasks and personnel skills by extracting the skill requirements in the equipment maintenance demand and matching them with the personnel skill library. On this basis, a personnel scheduling plan is generated by combining the equipment maintenance demand and the adapted personnel set, which improves the response speed and execution efficiency of after-sales service.

[0021] It should be noted that the execution subject of this embodiment may be a personnel dispatching system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a personnel dispatching device capable of realizing the above functions, etc. The following takes the personnel dispatching system as an example (hereinafter referred to as the "system") to illustrate this embodiment and the following embodiments.

[0022] Please refer to the personnel scheduling method of the first embodiment proposed in this application. Figure 1 The method comprises steps S10 to S70: Step S10: Calculate the equipment maintenance requirements within a future preset period based on the received equipment usage data and work order history data.

[0023] In this embodiment, equipment usage data and work order history data can be obtained by establishing a data connection interface with the after-sales Whale Ling SAAS spare parts cloud warehouse platform or the enterprise ERP (Enterprise Resource Planning) system.

[0024] Equipment usage data includes information such as equipment type, equipment operating hours, failure frequency, and failure records. These data can be converted into computable numerical forms to analyze and evaluate the health status and failure tendency of equipment.

[0025] The work order history data records past equipment maintenance tasks, including work order type, maintenance time, required skills, and consumed resources. Through in-depth analysis of equipment usage data and work order history data, the patterns and trends of equipment maintenance can be revealed.

[0026] In a feasible implementation, step S10 may include steps S11 to S13: Step S11: extracting features from the equipment usage data and the work order history data to obtain an equipment usage feature data set and a work order feature data set.

[0027] In this embodiment, the original equipment usage data and work order history data usually present diverse and unstructured characteristics. For example, the equipment type in the equipment usage data is described in text form, and the equipment operation time, failure frequency, etc. are in numerical form, but the data dimensions are multiple and scattered. The work order type, required skills, etc. in the work order history data also exist in different formats, so feature extraction operations are required.

[0028] Feature extraction is the use of data mining, machine learning and other related technical means. For example, the principal component analysis (PCA) method can be used to transform the originally complex data into a new set of relatively small feature representations that can retain the key information of the original data to the greatest extent through linear transformation, so as to obtain the equipment usage feature data set and the work order feature data set.

[0029] Feature extraction is the process of identifying and extracting the most relevant information from raw data. In this step, the equipment usage feature dataset includes key indicators such as equipment type, operating hours, fault frequency, and fault type. Similarly, the work order feature dataset includes work order type, resolution time, required skills, etc. These feature datasets are established to convert unstructured raw data into structured, quantifiable datasets for subsequent analysis.

[0030] For example, in terms of equipment usage data, the system can obtain the identification of the equipment type by identifying the equipment model, and can also calculate the cumulative running time of the equipment and analyze the equipment time change rate, thereby using the time change rate as the equipment's operating intensity feature. In addition, the system can also count the number of equipment failures and the corresponding running time intervals, thereby calculating the failure density and using it as the failure frequency feature.

[0031] For the historical data of work orders, different types of work orders are classified to form a work order type set, such as repair, maintenance, etc. The average resolution time and time dispersion of each work order type are calculated as the work order processing time feature or response efficiency feature. At the same time, the skills required for work order processing and the complexity of skills are identified as personnel matching features.

[0032] Furthermore, after the equipment usage features and work order features are extracted, feature selection is performed to determine the important features that affect the equipment maintenance requirements. Specifically, feature selection algorithms such as LASSO regression (Least Absolute Shrinkage and Selection Operator regression) and Random Forest can be used to screen the extracted feature data set.

[0033] Then, based on the results obtained from running the feature selection algorithm, feature screening is performed to select the features that have the greatest impact on the equipment maintenance demand prediction, and remove relatively unimportant features or features that contribute less to the prediction results. This reduces the complexity of the entire model and avoids the waste of computing resources and possible overfitting problems caused by too many redundant features, thereby effectively improving the accuracy of equipment maintenance demand prediction, so that the subsequent prediction model built based on these features can more accurately reflect the actual situation.

[0034] Step S12: Obtain a correlation matrix between the equipment usage dataset and the work order feature dataset.

[0035] The correlation matrix is ​​a matrix structure used to quantitatively represent the degree of association between two feature data sets. It uses specific statistical analysis methods, such as the Pearson Correlation Coefficient and the Spearman's Rank Correlation Coefficient, to calculate the correlation between each feature in the equipment usage feature data set and each feature in the work order feature data set. The calculation results are presented in the form of a matrix, and each element in the matrix represents the numerical value of the correlation between the corresponding two features.

[0036] For example, if the correlation coefficient between the equipment operating time and the number of maintenance work orders is positively correlated and the coefficient is large, it means that the longer the operating time, the more likely it is to generate a maintenance work order.

[0037] Step S13: Based on the correlation matrix, predict the equipment maintenance demand within a future preset period.

[0038] In this step, the correlation matrix is ​​used to guide feature selection and weight assignment for the machine learning model to predict equipment maintenance needs.

[0039] It should be noted that equipment maintenance demand refers to task data that may require maintenance within a preset period in the future, including equipment type, fault type, fault probability, occurrence time, and the location of the equipment.

[0040] Specifically, first, the equipment usage features and work order features that are highly correlated with equipment maintenance requirements are identified based on the correlation matrix. These features are represented as variables with high correlation coefficients with equipment maintenance requirements in the correlation matrix. Then, the equipment usage features, work order features, and the corresponding correlation coefficients of these features are used as inputs and trained using a machine learning algorithm.

[0041] For example, when using a decision tree model, features with higher correlation coefficients in the correlation matrix will be given priority as the basis for node splitting, thereby constructing a decision tree that can effectively predict equipment maintenance needs.

[0042] For example, in a multivariate linear regression model, the correlation matrix helps determine the weights of each characteristic variable, and the model predicts the possibility and extent of equipment maintenance requirements within a future preset period by learning the weight information.

[0043] In the above way, the correlation matrix can not only reveal the relationship between each feature, but also directly affect the construction and performance of the prediction model, making the predicted equipment maintenance demand more accurate and reliable.

[0044] In this embodiment, the system can use a machine learning model to classify and predict whether the equipment needs maintenance and the degree of maintenance, etc.; or use a regression model, and use the various characteristics of the equipment as independent variables, and whether maintenance is required as the dependent variable to establish a demand prediction model to effectively predict the equipment maintenance needs, etc.

[0045] Furthermore, based on the correlation between the features in the correlation matrix, and based on the sequence and change patterns of the equipment usage data and the work order history data in the time dimension, time series analysis and prediction models such as the ARIMA model (Autoregressive Integrated Moving Average Model) can be used to take the time-related data in the equipment usage feature data set and the work order feature data set as input. According to the time change pattern of the past data learned through model training, and the influence of the interaction of various features on the equipment maintenance demand, the equipment maintenance demand within the preset period in the future is predicted. For example, it is predicted which equipment may have which type of failure, the failure frequency, and the time when the failure occurs in the next week, etc., to provide basic information for subsequent work such as determining the personnel demand, thereby ensuring that the entire equipment maintenance and personnel scheduling work can be planned in advance and carried out in an orderly manner.

[0046] For example, if a device has often required maintenance of the same type of fault within a short period of time in the past, then in the future preset period, it will be predicted that the device will still have a high demand for this type of maintenance and may fail at a certain point in time.

[0047] During the model training process, the equipment usage feature data set and the work order feature data set are used as training data sets, and the k-fold cross-validation method is used to evaluate the stability and generalization ability of the model. The grid search method is used to optimize the model's hyperparameters and improve the model's prediction accuracy. The specific operations of the k-fold cross-validation method include: First, divide the data set into k subsets of similar size. In each round of verification, select one of the subsets as the test set and the remaining k-1 subsets as the training set. For example, if k is set to 5, each subset is used as the test set in turn, and the remaining 4 subsets are used as training sets, for a total of 5 rounds of training and testing operations. In this way, the model can be trained and evaluated on different combinations of data subsets, avoiding overfitting or underfitting problems caused by a single data partition, thereby effectively evaluating the generalization ability of the model.

[0048] In terms of optimizing model hyperparameters, the grid search method can find the optimal hyperparameter combination by exhaustively searching the predefined hyperparameter grid to improve the prediction accuracy of the model.

[0049] When evaluating the prediction performance of the model, you can use indicators such as Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) to evaluate the prediction performance of the model. Then adjust the structure and parameters of the model based on the evaluation results.

[0050] According to the evaluation results, when the mean square error or root mean square error value of the model is large, it indicates that the model prediction error is large. In this case, the cause of the error should be further analyzed, and the structure of the model should be adjusted accordingly, such as increasing the number of hidden layers or nodes of the neural network, or re-screening and combining data features, adjusting feature weights and other parameters, so that the model is continuously optimized and its prediction performance is gradually improved.

[0051] Step S20: extracting the device information of each device and the corresponding failure probability of the device from the device maintenance requirement.

[0052] The equipment maintenance requirements output by the prediction model usually include the corresponding equipment information of the equipment and the corresponding failure probability of the equipment. The equipment information includes but is not limited to the equipment type, equipment model, failure probability, expected time of occurrence and the location of the equipment. The failure probability is the result of a quantitative assessment of the possibility of equipment failure within a preset period in the future.

[0053] In this step, the equipment information allows the system to identify whether the equipment needs maintenance.

[0054] Step S30: screening the target devices whose failure probability reaches or exceeds the failure threshold, and generating a device maintenance task based on the device information of the target devices.

[0055] The system analyzes equipment usage data and work order history data to predict the probability of equipment failures that may occur in the future preset period. The prediction results allow the system to identify potential equipment maintenance needs in advance, so that maintenance resources can be allocated in a targeted manner and maintenance plans can be formulated.

[0056] In order to effectively manage after-sales service resources, the system can tilt service resources toward those devices that are most likely to fail, that is, target devices whose failure probability reaches or exceeds the preset failure threshold. This can help the system reduce unnecessary preventive maintenance work and ensure that high-risk equipment receives timely attention, thereby improving the overall response efficiency and service quality of after-sales service.

[0057] In a feasible implementation manner, step S30 includes steps S310 to S320: Step S310: extracting the device type and fault type of the target device according to the device information of each target device.

[0058] Step S320: Based on the device type and the fault type, a corresponding device maintenance task template is selected, and a device maintenance task is generated in combination with the device information of the target device.

[0059] It should be noted that the equipment maintenance task template is developed with reference to historical work order data, and includes the equipment type, fault type, fault occurrence time, estimated maintenance time, and required skills.

[0060] Based on the extracted equipment type and fault type, combined with other equipment information of the target equipment, such as the location of the equipment, required skill requirements, etc., the content of the template is supplemented to generate equipment maintenance tasks.

[0061] Step S40: Based on the equipment maintenance tasks, determine the personnel requirements corresponding to all the equipment maintenance tasks.

[0062] In order to effectively perform equipment maintenance tasks, after the equipment maintenance tasks are generated, the system calculates the number of personnel required for all equipment maintenance tasks based on these equipment maintenance tasks, so as to better perform personnel scheduling and resource allocation and avoid personnel shortages or surpluses.

[0063] In this embodiment, the average maintenance time required for different equipment types, or equipment of the same equipment type but with different equipment failures, can be analyzed based on the equipment maintenance records in the work order history data. Therefore, the average maintenance time can be used as the standard working hours required for equipment maintenance tasks of the corresponding equipment type, or equipment of the same equipment type but with different equipment failures. Then, the system can determine the number of personnel required for all equipment maintenance tasks based on the personnel's work efficiency and other records of historical personnel processing efficiency.

[0064] In a feasible implementation manner, step S40 includes steps S410 to S420: Step S410: Determine the processing level of the equipment maintenance task according to the equipment type and fault type in the equipment maintenance task.

[0065] Step S420: Determine the number of personnel required for all the equipment maintenance tasks according to the preset baseline number of personnel required for the processing level.

[0066] The baseline staff requirement is pre-set according to the processing level, indicating the minimum number of staff required to complete tasks of different levels. The processing level of the equipment maintenance task, i.e., the task difficulty, is determined by the type of equipment or equipment failure corresponding to the equipment maintenance task. Then the baseline staff requirement required for different task difficulties is set, so that the staff requirement required for all equipment maintenance tasks can be determined.

[0067] Specifically, when determining the processing level of an equipment maintenance task, you can refer to the time or manpower consumed by work order tasks of the same equipment type in the work order history data, and then set the processing level of the task through a time threshold or a manpower consumption threshold, that is, to indicate the difficulty of the task.

[0068] Furthermore, the system can also set the average working hours of each person when making personnel scheduling forecasts, and then calculate the personnel requirements corresponding to all equipment maintenance tasks based on the average working hours and the total man-hours of all equipment maintenance tasks.

[0069] Step S50: Identify the description text of the equipment maintenance task and determine the skill requirements of the equipment maintenance task.

[0070] In the personnel scheduling process, when equipment maintenance tasks are generated, in order to arrange appropriate personnel to perform these equipment maintenance tasks, it is necessary to clarify what specific skill requirements are required for each equipment maintenance task.

[0071] It is understandable that when generating equipment maintenance tasks, they are obtained based on the equipment information in the equipment maintenance requirements. Therefore, equipment maintenance tasks usually include relevant attributes of the equipment and description text such as fault manifestations, such as the equipment type, fault type, fault manifestation, and fault occurrence time of the equipment.

[0072] In this step, natural language processing (NLP) can be used to perform lexical analysis on the description text of the equipment maintenance task and decompose the description text into basic language units such as words and phrases. For example, the sentence "replace the transmission gear of equipment A" can be decomposed into terms such as "replace", "equipment A", and "transmission gear".

[0073] Then, we conduct syntactic analysis to clarify the grammatical structure relationship between each word item and determine the subject, predicate, object and other components of the sentence. For example, we can analyze that "replace" is the predicate verb and "transmission gear" is the object, so as to more accurately grasp the core action and object expressed in the text.

[0074] Finally, semantic analysis is used to understand the actual meaning of the description text based on the pre-existing equipment maintenance knowledge base, and to determine actions such as "replacing the transmission gear" or the skill requirements corresponding to the equipment type or fault type. The equipment maintenance knowledge base is based on historical equipment maintenance records or expert experience, and includes equipment maintenance operations corresponding to equipment types or fault types, as well as technical requirements required for equipment types or fault types.

[0075] Furthermore, a deep learning model can be used to pre-train the model using a large number of descriptive texts of equipment maintenance tasks with labeled skill requirements, so that the model can learn the mapping relationship between different descriptive text expressions and skill requirements. The descriptive text of the current equipment maintenance task to be identified is then input into the trained model, and the model outputs the corresponding skill requirements, thereby determining the skill requirements in the equipment maintenance task.

[0076] In this embodiment, the prediction model is learned based on the equipment usage data and the work order history data to predict the equipment maintenance needs. Therefore, when the work order history data includes a note on the skills required for the corresponding task, the equipment maintenance needs output after the prediction model is learned may also include the skills required for the equipment.

[0077] Therefore, when generating equipment maintenance tasks based on equipment maintenance requirements, the equipment maintenance tasks may contain descriptions of required skills. In this case, the determination of the skills required for the equipment maintenance tasks can be simpler and more accurate. The skill requirements required for the equipment maintenance tasks can be determined by similarity calculation or matching calculation.

[0078] Step S60: According to the skill requirements in the equipment maintenance task and the required number of personnel, a set of suitable personnel is obtained from a personnel skill library.

[0079] In this step, in order to accurately provide after-sales service, the system needs to clarify the skills or other requirements required for equipment maintenance tasks, such as the location of the equipment, the time when the fault occurred, and the estimated repair time. Then, based on these requirements, the system finds suitable personnel from the existing personnel resources to match the corresponding equipment maintenance tasks.

[0080] For example, when different tasks have specific skill requirements for the executors, such as repairing a complex electronic device, the maintenance personnel need to have professional skills such as electronic circuit testing; if the task is to maintain a large mechanical device, the personnel are required to master skills such as lubrication and precision debugging of mechanical parts.

[0081] It should be noted that the personnel skills database is a database that collects, organizes and stores information about the skills of all relevant personnel within the enterprise in advance. It records the name of the skill, skill level and other information mastered by each person, providing a data basis for screening suitable personnel.

[0082] By comparing the skills required for the task with the skills possessed by the personnel, we can obtain a matching result that reflects the matching between the personnel skills and the skill requirements. Then, according to the required personnel demand, we screen out personnel who meet the quantity requirements and have the corresponding skill requirements from the matching results. Finally, we integrate these personnel to form a set of adapted personnel. The personnel in the set of adapted personnel are personnel resources that are competent for the corresponding equipment maintenance tasks and meet the overall personnel allocation plan.

[0083] Step S70: Based on the set of adapted personnel, a personnel scheduling plan for the equipment maintenance task is generated.

[0084] In this embodiment, in order to ensure the rationality and effectiveness of the personnel scheduling plan, multiple factors such as the required skills, geographical distribution, and the urgency of the work order in the equipment maintenance requirements can be considered, and an optimization algorithm can be designed and applied to solve the optimal personnel scheduling plan. The required skills reflect the ability to handle a specific task. The geographical distribution affects the time cost of after-sales personnel arriving at the site. The urgency of the work order determines the priority of the task.

[0085] Specifically, in this embodiment, optimization algorithms such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) can be used to solve the optimal personnel scheduling solution. The optimal solution output by the optimization algorithm will be converted into a task allocation table, which includes the specific equipment maintenance tasks, execution time and location corresponding to each person, or includes the execution time, location and personnel arrangement information corresponding to each equipment maintenance task.

[0086] In this embodiment, the genetic algorithm is used to initialize a set of possible personnel scheduling schemes as the initial population, and then the fitness value of each personnel scheduling scheme is calculated through the evaluation function. Subsequently, the genetic algorithm selects individuals with higher fitness to perform crossover and mutation operations to generate a new generation of populations, and repeats this process until the preset termination conditions are met, such as reaching the maximum number of iterations or the fitness value is no longer significantly improved.

[0087] Particle swarm optimization searches for the optimal solution by simulating the flight of a group of particles in the solution space. Each particle represents a potential solution and adjusts its flight direction and speed based on its own experience and the experience of other particles in the group.

[0088] In this embodiment, the particle swarm optimization algorithm can be used to further optimize the scheduling scheme initially selected by the genetic algorithm. The position of each particle corresponds to a specific personnel scheduling scheme, and its speed indicates the direction and amplitude of the adjustment of the personnel scheduling scheme. By continuously updating the speed and position of the particles, the particle swarm optimization algorithm gradually converges to the optimal solution, ensuring that the final generated scheduling scheme meets all constraints.

[0089] In the process of generating personnel scheduling plans, in order to ensure that the adopted optimization algorithm is highly feasible and effective, its effect can be verified by simulating actual after-sales service scenarios.

[0090] Optionally, the failure rate curves of different equipment types in actual operation are analyzed based on historical data, and the random occurrence mode of equipment failure is set in the simulation environment based on this. At the same time, the skill level of after-sales personnel is quantified according to the level, and the response time model is constructed based on the relationship between their region and the service area.

[0091] In the simulation environment, after the optimization algorithm is used to generate a personnel scheduling plan, the personnel scheduling plan is applied to the simulated after-sales service process.

[0092] During the simulation, various key indicators are recorded, such as the average task response time, the total time for task completion, the proportion of personnel idle time, etc.

[0093] Exemplarily, the average task response time is calculated by recording the time interval from the generation of the work order to the start of the personnel processing, the total time spent on all equipment maintenance tasks from start to finish is counted to obtain the total task completion time data, and the proportion of time that personnel are in a task-free state during the entire simulation cycle is calculated to obtain the proportion of personnel idle time, etc.

[0094] According to the verification results collected during the simulation, the effect of the optimization algorithm is analyzed and evaluated. If it is found that some key indicators do not meet the expected goals, such as the average response time of work orders is too long or the proportion of idle time of personnel is too high, the parameters and rules of the optimization algorithm need to be adjusted.

[0095] For example, when adjusting algorithm parameters, if a genetic algorithm is used, parameters such as crossover probability and mutation probability can be adjusted. For example, when it is found that the algorithm converges too slowly, resulting in low efficiency in generating scheduling solutions, the crossover probability is increased to increase the diversity of the population and promote the algorithm to converge to a better solution faster.

[0096] For example, for the particle swarm optimization algorithm, parameters such as inertia weight and learning factor can be adjusted. For example, the inertia weight can be dynamically adjusted according to the urgency of the task, so that particles can explore the search space more widely in the early stage of the search and converge to the optimal solution more accurately in the later stage of the search.

[0097] In this embodiment, the effect of the optimization algorithm is verified by simulating an actual after-sales service scenario. The optimization algorithm parameters and rules are adjusted based on the verification results to ensure that personnel skills are more reasonably utilized in the entire scheduling process, thereby improving the feasibility and effectiveness of the scheduling solution.

[0098] Please refer to Figure 2 , the personnel dispatching method of the second embodiment proposed in the present application, step S60 includes steps S610~S620: Step S610: traverse the personnel skill library, match each personnel's skills with each of the skill requirements, and obtain a matching result.

[0099] Identify the description text of each specific equipment maintenance task, extract the corresponding skill requirements from it, and form a skill requirement list. Then traverse the personnel skill library and compare the skills mastered by each person in the personnel skill library with each skill requirement in the skill requirement list one by one.

[0100] The comparison operation can be achieved by setting matching rules, for example, requiring that the skill names are consistent and the skill levels reach or exceed the minimum level standards required for the task for a successful match; or pre-establishing matching rules based on factors such as the relevance and substitutability of skills. For example, a certain equipment maintenance task requires personnel to master welding skills. If the personnel master other welding skills that are similar to welding skills and can achieve the same maintenance effect, it can also be considered a match to a certain extent.

[0101] Step S620: According to the matching results, select the personnel who meet the personnel demand and have the skill requirements, and generate a set of suitable personnel.

[0102] The personnel demand is the number of personnel required calculated based on the number of equipment maintenance tasks, processing level and other factors. From the matching results of step S610, according to the standard of personnel demand, select personnel who meet both the quantity requirements and the corresponding skill requirements, and then integrate them to obtain a set of matching personnel. The matching personnel set can ensure that in the personnel scheduling and allocation of subsequent equipment maintenance tasks, the personnel skills are well matched with the task requirements, thereby improving the service quality of after-sales service.

[0103] In a feasible implementation, step S620 may include steps S621 to S623: Step S621: Count the occurrence frequency of each skill requirement in the equipment maintenance task, and calculate the frequency ratio of each skill requirement in all skill requirements.

[0104] It should be noted that the frequency of occurrence refers to the number of times a skill requirement appears in all equipment maintenance tasks. The frequency ratio refers to the proportion of the frequency of occurrence of the skill requirement in the total frequency of occurrence of all skill requirements.

[0105] For example, if there are multiple equipment maintenance tasks, and the electrical maintenance skill requirement appears 5 times in these equipment maintenance tasks, then the frequency of occurrence of the electrical maintenance skill requirement is 5 times.

[0106] For example, the total frequency of all skill requirements is 20 times, and the frequency of electrical maintenance skill requirements is 5 times, so the frequency ratio of electrical maintenance skill requirements is 1 / 4.

[0107] The process of counting the occurrence frequency and calculating the frequency ratio is to record the skill requirements included in all equipment maintenance tasks, then record the number of times each skill requirement occurs one by one, and finally obtain the corresponding frequency ratio by dividing the occurrence frequency of each skill requirement by the sum of the occurrence frequencies of all skill requirements.

[0108] Step S622: Determine the number of pre-allocated personnel corresponding to each skill requirement based on the personnel demand and the frequency ratio.

[0109] Step S623: Based on the number of pre-assigned personnel corresponding to each of the skill requirements, the set of suitable personnel is screened and obtained.

[0110] After determining the skill requirements for each equipment maintenance task, it is necessary to screen out personnel who can meet these skill requirements from the personnel skill library to form the final set of suitable personnel.

[0111] It should be noted that the personnel demand refers to the total number of personnel required based on the equipment maintenance requirements. The number of pre-allocated personnel refers to the number of personnel pre-allocated to each skill requirement based on the frequency ratio of each skill requirement, on the premise of meeting the overall personnel demand.

[0112] Further, step S623 may include steps S6231-S6232: Step S6231: Score the matching degree between each person's skill and each skill requirement in the personnel skill database to form a matching ranking list.

[0113] In this embodiment, the matching score involves a quantitative evaluation of the matching degree between the personnel skills and the skill requirements in the equipment maintenance task. The matching process generally includes factors such as whether the skill name is consistent or whether the matching degree exceeds a threshold, whether the skill level meets or exceeds the task requirement level, etc.

[0114] In this embodiment, the matching scores between the skills mastered by each person and the skill requirements in the equipment maintenance task can be determined by matching calculation or similarity calculation, thereby forming a matching ranking list.

[0115] Step S6232: For each skill requirement, according to the number of pre-assigned personnel, select the corresponding number of personnel from the matching ranking list in order to obtain a set of suitable personnel.

[0116] After determining the number of personnel to be assigned for each skill requirement, you can select the corresponding number of personnel from the matching ranking list in descending order. For example, if the number of pre-assigned personnel corresponding to a skill requirement is 5, then select the first 5 personnel from the top of the matching ranking list.

[0117] Next, for equipment maintenance tasks with the same skill requirements, these five personnel can be further assigned based on the processing level of the tasks.

[0118] Please refer to Figure 3 , the personnel dispatching method of the third embodiment proposed in the present application, step S70 includes steps S710~S750: Step S710: construct a task directed graph according to the task identifier of each of the equipment maintenance tasks.

[0119] Task identification is a mark used to distinguish different equipment maintenance tasks, which facilitates the identification and processing of each equipment maintenance task. Task directed graph is a way to visualize and structure the complex relationship between equipment maintenance tasks, where nodes represent equipment maintenance tasks and directed edges represent the logical association and sequence requirements between equipment maintenance tasks.

[0120] For example, if there are multiple equipment maintenance tasks in the predicted equipment maintenance needs, and their failure occurrence times are in chronological order, then one of the equipment maintenance tasks must be carried out after other equipment maintenance tasks are completed. The task flow can be clearly sorted out through a directed graph.

[0121] Step S720: Mark each person in the set of suitable persons with a number.

[0122] The number tag is used to easily identify and reference specific personnel when building the personnel task adaptation matrix. The number can directly adopt the existing identification in the personnel-related information, such as the employee number, or assign a unique serial number.

[0123] Step S730: construct a personnel task adaptation matrix, and assign values ​​according to the degree of adaptation between each personnel's skills and the skill requirements corresponding to the equipment maintenance task.

[0124] The personnel task adaptation matrix is ​​a two-dimensional matrix, whose rows can represent different tasks and columns can represent different personnel. The element values ​​in the matrix represent the degree of adaptation between the corresponding personnel and the task, which can be the result of the matching score between the personnel skills and the task skill requirements.

[0125] Step S740: Starting from the starting node of the task directed graph, according to the personnel task adaptation matrix, a set of prepared personnel who can perform the equipment maintenance task is screened for each node in turn.

[0126] The equipment maintenance task corresponding to the starting node is usually the first part of the entire task process, that is, the equipment maintenance task corresponding to the earliest equipment failure in the equipment maintenance requirements. According to the constructed personnel task adaptation matrix, the set of reserve personnel who can perform the corresponding equipment maintenance tasks is screened, that is, the adaptation of the corresponding tasks and personnel in the matrix is ​​checked, and the personnel who meet certain standards of adaptation and are capable of performing the task are selected to form a set of reserve personnel.

[0127] Step S750: Calculate and select the personnel with the shortest total time to perform the equipment maintenance task, record the execution order and the time schedule of the equipment maintenance task, recursively complete the personnel allocation of all the equipment maintenance tasks, and generate a personnel scheduling plan.

[0128] The shortest total time consumption is measured based on multiple factors such as the efficiency of personnel in performing equipment maintenance tasks and the order requirements between equipment maintenance tasks. By calculating the time consumption of different personnel in performing equipment maintenance tasks, comprehensively considering the order constraints of equipment maintenance tasks, the personnel with the shortest total time consumption are selected to perform the corresponding equipment maintenance tasks, and the execution order and the specific time schedule of each equipment maintenance task are recorded. Then, in this way, the personnel allocation of all equipment maintenance tasks is gradually completed, and finally a personnel scheduling plan that can meet the logical association and order requirements of tasks and ensure the overall optimal time consumption is generated, thereby realizing efficient personnel scheduling arrangements.

[0129] In a feasible implementation manner, step S730 further includes steps S731 to S733: Step S731: construct a multi-dimensional personnel task adaptation matrix, and calculate the regional adaptation value according to the geographical location of the equipment maintenance task and the current location of the personnel.

[0130] The multi-dimensional adaptation matrix is ​​an expanded matrix structure compared to the adaptation matrix that only considers the personnel skill dimension, and is designed to more comprehensively reflect the adaptation between personnel and equipment maintenance tasks. The geographical dimension refers to the dimension involving geographical factors such as the geographical location of the equipment maintenance task and the current location of the personnel. The time dimension covers time-related factors such as the available working hours of the personnel and the estimated time window of the equipment maintenance task. By adding these dimensions to the original adaptation matrix, a matrix that measures the adaptation situation from multiple angles can be constructed to ensure that the multi-dimensional adaptation information can be accurately reflected.

[0131] The regional adaptation value is a numerical value used to quantify the degree of adaptation between the geographical location of the equipment maintenance task and the current location of the personnel. The coordinate information and other data of the two places can be obtained through the relevant technology of the Geographic Information System (GIS), and then the distance between the two places can be calculated using the distance calculation formula. Then, according to the distance, transportation convenience and other factors, the rules are set to convert it into the corresponding regional adaptation value. The regional adaptation value of the region with short distance and convenient transportation is relatively high, and vice versa, which can intuitively reflect the degree of regional adaptation. If the task location of the equipment maintenance task and the area where the personnel are located belong to the same administrative division or service area, the regional adaptation value will be relatively higher.

[0132] Optionally, the degree of geographical adaptability may be reflected in turn according to whether the area where the equipment maintenance task is located matches the area where the personnel are located.

[0133] Step S732: Determine the time adaptability based on the available working time of the personnel and the estimated time window of the equipment maintenance task.

[0134] Time adaptability is mainly an indicator to measure the degree of fit between personnel's available working hours and the estimated time window of equipment maintenance tasks.

[0135] Specifically, by comparing and analyzing the time periods in which personnel can work (such as the available attendance time in shifts, etc.) and the estimated time windows for equipment maintenance tasks (the time windows constituted by the estimated maintenance time in the equipment information), the specific value of the time adaptation is determined based on the ratio of the overlapping time between the two to the estimated time window for the equipment maintenance task, or according to pre-set time matching rules, for example, if the overlapping time reaches a preset ratio, it indicates a high degree of adaptation, etc., to reflect the time adaptation situation.

[0136] Step S733: adding the regional adaptation value and / or the time adaptation degree to the personnel task adaptation matrix according to preset weights, and updating the comprehensive adaptation score of the personnel task adaptation matrix.

[0137] The preset weight is a proportion weight set in advance based on factors such as personnel technical requirements, region, and time, and the regional adaptation value and / or time adaptation degree are added to the personnel task adaptation matrix according to the preset weight, and then the adaptation value of each dimension is weighted according to the preset weight, so as to update and adjust the comprehensive adaptation score in the personnel task adaptation matrix. This enables the personnel task adaptation matrix after updating the comprehensive adaptation score to comprehensively and accurately reflect the overall adaptation between personnel and equipment maintenance tasks under multi-dimensional factors including region, time, and personnel technical requirements.

[0138] The present application provides a personnel scheduling device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the personnel scheduling method in the above-mentioned embodiment one.

[0139] Reference below Figure 4 , which shows a schematic diagram of the structure of a personnel scheduling device suitable for implementing the embodiment of the present application. The personnel scheduling device in the embodiment of the present application may include various hardware and software components for implementing the personnel scheduling method. Figure 4 The personnel dispatching device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0140] like Figure 4 As shown, the personnel dispatching device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the personnel dispatching device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the personnel dispatching device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a personnel dispatching device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0141] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0142] The personnel dispatching device provided by the present application adopts the personnel dispatching device method in the above embodiment, which can solve the technical problem of low service efficiency caused by unreasonable dispatch of after-sales service personnel. Compared with the prior art, the beneficial effects of the personnel dispatching device provided by the present application are the same as the beneficial effects of the personnel dispatching method provided by the above embodiment, and other technical features in the personnel dispatching device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0143] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0144] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0145] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the personnel scheduling method in the above-mentioned embodiment.

[0146] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0147] The computer-readable storage medium may be included in the personnel dispatching device; or may exist independently without being assembled into the personnel dispatching device.

[0148] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the personnel scheduling device, the personnel scheduling device: calculates the equipment maintenance requirements within a future preset period based on the received equipment usage data and work order history data; extracts the equipment information of each device and the corresponding failure probability of the device from the equipment maintenance requirements; screens the target devices whose failure probability reaches or exceeds the failure threshold, and generates equipment maintenance tasks based on the equipment information of the target devices; determines the personnel requirements corresponding to all the equipment maintenance tasks based on the equipment maintenance tasks; identifies the description text of the equipment maintenance tasks and determines the skill requirements in the equipment maintenance tasks; screens a set of suitable personnel from a personnel skill library based on the skill requirements in the equipment maintenance tasks and the personnel requirements; and generates a personnel scheduling plan for the equipment maintenance tasks based on the set of suitable personnel.

[0149] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0150] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0151] The modules involved in the embodiments described in the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0152] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned personnel scheduling method, and can solve the technical problem of low service efficiency caused by unreasonable scheduling of after-sales service personnel. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the personnel scheduling method provided in the above-mentioned embodiment, and will not be repeated here.

[0153] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned personnel scheduling method when executed by a processor.

[0154] The computer program product provided in this application can solve the technical problem of low service efficiency caused by unreasonable scheduling of after-sales service personnel. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the personnel scheduling method provided in the above embodiment, which will not be repeated here.

[0155] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

[0156] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0157] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0158] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A personnel scheduling method, characterized in that: The personnel scheduling method comprises: Calculate the equipment maintenance requirements within the future preset period based on the received equipment usage data and work order history data; Extracting device information of each device and the corresponding failure probability of the device from the device maintenance requirements; Screening target devices whose failure probability reaches or exceeds a failure threshold, and generating device maintenance tasks based on device information of the target devices; Based on the equipment maintenance tasks, determining the number of personnel required for all the equipment maintenance tasks; Identify the description text of the equipment maintenance task and determine the skill requirements in the equipment maintenance task; According to the skill requirements of the equipment maintenance task and the demand for personnel, a set of suitable personnel is obtained by screening from a personnel skill library; Based on the set of adapted personnel, a personnel scheduling plan for the equipment maintenance task is generated.

2. The personnel dispatching method according to claim 1, characterized in that: The step of calculating the equipment maintenance demand within a future preset period based on the received equipment usage data and work order history data includes: Performing feature extraction on the device usage data and the work order history data to obtain a device usage feature data set and a work order feature data set; Obtaining a correlation matrix between the equipment usage dataset and the work order feature dataset; Based on the correlation matrix, the equipment maintenance demand within a future preset period is predicted.

3. The personnel dispatching method according to claim 1, characterized in that: The step of selecting a set of suitable personnel from a personnel skill library according to the skill requirements in the equipment maintenance task and the personnel demand includes: Traversing the personnel skill library, matching each personnel's skills with each of the skill requirements, and obtaining a matching result; According to the matching results, personnel who meet the personnel demand and have the skill requirements are screened out to generate a set of suitable personnel.

4. The personnel dispatching method according to claim 3, characterized in that: The step of screening out personnel who meet the personnel demand and have the skill requirements according to the matching results and generating a set of suitable personnel includes: Counting the occurrence frequency of each skill requirement in the equipment maintenance task, and calculating the frequency ratio of each skill requirement in all skill requirements; Determine the number of pre-allocated personnel corresponding to each skill requirement according to the personnel demand and the frequency ratio; Based on the number of pre-assigned personnel corresponding to each of the skill requirements, the set of suitable personnel is obtained by screening.

5. The personnel dispatching method according to claim 1, characterized in that: The step of screening the target devices whose failure probability reaches or exceeds the failure threshold and generating a device maintenance task based on the device information of the target devices includes: Extracting the device type and fault type of the target device according to the device information of each target device; Based on the device type and the fault type, a corresponding device maintenance task template is selected, and a device maintenance task is generated in combination with the device information of the target device.

6. The personnel dispatching method according to claim 1, characterized in that: The step of determining the number of personnel required for all the equipment maintenance tasks based on the equipment maintenance tasks includes: Determining a processing level of the equipment maintenance task according to the equipment type and the fault type in the equipment maintenance task; The personnel requirements corresponding to all the equipment maintenance tasks are determined according to the preset benchmark personnel requirements of the processing level.

7. The personnel dispatching method according to claim 1, characterized in that: The step of generating a personnel scheduling scheme for the equipment maintenance task based on the set of adapted personnel includes: Constructing a task directed graph according to the task identifier of each of the equipment maintenance tasks; Marking each person in the set of suitable persons with a number; Construct a personnel task adaptation matrix and assign values ​​according to the degree of adaptation of each personnel's skills to the skill requirements corresponding to the equipment maintenance task; Starting from the starting node of the task directed graph, according to the personnel task adaptation matrix, a set of prepared personnel who can perform the equipment maintenance task is screened for each node in turn; Calculate and select the personnel with the shortest total time to perform the equipment maintenance task, record the execution order and the time schedule of the equipment maintenance task, recursively complete the personnel allocation of all the equipment maintenance tasks, and generate a personnel scheduling plan.

8. The personnel dispatching method according to claim 7, characterized in that: The step of constructing a personnel task adaptation matrix and assigning values ​​according to the degree of adaptation between each personnel's skills and the skill requirements corresponding to the equipment maintenance task also includes: Construct a multi-dimensional personnel task adaptation matrix and calculate the regional adaptation value according to the geographical location of the equipment maintenance task and the current location of the personnel; Determine the time adaptability by combining the available working hours of the personnel and the estimated time window of the equipment maintenance task; The regional adaptation value and / or the time adaptation degree are added to the personnel task adaptation matrix according to preset weights, and the comprehensive adaptation score of the personnel task adaptation matrix is ​​updated.

9. A personnel scheduling prediction device, characterized in that: The personnel scheduling prediction device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the personnel scheduling method according to any one of claims 1 to 8.

10. A computer storage medium, characterized in that: The computer storage medium is a computer-readable storage medium, and a computer program is stored on the computer storage medium. When the computer program is executed by a processor, the steps of the personnel scheduling method according to any one of claims 1 to 8 are implemented.

Images