A dynamic perception training method and system for a data center risk assessor

Abstract

The application provides a data center risk assessment personnel dynamic perception cultivation method and system, which can be applied to the technical field of data center operation and risk assessment. The method comprises the following steps: obtaining operation situation data of a target data center and multi-dimensional personnel capability portraits corresponding to each risk assessment personnel; determining risk index information corresponding to each professional field based on the operation situation data; determining capability gaps based on the multi-dimensional personnel capability portraits; when the risk index information or the capability gaps exceeds a threshold value, determining personnel to be trained and a training plan according to the gap type, and performing training; after the training is completed, collecting examination and knowledge sharing data corresponding to the personnel to be trained, and updating the multi-dimensional personnel capability portraits corresponding to the personnel to be trained. In this way, the operation situation data of the data center and the dynamic multi-dimensional personnel capability portraits are linked, the training plan is generated in advance according to needs, and the personnel capability is updated in a closed loop, thereby improving the comprehensive business support capability of the data center risk assessment personnel.

Description

Technical Field

[0001] This application relates to the field of data center operation and maintenance and risk assessment technology, and in particular to a dynamic perception training method and system for data center risk assessment personnel. Background Technology

[0002] In data center operations and maintenance scenarios, it is usually necessary to have professional risk assessment personnel to handle equipment failures, investigate security risks, and support various critical business operations.

[0003] Existing personnel training programs rely on fixed-cycle, standardized training to maintain staff skills. They only retain static certifications as a reference for personnel capabilities, failing to incorporate real-time data center operational data into training planning or establish a process for post-training feedback and updating of personnel information. This approach cannot quantify operational risks and staffing gaps in various professional areas, cannot customize training content based on business shortcomings, and personnel competency profiles cannot reflect real-time changes in assessments, knowledge sharing, and skill degradation. Furthermore, it fails to form a complete closed loop of training, assessment, and knowledge accumulation, ultimately resulting in insufficient comprehensive business support capabilities for data center risk assessment personnel.

[0004] Therefore, how to improve the comprehensive business support capabilities of data center risk assessment personnel is an urgent problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a dynamic awareness training method and system for data center risk assessment personnel. By linking data center operational status data with dynamic multi-dimensional personnel capability profiles, training plans are generated proactively on demand and personnel capabilities are updated in a closed loop, thereby improving the comprehensive business support capabilities of data center risk assessment personnel.

[0006] In a first aspect, embodiments of this application provide a dynamic awareness training method for data center risk assessment personnel, including: Obtain operational status data of the target data center, as well as multi-dimensional personnel capability profiles for each risk assessment personnel; Based on the operational status data, determine the risk index information corresponding to each professional field of the target data center; Based on the multi-dimensional personnel capability profile, capability gaps are determined by combining preset target configurations. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, personnel to be trained are identified from all risk assessment personnel based on the gap type, and a training plan is generated. The trainees will be trained based on the aforementioned training plan; After the training is completed, the assessment and knowledge sharing data of the trainees are collected, and the multi-dimensional personnel capability profile of the trainees is updated.

[0007] Optionally, the method further includes: When an emergency dispatch task is triggered, candidates who meet the constraints of qualification level, professional direction, geographical location and dispatchable status are selected based on the multi-dimensional personnel capability profile. A multi-objective optimization algorithm is used to determine the scheduling scheme corresponding to the candidates. Issue and execute the scheduling scheme; After the emergency dispatch task is completed, the dispatch task evaluation data is collected and the multi-dimensional personnel capability profile corresponding to the candidate is updated synchronously.

[0008] Optionally, the operational status data includes: equipment fault data, hidden danger rectification records, and fault impact indicators; The multidimensional personnel competency profile includes at least qualification level, professional direction, historical assessment results, competency decay factor, and knowledge sharing records.

[0009] Optionally, determining the risk index information corresponding to each professional field of the target data center based on the operational status data includes: Based on the equipment failure data, hidden danger rectification records, and failure impact indicators of the target data center, the risk factors in each professional field are weighted and quantified to obtain the risk index information corresponding to each professional field of the target data center.

[0010] Optionally, the step of determining capability gaps based on the multi-dimensional personnel capability profile, in conjunction with preset target configurations, includes: Based on the preset target configuration, obtain the personnel quantity requirements and qualification level requirements corresponding to each professional field; Based on the aforementioned multi-dimensional personnel capability profile, the qualification level and professional direction of each risk assessment personnel are determined; By comparing the personnel quantity and qualification level requirements for each professional field with the qualification level and professional direction of each risk assessment personnel, the corresponding capacity gaps in each professional field can be obtained.

[0011] Optionally, the gap types include professional direction gaps and qualification level gaps; The process of identifying personnel to be trained from all risk assessment personnel based on the gap type and generating a training plan includes: If the risk index information exceeds a first preset threshold, identify at least one of the professional direction gap and qualification level gap that need to be strengthened in the corresponding professional field; if the capability gap exceeds a second preset threshold, identify at least one of the professional direction gap and qualification level gap that are corresponding to insufficient job allocation. Based on the identified gaps, trainees were selected from all risk assessment personnel. Based on the identified gaps, training content is developed and a training plan is generated.

[0012] Optionally, the step of collecting assessment and knowledge sharing data corresponding to the trainees and updating the multi-dimensional personnel competency profile corresponding to the trainees includes: The assessment scores and practical performance of the trainees after the training are collected as assessment data, and the technical sharing materials output by the trainees are collected as knowledge sharing data. Based on the assessment data, update the historical assessment scores in the multidimensional personnel competency profile corresponding to the trainee, and based on the knowledge sharing data, update the knowledge sharing records in the multidimensional personnel competency profile corresponding to the trainee.

[0013] Optionally, the step of using a multi-objective optimization algorithm to determine the scheduling scheme corresponding to the candidate includes: Based on the multi-dimensional personnel capability profiles corresponding to the candidates, and with the optimization objectives of maximizing candidate capabilities, minimizing distance, and load balancing, the NSGA-II algorithm is used to obtain the corresponding Pareto optimal solution set, and the scheduling scheme corresponding to the candidates is determined from the Pareto optimal solution set.

[0014] Secondly, embodiments of this application provide a dynamic awareness training system for data center risk assessment personnel, comprising: The data acquisition module is used to acquire operational status data of the target data center, as well as multi-dimensional personnel capability profiles for each risk assessment personnel. The first determining module is used to determine the risk index information corresponding to each professional field of the target data center based on the operational status data; The second determining module is used to determine capability gaps based on the multi-dimensional personnel capability profile, in conjunction with preset target configurations. An adaptive decision-making module is used to determine the personnel to be trained from all risk assessment personnel according to the gap type and generate a training plan when the risk index information exceeds a first preset threshold or the capability gap exceeds a second preset threshold. An execution module is used to train the personnel to be trained based on the training plan; The update module is used to collect the assessment and knowledge sharing data of the trainees after the training is completed, and update the multi-dimensional personnel capability profile of the trainees.

[0015] Optionally, the system further includes: a scheduling module; The scheduling module is used to, when an emergency scheduling task is triggered, screen candidates who meet the constraints of qualification level, professional direction, geographical location, and on-the-job scheduling based on the multi-dimensional personnel capability profile; determine the scheduling plan corresponding to the candidates using a multi-objective optimization algorithm; issue and execute the scheduling plan; and after the emergency scheduling task is completed, collect scheduling task evaluation data and update the multi-dimensional personnel capability profile corresponding to the candidates synchronously.

[0016] As can be seen from the above technical solutions, compared with the prior art, this application has the following advantages: This application provides a dynamic perception training method for data center risk assessment personnel. First, it acquires operational status data of the target data center and multi-dimensional personnel capability profiles for each risk assessment personnel. Then, based on the operational status data, it determines the risk index information corresponding to each professional field of the target data center; combined with preset target configurations, it identifies capability gaps based on the multi-dimensional personnel capability profiles. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, it identifies personnel to be trained from all risk assessment personnel according to the gap type and generates a training plan; finally, it trains the personnel to be trained based on the training plan. After training, it collects the assessment and knowledge sharing data corresponding to the personnel to be trained and updates the multi-dimensional personnel capability profiles corresponding to the personnel to be trained. In this way, by linking data center operational status data with dynamic multi-dimensional personnel capability profiles, it can proactively generate training plans on demand and update personnel capabilities in a closed loop, simultaneously addressing the shortcomings of training being detached from business, static personnel information, lack of predictive training, and lack of feedback on capability optimization, thereby improving the comprehensive business support capabilities of data center risk assessment personnel. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a dynamic perception training method for data center risk assessment personnel, provided as an embodiment of this application; Figure 2 A flowchart illustrating a method for intelligently deploying data center risk assessment personnel, provided as an embodiment of this application; Figure 3 This is a schematic diagram of a dynamic perception training system for data center risk assessment personnel, provided as an embodiment of this application. Detailed Implementation

[0018] As mentioned earlier, existing personnel training programs suffer from insufficient comprehensive business support capabilities for data center risk assessment personnel. Specifically, current programs rely on fixed-cycle, standardized training to maintain staff skills, and only retain static certification qualifications as a reference for personnel capabilities. They fail to incorporate real-time data center operational data as a basis for training planning, and lack a process for post-training feedback and updating of personnel information. This approach cannot quantify operational risks and staffing gaps in various professional areas, cannot customize training content based on business shortcomings, and personnel competency profiles cannot reflect real-time dynamic changes in assessments, knowledge sharing, and skill degradation. Furthermore, it fails to form a complete closed loop of training, assessment, and knowledge accumulation, ultimately resulting in insufficient comprehensive business support capabilities for data center risk assessment personnel.

[0019] To address the aforementioned issues, this application provides a dynamic perception training method for data center risk assessment personnel, comprising: first, acquiring operational status data of the target data center and multi-dimensional personnel capability profiles corresponding to each risk assessment personnel; then, determining risk index information corresponding to each professional field of the target data center based on the operational status data; and determining capability gaps based on the multi-dimensional personnel capability profiles in conjunction with preset target configurations. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, identifying personnel to be trained from all risk assessment personnel according to the gap type, and generating a training plan; finally, training the personnel to be trained based on the training plan. After training, collecting assessment and knowledge sharing data corresponding to the personnel to be trained, and updating the multi-dimensional personnel capability profiles corresponding to the personnel to be trained.

[0020] In this way, by linking data center operational status data with dynamic multi-dimensional personnel capability profiles, training plans can be generated in advance as needed and personnel capabilities can be updated in a closed loop. This simultaneously addresses the shortcomings of training being detached from business, static personnel information, lack of forecasting in training, and lack of feedback on capability optimization, thereby improving the comprehensive business support capabilities of data center risk assessment personnel.

[0021] It should be noted that the dynamic perception training method and system for data center risk assessment personnel provided in this application can be applied to the field of data center operation and maintenance and risk assessment technology. The above is merely an example and does not limit the application field of the dynamic perception training method and system for data center risk assessment personnel provided in this application.

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0023] Figure 1 A flowchart illustrating a dynamic awareness training method for data center risk assessment personnel, provided as an embodiment of this application. (Combined with...) Figure 1 As shown in the embodiment of this application, a dynamic perception training method for data center risk assessment personnel may include: S101: Obtain operational status data of the target data center, as well as multi-dimensional personnel capability profiles for each risk assessment personnel.

[0024] The operational status data includes: equipment fault data, hidden danger rectification records, and fault impact indicators; The multidimensional personnel competency profile includes at least qualification level, professional direction, historical assessment results, competency decay factor, and knowledge sharing records.

[0025] In practical applications, the system periodically (e.g., monthly) acquires operational status data of the target data center, along with multi-dimensional personnel capability profiles for each risk assessment specialist. The operational status data includes, but is not limited to, equipment failure data (such as power outages, HVAC failures, IT equipment overloads), hazard rectification records, and failure impact indicators, providing a clear picture of the current operational risks for each specialty within the data center. The multi-dimensional personnel capability profile includes at least qualification levels, professional specialization, historical performance evaluations, capability decay factors, and knowledge sharing records, moving away from the previous method of relying solely on static qualifications to assess personnel capabilities and dynamically depicting the actual professional competence of each risk assessment specialist. The qualification level dimension includes three fields: Assistant Appraiser, Appraiser, and Senior Appraiser. Data is sourced from the certification database and can be updated every three years (upon renewal). The professional direction dimension includes three fields: Power Supply and Distribution, HVAC, IT Network, Automation, and Safety and Fire Protection. Data is sourced from the certification database and can be updated statically. The capability decay factor dimension includes a field showing the time (in months) since the last training or assessment. Data is automatically calculated by the system and can be updated dynamically. The knowledge sharing record dimension includes the number of internal training sessions, sharing topics, and audience feedback. Data is sourced from the training system and can be updated in real-time. The historical assessment results dimension can be included within the training record dimension. Historical assessment results can be included along with the training courses and hours as fields in the training record dimension. Data is sourced from the training system and updated in real-time. In addition, the multi-dimensional personnel capability profile can include more dimensions, such as basic information, project practice, and availability status. The basic information dimension can include fields for name, organization, and geographic location, with data sourced from an authentication database and updated statically. The project practice dimension can include fields for the number of projects participated in, role, and performance, with data sourced from the project management system and updated in real-time. The availability status dimension can include fields for being on duty, on business trip, on leave, and current workload, with data sourced from the human resources system and updated in real-time. In this way, the system first synchronously aggregates operational status data and multi-dimensional personnel capability profiles, breaking down data barriers between risk status and personnel capabilities. This provides comprehensive and reliable data support for subsequent calculations of risk indices, identification of job capability gaps, and development of appropriate training plans, ensuring that training arrangements align with real-world business needs.

[0026] S102: Based on the operational status data, determine the risk index information corresponding to each professional field of the target data center.

[0027] In practical applications, we continue to rely on the acquired operational status data to analyze the risks faced by each professional field and output corresponding risk index information. The risk index can quantitatively represent the current risk level of each professional field, rather than simply relying on the subjective feelings of managers to judge risks. This provides an objective basis for subsequent decisions on whether to initiate personnel training, ensuring that personnel training work is aligned with the actual operational risks of the data center.

[0028] Furthermore, since the methods for determining risk index information are not entirely the same, this application embodiment can describe one possible determination method.

[0029] In one scenario, S102: Based on the operational status data, determine the risk index information corresponding to each professional field of the target data center, which may specifically include: Based on the equipment failure data, hidden danger rectification records, and failure impact indicators of the target data center, the risk factors in each professional field are weighted and quantified to obtain the risk index information corresponding to each professional field of the target data center.

[0030] In practical applications, risk factors in various professional fields can be weighted and quantified based on the acquired equipment failure data, hazard rectification records, and failure impact indicators of the target data center, thereby obtaining the risk index information corresponding to each professional field of the target data center. Specifically, the risk index information mentioned in the embodiments of this application... The following weighted formula is used for calculation: ; In the formula , , The system uses pre-set weighting coefficients; the number of major failures in this professional field over the past three months is taken from equipment failure data; the average failure impact index is taken from failure impact indicators, which can be represented by indicators such as business interruption duration and the number of affected cabinets; and the number of currently unrectified hidden dangers is taken from the hidden danger rectification records. In this way, differentiated weights are assigned to different risk elements, and a quantitative assessment is completed by comprehensively considering multi-dimensional information such as failure frequency, failure impact, and the number of hidden dangers to be rectified, thus moving away from the model of subjective risk judgment based on management experience. The calculated risk index information has a unified measurement standard, enabling horizontal comparison of risk levels in various professional fields such as power supply and distribution, HVAC, IT networks, automation, and fire safety. This provides an objective quantitative basis for subsequent comparison with the first preset threshold and determining whether to trigger the training mechanism, achieving linkage between training planning and the actual operational risk situation of the data center.

[0031] S103: Combine the preset target configuration and determine the capability gap based on the multi-dimensional personnel capability profile.

[0032] In practical applications, the pre-defined target configuration clearly defines the reserve size and capability standards that risk assessment personnel in each professional field should meet. For example, each professional field requires at least two corresponding senior assessors. Multi-dimensional personnel capability profiles can dynamically reflect the true business level of each risk assessment personnel. The system can compare the capability baseline of existing risk assessment personnel in each professional field with the pre-defined target configuration to identify capability gaps in each professional field. In this way, by quantitatively understanding the shortcomings of the professional talent pool in each field, and in conjunction with the professional risk indices obtained earlier, a dual-dimensional assessment of risk situation and personnel capability gaps is constructed. This provides another core criterion for deciding whether to initiate a training process, helping to achieve forward-looking talent development and avoiding the one-sidedness of relying solely on a single dimension of business risk in formulating training plans.

[0033] Furthermore, since there are different ways to determine the capacity gap, this application embodiment can describe one possible determination method.

[0034] In one scenario, S103: Combining the preset target configuration, determine the capability gap based on the multi-dimensional personnel capability profile, which may specifically include: Based on the preset target configuration, obtain the personnel quantity requirements and qualification level requirements corresponding to each professional field; Based on the aforementioned multi-dimensional personnel capability profile, the qualification level and professional direction of each risk assessment personnel are determined; By comparing the personnel quantity and qualification level requirements for each professional field with the qualification level and professional direction of each risk assessment personnel, the corresponding capacity gaps in each professional field can be obtained.

[0035] In practical applications, the system compares the preset number of personnel and qualification level admission standards (the required reserve scale and capability standards) for each professional field with the qualification level and professional direction information of the risk assessment personnel themselves to determine the corresponding capability gaps in each professional field. Specifically, the capability gaps mentioned in the embodiments of this application... The following formula is used for calculation: ; In the formula, the subscript "domain" represents the professional field, and "level" represents the qualification level. The target number of personnel is taken from the preset target configuration's personnel quantity requirements. The current number of certified personnel of this profession and level is obtained by extracting the professional direction and qualification level of each risk assessment personnel from the multi-dimensional personnel capability profile. The max function ensures that the capability gap will not be negative; when the number of existing risk assessment personnel meets the target configuration standard, the gap value is 0. In this way, this method achieves quantitative benchmarking between the personnel reserve standard and the existing personnel base, accurately locating the types of personnel gaps in different professions, and avoiding biases caused by subjective human judgment. The capability gap results, combined with the risk index information of each professional field, serve as the basis for training initiation and training program formulation, promoting the precise allocation of training resources to in-demand professions and alleviating the resource waste caused by the traditional "blanket" training model.

[0036] S104: When the risk index information exceeds the first preset threshold, or the capability gap exceeds the second preset threshold, determine the personnel to be trained from all risk assessment personnel according to the gap type, and generate a training plan.

[0037] Furthermore, the types of gaps include gaps in professional specializations and gaps in qualification levels; The process of identifying personnel to be trained from all risk assessment personnel based on the gap type and generating a training plan includes: If the risk index information exceeds a first preset threshold, identify at least one of the professional direction gap and qualification level gap that need to be strengthened in the corresponding professional field; if the capability gap exceeds a second preset threshold, identify at least one of the professional direction gap and qualification level gap that are corresponding to insufficient job allocation. Based on the identified gaps, trainees were selected from all risk assessment personnel. Based on the identified gaps, training content is developed and a training plan is generated.

[0038] In practical applications, when the risk index exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, the system selects trainees from all risk assessment personnel based on the gap type and generates a training plan. The gap types include professional direction gaps and qualification level gaps. The corresponding execution logic is as follows: If the risk index exceeds the first preset threshold, it indicates a high operational risk in the corresponding professional field, and the system automatically identifies at least one of the urgently needed professional direction gaps and qualification level gaps for that field. If the capability gap exceeds the second preset threshold, it indicates that the personnel reserve in that professional field has not reached the configuration (preset target configuration) standard, and the system automatically identifies at least one of the corresponding professional direction gaps and qualification level gaps due to insufficient job allocation. Furthermore, the system selects trainees (e.g., personnel with low certification levels in a certain professional field) based on the identified gaps (professional direction gaps and / or qualification level gaps), and develops corresponding training content and generates a training plan based on the gap requirements. For example, to address gaps in professional specialization, training content focuses on practical knowledge related to fault handling and hazard identification in the corresponding professional field; to address gaps in qualification levels, training content includes courses on advanced assessment standards and major fault judgment capabilities required for the corresponding level assessments. The generated training plan can include information such as the list of trainees, training topics (e.g., advanced risk assessment of power supply and distribution systems), class hours, training format (online / offline), and graduation assessment requirements. In this way, by setting dual trigger conditions of risk situation and personnel gaps, it is no longer limited to the extensive training with fixed cycles and uniform content. The system distinguishes between gaps in professional specialization and qualification levels to accurately locate the need for capability enhancement, and matches trainees with training courses in a targeted manner. This can not only respond to real-time operational risks of data centers, but also fill talent gaps, achieve forward-looking talent development, effectively improve the problem of traditional "blanket" training being out of touch with business needs, reduce ineffective training investment, and avoid wasting training resources.

[0039] S105: Train the personnel to be trained based on the training plan.

[0040] In practical applications, the system organizes and carries out training based on the targeted training plan generated above, matches corresponding training content according to the type of gap, implements targeted capacity building for the selected trainees, and tracks the training effect.

[0041] S106: After the training is completed, collect the assessment and knowledge sharing data corresponding to the trainees, and update the multi-dimensional personnel capability profile corresponding to the trainees.

[0042] In practical applications, after trainees complete their training, the system automatically assigns them knowledge-sharing tasks (such as organizing internal sharing sessions, writing technical case studies, and recording training videos). Trainees who pass the training are required to disseminate the knowledge and conduct technical analysis among untrained members of their organization, spreading the learned knowledge within the organization. Simultaneously, the system collects the corresponding assessment and knowledge-sharing data of the trainees and updates their multi-dimensional personnel competency profiles based on this data. This incorporates training effectiveness information into the personnel dynamic file, continuously updating the latest business competency status of each risk assessment personnel, preventing the long-term stagnation and distortion of personnel competency information, and providing more timely data support for subsequent professional risk assessment, competency gap calculation, and trainee selection.

[0043] Furthermore, since there are different ways to update the multidimensional personnel capability profile, this application embodiment can describe one possible updating method.

[0044] In one scenario, S106: After training is completed, the assessment and knowledge sharing data corresponding to the trainees are collected, and the multi-dimensional personnel competency profile corresponding to the trainees is updated, which may specifically include: The assessment scores and practical performance of the trainees after the training are collected as assessment data, and the technical sharing materials output by the trainees are collected as knowledge sharing data. Based on the assessment data, update the historical assessment scores in the multidimensional personnel competency profile corresponding to the trainee, and based on the knowledge sharing data, update the knowledge sharing records in the multidimensional personnel competency profile corresponding to the trainee.

[0045] In practical applications, the system collects the assessment scores and practical performance of trainees after training as assessment data, and collects the technical sharing materials produced by trainees as knowledge sharing data. Based on the assessment data, the system updates the historical assessment scores in the multi-dimensional personnel competency profiles of trainees, and updates the knowledge sharing records in the multi-dimensional personnel competency profiles based on the knowledge sharing data. Furthermore, after training, the "Time Since Last Training / Assessment (Months)" field in the profile can be updated synchronously, and the corresponding competency decay factor for trainees can be corrected based on the updated time information. Further, trainees can conduct internal knowledge dissemination work, such as organizing technical sharing sessions, writing case analysis reports, and recording training videos to transfer the learned skills. The system records the theme, number of attendees, and evaluation feedback of the knowledge sharing activities, quantifying the relevant information into a knowledge sharing score K and incorporating it into the personnel's comprehensive competency score. In this way, the system, on the one hand, records assessment data to retain the effectiveness of personnel training, reflects the internal technical contributions of personnel based on knowledge sharing records, and the relevant indicators together constitute the basis for evaluating personnel's comprehensive competency; on the other hand, it refreshes the training time baseline to update the competency decay factor, dynamically representing the natural decay of personnel skills over time, thus overcoming the limitations of judging personnel competency solely based on static qualification levels. The iterated multidimensional personnel capability profile can provide more accurate data support for subsequent professional risk assessment, capability gap calculation, and selection of trainees. It establishes a talent management closed loop of training implementation, effectiveness collection, knowledge transfer, and continuous iteration of personnel profiles, promotes the full dissemination of the skills learned in training within the team, avoids training results remaining only in the trainees, and fully leverages the value of training investment.

[0046] Figure 2 A flowchart illustrating a method for intelligently deploying data center risk assessment personnel, provided as an embodiment of this application. (Combined with...) Figure 2 As shown, the method may include: S201: When an emergency dispatch task is triggered, candidates who meet the constraints of qualification level, professional direction, geographical location and dispatchable status are screened based on the multi-dimensional personnel capability profile. S202: Use a multi-objective optimization algorithm to determine the scheduling scheme corresponding to the candidate; S203: Issue and execute the scheduling scheme; S204: After the emergency dispatch task is completed, collect the dispatch task evaluation data and update the multi-dimensional personnel capability profile corresponding to the candidate personnel in a synchronous manner.

[0047] Furthermore, S202: A multi-objective optimization algorithm is used to determine the scheduling scheme corresponding to the candidate, which may specifically include: Based on the multi-dimensional personnel capability profiles corresponding to the candidates, and with the optimization objectives of maximizing candidate capabilities, minimizing distance, and load balancing, the NSGA-II algorithm is used to obtain the corresponding Pareto optimal solution set, and the scheduling scheme corresponding to the candidates is determined from the Pareto optimal solution set.

[0048] In practical applications, emergency dispatch tasks are triggered in situations including, but not limited to, "a sudden major operational accident in a data center campus (such as a large-scale power outage or cooling system failure) requiring an urgent risk assessment," "a specific assessment task needs to be completed within a limited time, but local personnel are insufficient," and "assessment resources need to be allocated across regions before a major national event." When an emergency dispatch task is triggered, the system, based on the task requirements R={professional direction, minimum level, number of personnel, location, time limit} and relying on multi-dimensional personnel capability profiles, selects candidates from all risk assessment personnel who simultaneously meet the constraints of qualification level, professional direction, geographical location, and schedulable status (qualification level ≥ minimum level required by the task; professional direction matches the task requirement; geographical location is near the task requirement location, such as within 30km; current availability status is "schedulable"). Subsequently, the system uses a multi-objective optimization algorithm to select the best candidates for allocation, determine the corresponding dispatch plan, and issue and execute the dispatch plan. The system tracks the execution results, and after the emergency dispatch task is completed, it collects dispatch task evaluation data (such as report quality and customer satisfaction) and updates the multi-dimensional personnel capability profiles of the candidates accordingly. When using multi-objective optimization algorithms to solve scheduling schemes, the system combines task requirements with a comprehensive consideration of factors such as personnel competency scores, distance between personnel and task locations, and existing workload of personnel to perform optimization calculations. The multi-objective optimization algorithm can utilize the NSGA-II multi-objective genetic algorithm to output a Pareto-optimal scheduling scheme (the system can adaptively select the scheduling algorithm based on information such as task urgency, number of candidate personnel, and user preferences); the personnel competency score can be calculated using a formula... The urgency of data center campus demand can be calculated using the formula. Quantification aids in scheduling decisions. In the formula, A comprehensive evaluation of personnel capabilities; , , , This is a weighting coefficient that can be dynamically adjusted based on the task type; For qualification level coefficients (Assistant Appraiser = 1, Appraiser = 2, Senior Appraiser = 3); This represents the degree of match between the risk assessment personnel's professional expertise and the professional expertise of the target task, with a value between 0 and 1. Historical performance evaluation scores of risk assessment personnel (normalized to the 0-1 range); As the capacity decay factor, This refers to the time (in months) since the last training / assessment. This is the attenuation coefficient (usually set to 0.05); Knowledge sharing points are normalized to the 0-1 range based on information such as the number of internal training sessions, the number of audience members, and evaluation feedback. Given the urgency of the data center campus demand, and Adjustable weight parameters can be preset and dynamically configured according to operation and maintenance management strategies. Fault prediction probability is derived from analysis of the target data center's operational status data, and business importance levels are pre-assigned based on the impact on the business carried by the park. The urgency of park demands helps the system determine the priority of multiple concurrent scheduling tasks. Thus, the system uses multi-dimensional personnel capability profiles to initially screen candidates, and leverages multi-objective optimization algorithms to balance the goals of maximizing personnel capabilities, minimizing travel distance, and balancing personnel load, achieving intelligent cross-regional allocation of risk assessment personnel. After a task is completed, scheduling evaluation information is updated to the personnel profile, establishing a closed-loop workflow of emergency scheduling, task execution, and dynamic iteration of personnel files. This effectively addresses the pain points of traditional manual scheduling, such as strong subjectivity, difficulty in balancing multiple objectives, and unreasonable personnel allocation. It can quickly match suitable assessment resources in major fault handling and critical support scenarios, improving the efficiency of data center emergency response.

[0049] In addition, the parameters of the situational awareness model and the scheduling algorithm can be optimized regularly (e.g., quarterly) to improve the accuracy of decision-making.

[0050] The following specific scenario illustrates this point: "A large data center operator plans to complete a special risk assessment of the power supply and distribution system of its East China data center cluster (including 3 campuses) within one month. According to the configuration standards, each campus needs to be equipped with 2 assessors with power supply and distribution assessment qualifications or above, for a total of 6 assessors required. Currently, the company's personnel pool has 5 assistant assessors, 2 assessors, and 1 senior assessor in the power supply and distribution field, totaling 3 assessors or above, resulting in a personnel shortage of 3."

[0051] First, the system collects recent power supply and distribution related fault data for the cluster, such as UPS overload and busbar overheating records, and calculates the power supply and distribution risk index. The value exceeded the first preset threshold of 70, triggering a demand for personnel training. Simultaneously, the system compared the data with preset target configurations and calculated a shortage of 3 power supply and distribution assessors or higher-level personnel in the cluster. Then, based on multi-dimensional personnel capability profiles, the system selected 8 assistant assessors from the cluster and surrounding areas who possessed basic power supply and distribution knowledge but had not yet obtained assessor certification. Considering their historical assessment scores and available time, the system recommended 3 of them to participate in a 2-week intensive training program on "Advanced Risk Assessment of Power Supply and Distribution Systems," and automatically generated a training plan, which was then pushed to the training management system. The 3 trainees completed the training and passed the assessment, obtaining assessor qualifications. After the training, the trainees were required to conduct internal knowledge dissemination, explaining key points of power supply and distribution risk assessment and typical fault handling experience to colleagues who had not participated in the training through technical sharing sessions and writing fault case reports. Simultaneously, the system collected assessment and knowledge sharing data corresponding to the trainees and updated their multi-dimensional personnel capability profiles; it recorded the theme, number of attendees, and feedback of knowledge sharing activities, quantifying the relevant information into a knowledge sharing score K and incorporating it into the personnel's comprehensive capability score. Following this training, the number of power distribution and supply assessment specialists and above in the cluster has increased to 6, meeting the basic configuration requirements. During the operational phase, one assessment specialist in one of the parks was temporarily on leave, creating a temporary staffing shortage and triggering an emergency dispatch task. Based on multi-dimensional personnel capability profiles, the system screened candidates from the national personnel database who simultaneously met the constraints of "professional direction = power distribution and supply, qualification level ≥ assessment specialist, distance from the target park within 30km, and availability for dispatch," resulting in 28 candidates. The system set optimization objectives: maximizing the overall personnel capability score, minimizing personnel dispatch distance, and balancing the workload of all assessment personnel. The NSGA-II multi-objective genetic algorithm was used for iterative solution, outputting a Pareto optimal dispatch scheme after 200 iterations: dispatching a senior assessment specialist (overall capability score 0.94, distance from the target park 15km) from a neighboring park to provide temporary on-site support. Finally, the system summarizes all the data generated in this operation: trainees' assessment scores, knowledge sharing points, and emergency dispatch task evaluation results. The above data is used as historical samples to iteratively optimize the risk index threshold, capability decay factor, and dispatch algorithm parameters for the next cycle, and continuously optimize the entire personnel perception training and emergency dispatch system.

[0052] In summary, this application first acquires operational status data of the target data center and multi-dimensional personnel capability profiles for each risk assessment personnel. Then, based on the operational status data, it determines the risk index information corresponding to each professional field of the target data center; combined with preset target configurations, it identifies capability gaps based on the multi-dimensional personnel capability profiles. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, it identifies personnel to be trained from all risk assessment personnel according to the gap type and generates a training plan; finally, it trains the personnel to be trained based on the training plan. After training, it collects the assessment and knowledge sharing data corresponding to the personnel to be trained and updates the multi-dimensional personnel capability profiles corresponding to the personnel to be trained. Thus, by linking data center operational status data with dynamic multi-dimensional personnel capability profiles, it proactively generates training plans on demand and updates personnel capabilities in a closed loop, simultaneously addressing the shortcomings of training being detached from business, static personnel information, lack of predictive training, and lack of feedback on capability optimization, thereby improving the comprehensive business support capabilities of data center risk assessment personnel.

[0053] Figure 3 This is a schematic diagram of a dynamic awareness training system for data center risk assessment personnel, provided as an embodiment of this application. (Combined with...) Figure 3 As shown, the dynamic sensing and cultivation system 300 includes: The data acquisition module 301 is used to acquire the operational status data of the target data center, as well as the multi-dimensional personnel capability profiles corresponding to each risk assessment personnel. The first determining module 302 is used to determine the risk index information corresponding to each professional field of the target data center based on the operational status data; The second determining module 303 is used to determine the capability gap based on the multi-dimensional personnel capability profile, in conjunction with the preset target configuration. The adaptive decision module 304 is used to determine the personnel to be trained from all risk assessment personnel according to the gap type and generate a training plan when the risk index information exceeds a first preset threshold or the capability gap exceeds a second preset threshold. Execution module 305 is used to train the trainees based on the training plan; The update module 306 is used to collect the assessment and knowledge sharing data of the trainees after the training is completed, and update the multi-dimensional personnel capability profile of the trainees. The operational status data includes: equipment fault data, hidden danger rectification records, and fault impact indicators; The multidimensional personnel competency profile includes at least qualification level, professional direction, historical assessment results, competency decay factor, and knowledge sharing records.

[0054] As one implementation method, regarding how to determine the risk index information, the first determining module 302 is specifically used for: Based on the equipment failure data, hidden danger rectification records, and failure impact indicators of the target data center, the risk factors in each professional field are weighted and quantified to obtain the risk index information corresponding to each professional field of the target data center.

[0055] As one implementation method, regarding how to determine the capacity gap, the second determining module 303 is specifically used for: Based on the preset target configuration, obtain the personnel quantity requirements and qualification level requirements corresponding to each professional field; Based on the aforementioned multi-dimensional personnel capability profile, the qualification level and professional direction of each risk assessment personnel are determined; By comparing the personnel quantity and qualification level requirements for each professional field with the qualification level and professional direction of each risk assessment personnel, the corresponding capacity gaps in each professional field can be obtained.

[0056] The gap types include gaps in professional specializations and gaps in qualification levels.

[0057] As one implementation method, regarding how to identify trainees and generate training plans, the aforementioned adaptive decision module 304 is specifically used for: If the risk index information exceeds a first preset threshold, identify at least one of the professional direction gap and qualification level gap that need to be strengthened in the corresponding professional field; if the capability gap exceeds a second preset threshold, identify at least one of the professional direction gap and qualification level gap that are corresponding to insufficient job allocation. Based on the identified gaps, trainees were selected from all risk assessment personnel. Based on the identified gaps, training content is developed and a training plan is generated.

[0058] As one implementation method, regarding how to update the multi-dimensional personnel competency profile corresponding to the trainees, the aforementioned update module 306 is specifically used for: The assessment scores and practical performance of the trainees after the training are collected as assessment data, and the technical sharing materials output by the trainees are collected as knowledge sharing data. Based on the assessment data, update the historical assessment scores in the multidimensional personnel competency profile corresponding to the trainee, and based on the knowledge sharing data, update the knowledge sharing records in the multidimensional personnel competency profile corresponding to the trainee.

[0059] As one implementation method, the aforementioned dynamic perception training system 300 further includes a scheduling module for scheduling personnel; The scheduling module is used to, when an emergency scheduling task is triggered, screen candidates who meet the constraints of qualification level, professional direction, geographical location, and on-the-job scheduling based on the multi-dimensional personnel capability profile; determine the scheduling plan corresponding to the candidates using a multi-objective optimization algorithm; issue and execute the scheduling plan; and after the emergency scheduling task is completed, collect scheduling task evaluation data and update the multi-dimensional personnel capability profile corresponding to the candidates synchronously.

[0060] In summary, this application first acquires operational status data of the target data center and multi-dimensional personnel capability profiles for each risk assessment personnel. Then, based on the operational status data, it determines the risk index information corresponding to each professional field of the target data center; combined with preset target configurations, it identifies capability gaps based on the multi-dimensional personnel capability profiles. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, it identifies personnel to be trained from all risk assessment personnel according to the gap type and generates a training plan; finally, it trains the personnel to be trained based on the training plan. After training, it collects the assessment and knowledge sharing data corresponding to the personnel to be trained and updates the multi-dimensional personnel capability profiles corresponding to the personnel to be trained. Thus, by linking data center operational status data with dynamic multi-dimensional personnel capability profiles, it proactively generates training plans on demand and updates personnel capabilities in a closed loop, simultaneously addressing the shortcomings of training being detached from business, static personnel information, lack of predictive training, and lack of feedback on capability optimization, thereby improving the comprehensive business support capabilities of data center risk assessment personnel.

[0061] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A dynamic perception training method for data center risk assessment personnel, characterized in that, The method includes: Obtain operational status data of the target data center, as well as multi-dimensional personnel capability profiles for each risk assessment personnel; Based on the operational status data, determine the risk index information corresponding to each professional field of the target data center; Based on the multi-dimensional personnel capability profile, capability gaps are determined by combining preset target configurations. When the risk index information exceeds a first preset threshold, or the capability gap exceeds a second preset threshold, personnel to be trained are identified from all risk assessment personnel based on the gap type, and a training plan is generated. The trainees will be trained based on the aforementioned training plan; After the training is completed, the assessment and knowledge sharing data of the trainees are collected, and the multi-dimensional personnel capability profile of the trainees is updated.

2. The method according to claim 1, characterized in that, The method further includes: When an emergency dispatch task is triggered, candidates who meet the constraints of qualification level, professional direction, geographical location and dispatchable status are selected based on the multi-dimensional personnel capability profile. A multi-objective optimization algorithm is used to determine the scheduling scheme corresponding to the candidates. Issue and execute the scheduling scheme; After the emergency dispatch task is completed, the dispatch task evaluation data is collected and the multi-dimensional personnel capability profile corresponding to the candidate is updated synchronously.

3. The method according to claim 1, characterized in that, The operational status data includes: equipment fault data, hidden danger rectification records, and fault impact indicators; The multidimensional personnel competency profile includes at least qualification level, professional direction, historical assessment results, competency decay factor, and knowledge sharing records.

4. The method according to claim 1, characterized in that, The process of determining the risk index information corresponding to each professional field of the target data center based on the operational status data includes: Based on the equipment failure data, hidden danger rectification records, and failure impact indicators of the target data center, the risk factors in each professional field are weighted and quantified to obtain the risk index information corresponding to each professional field of the target data center.

5. The method according to claim 1, characterized in that, The process of determining capability gaps based on the multi-dimensional personnel capability profile, combined with preset target configuration, includes: Based on the preset target configuration, obtain the personnel quantity requirements and qualification level requirements corresponding to each professional field; Based on the aforementioned multi-dimensional personnel capability profile, the qualification level and professional direction of each risk assessment personnel are determined; By comparing the personnel quantity and qualification level requirements for each professional field with the qualification level and professional direction of each risk assessment personnel, the corresponding capacity gaps in each professional field can be obtained.

6. The method according to claim 1, characterized in that, The gap types include professional direction gaps and qualification level gaps; The process of identifying personnel to be trained from all risk assessment personnel based on the gap type and generating a training plan includes: If the risk index information exceeds a first preset threshold, identify at least one of the professional direction gap and qualification level gap that need to be strengthened in the corresponding professional field; if the capability gap exceeds a second preset threshold, identify at least one of the professional direction gap and qualification level gap that are corresponding to insufficient job allocation. Based on the identified gaps, trainees were selected from all risk assessment personnel. Based on the identified gaps, training content is developed and a training plan is generated.

7. The method according to claim 1, characterized in that, The process of collecting assessment and knowledge sharing data corresponding to the trainees and updating the multi-dimensional personnel competency profiles corresponding to the trainees includes: The assessment scores and practical performance of the trainees after the training are collected as assessment data, and the technical sharing materials output by the trainees are collected as knowledge sharing data. Based on the assessment data, update the historical assessment scores in the multidimensional personnel competency profile corresponding to the trainee, and based on the knowledge sharing data, update the knowledge sharing records in the multidimensional personnel competency profile corresponding to the trainee.

8. The method according to claim 2, characterized in that, The step of using a multi-objective optimization algorithm to determine the scheduling scheme corresponding to the candidate includes: Based on the multi-dimensional personnel capability profiles corresponding to the candidates, and with the optimization objectives of maximizing candidate capabilities, minimizing distance, and load balancing, the NSGA-II algorithm is used to obtain the corresponding Pareto optimal solution set, and the scheduling scheme corresponding to the candidates is determined from the Pareto optimal solution set.

9. A dynamic perception training system for data center risk assessment personnel, characterized in that, include: The data acquisition module is used to acquire operational status data of the target data center, as well as multi-dimensional personnel capability profiles for each risk assessment personnel. The first determining module is used to determine the risk index information corresponding to each professional field of the target data center based on the operational status data; The second determining module is used to determine capability gaps based on the multi-dimensional personnel capability profile, in conjunction with preset target configurations. An adaptive decision-making module is used to determine the personnel to be trained from all risk assessment personnel according to the gap type and generate a training plan when the risk index information exceeds a first preset threshold or the capability gap exceeds a second preset threshold. An execution module is used to train the personnel to be trained based on the training plan; The update module is used to collect the assessment and knowledge sharing data of the trainees after the training is completed, and update the multi-dimensional personnel capability profile of the trainees.

10. The system according to claim 9, characterized in that, The system also includes: a scheduling module; The scheduling module is used to, when an emergency scheduling task is triggered, screen candidates who meet the constraints of qualification level, professional direction, geographical location, and on-the-job scheduling based on the multi-dimensional personnel capability profile; determine the scheduling plan corresponding to the candidates using a multi-objective optimization algorithm; issue and execute the scheduling plan; and after the emergency scheduling task is completed, collect scheduling task evaluation data and update the multi-dimensional personnel capability profile corresponding to the candidates in a synchronous manner.

Images