New energy intelligent training examination system and method based on cloud rendering

Abstract

The invention relates to the technical field of new energy training, in particular to a new energy intelligent training examination system and method based on cloud rendering, and the method comprises the steps: a cloud rendering central platform system carries out the virtualization integration of graphic computing resources according to the course learning request data uploaded by a student terminal device and the type of a student access terminal; generating a computing resource allocation scheme; the post skill training assessment module generates personalized learning assessment data containing ability short board positioning according to the course interaction data of the student in the virtual simulation environment and the learning behavior data of the student; and the virtual-real fusion module fuses the virtual training environment and the real operation training scene through a data coupling engine to generate force feedback operation data synchronously updated with the real operation training scene. According to the invention, a new energy intelligent training examination system in which virtual and real operation scenes are seamlessly fused is realized, and the utilization efficiency and accurate distribution of cloud rendering platform resources are improved.

Description

Technical Field

[0001] The present invention relates to the field of new energy training technology, and in particular to a new energy intelligent training and assessment system and method based on cloud rendering. Background Art

[0002] With the rapid development of the new energy industry, the importance of its training skills has become increasingly prominent. However, the training and assessment methods of traditional new energy training skills face many challenges. At the level of traditional training models, practical training based on physical equipment is limited by equipment costs and site resources, making it difficult to achieve large-scale training. At the same time, offline theoretical training is subject to the dual constraints of time and space. Although existing digital training systems have achieved large-scale coverage at the theoretical teaching level, these systems mostly use a combination of video courseware, graphic materials and online test papers. This two-dimensional information transmission method lacks simulation of the real operating environment, which makes it difficult for students to combine theory with practice during the learning process.

[0003] Although the introduction of virtual simulation technology has alleviated the problem of the disconnect between theory and practice to a certain extent, this type of software usually requires high-performance computer support, which not only increases training costs, but also poses the risk of software resources being cracked and leaked. At the same time, existing training methods are difficult to keep up with the rapid development of the new energy industry. The existing training system lacks dynamic data docking capabilities and is unable to obtain real-time on-site data such as operating parameters and fault cases of production line equipment, resulting in a data gap between the training scenario and the actual working environment. As a result, the training content is often out of touch with the industry's most advanced workflow and cannot meet the needs of the industry's rapid development.

[0004] To sum up, there are many problems with the existing new energy training skills training and assessment methods. The current new energy training skills training field urgently needs to provide a more efficient, flexible training and assessment method that can closely combine theory and practice. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a new energy intelligent training and assessment system and method based on cloud rendering.

[0006] In a first aspect, the present invention provides a new energy intelligent training and assessment system based on cloud rendering, comprising:

[0007] The cloud rendering hub platform system is used to virtualize and integrate the graphics computing resources according to the course learning request data uploaded by the student terminal device and the student access terminal type, generate a computing resource allocation plan, and based on the computing resource allocation plan and course type characteristics, use different transmission strategies to transmit the virtual simulation environment rendering picture to the front-end interface of the student terminal device;

[0008] The post - skill training assessment module is used to quantitatively evaluate the operation standardization of new - energy training parameters, the compliance rate of standard parameters, and the data of abnormal - condition handling based on the course interaction data and the learning behavior data of trainees in the virtual simulation environment, and generate personalized learning assessment data including the positioning of ability short - boards;

[0009] The virtual - reality and real - world integration module is used to integrate the virtual training environment with the real - world operation training scenario according to the personalized learning assessment data and the real - time collected operation data of on - site training equipment through a data coupling engine, generate force - feedback operation data that is synchronized and updated with the real - world operation training scenario, and feedback the force - feedback operation data to the cloud - rendering central platform system to trigger the iterative optimization of the computing - resource allocation scheme.

[0010] In a further implementation scheme, the cloud - rendering central platform system includes a computing - resource dynamic scheduling module, a cloud - rendering course - image transmission module, a human - environment - equipment data integration module, and a spatial - computing course recommendation module;

[0011] The spatial - computing course recommendation module is used to recommend a list of training - project courses with the shortest straight - line distance in space according to the geographical location information or spatial distribution information of trainees, and generate course - learning request data when trainees select a target training - project course according to all the training - project course lists;

[0012] The computing - resource dynamic scheduling module is used to identify the type of trainee access terminal according to the course - learning request data uploaded by the trainee terminal device, and dynamically schedule graphic computing resources from the server resource pool to run various basic courses based on the trainee access terminal type and the computing - resource requirements of various basic courses, and generate a computing - resource allocation scheme;

[0013] The cloud - rendering course - image transmission module is used to perform streaming - media encoding processing on the rendering screen of the virtual simulation environment according to the characteristics of the course type to be learned, generate an encrypted rendering data stream, and transmit the encrypted rendering data stream to the front - end interface of the trainee terminal device through the computing - resource allocation scheme;

[0014] The human - environment - equipment data integration module is used to perform real - time update and structured - knowledge integration on the dynamic background data and trainee - learning associated information involved in the post - training assessment course.

[0015] In a further implementation scheme, when the characteristics of the course type to be learned are theoretical courses, the encrypted rendering data stream is transmitted to the front - end interface of the trainee terminal device through a remote - encryption access mode;

[0016] When the characteristics of the course type to be learned are practical courses, the encrypted rendering data stream is transmitted to the front - end interface of the trainee terminal device through a cloud - rendering mode;

[0017] When the type feature of the course to be learned is an assessment course, the encrypted rendering data stream is transmitted to the front-end interface of the trainee terminal device through the front-end encryption display mode.

[0018] In a further embodiment, the spatial computing course recommendation module includes a spatial positioning unit, a distance calculation unit, and a course recommendation unit;

[0019] The spatial positioning unit is used to extract new energy training equipment instrument feature information, parameter identification information, and operating environment information from the current environment information uploaded by the trainee terminal device, generate a structured device positioning feature data set, and associate and match the structured device positioning feature data set with a preset new energy training equipment parameter database to generate positioning point data;

[0020] The distance calculation unit is used to determine the shortest straight-line distance in space between the trainee and the new energy training equipment according to the new energy training equipment spatial coordinate information and the trainee terminal IP address in the positioning point data;

[0021] The course recommendation unit is used to retrieve the post skill training assessment course database according to the shortest straight-line distance in space, and sort the retrieval results according to the device association degree weight to obtain a training project course list.

[0022] In a further embodiment, the computing resource dynamic scheduling module includes a computing cluster unit, a resource pool unit, and a dynamic scheduling unit composed of multiple cloud rendering servers;

[0023] The resource pool unit is used to virtualize and integrate the physical server cluster in the computing cluster unit according to the pre-acquired server performance parameters to form a dynamically allocable resource pool;

[0024] The dynamic scheduling unit is used to generate an initial resource allocation plan through an iterative optimization algorithm according to the historical training scale and the single-course resource demand matrix, and monitor the number of waiting people in the course reservation queue and the current resource utilization rate in real time according to the initial resource allocation plan. When it is detected that the current resource utilization rate exceeds the resource pool capacity, reallocate resources according to the course weight priority, and send an elastic expansion instruction to the administrator.

[0025] In a further embodiment, the human-environment-device data integration module includes a data integration unit, a data mapping unit, a data update unit, and a large model intelligent unit;

[0026] The data integration unit is used to collect trainee basic information, post curriculum system, curriculum learning status data, new energy training equipment parameters, and training environment parameters to form a structured data set;

[0027] The data mapping unit is used to perform real-time update and structured knowledge integration on the dynamic background data and trainee learning association information involved in the post training assessment courses according to the structured data set, and generate a standardized long text question based on the new energy training scenario;

[0028] The large model intelligent unit is used to analyze the standardized long text question and generate a new energy training solution;

[0029] The data update unit is used to update all materials of people, equipment and environment involved in the post training assessment courses according to the new energy training solution.

[0030] In a further implementation plan, the post skill training assessment module includes a post course pool unit, a peripheral compatibility unit and a learning evaluation unit;

[0031] The post course pool unit is connected to the cloud rendering central platform system, and is used to store the new energy training basic course data set based on the distributed database architecture, add different post tags to the new energy training basic course data set, and set a dependency unlocking relationship for the new energy training basic courses with the same post tags;

[0032] The learning evaluation unit is used to calculate the learning activity, learning score and performance ranking of the trainee according to the learning behavior data of the trainee in each learning link, and generate personalized learning evaluation data including ability short board analysis according to the learning behavior data, learning activity, learning score and performance ranking;

[0033] The peripheral compatibility unit establishes a two-way data channel with the third-party training equipment and the cloud rendering central platform. The peripheral compatibility unit is used to automatically load the corresponding new energy training equipment driver according to the communication protocol type of the third-party training equipment, communicate with the cloud rendering central platform system, and transmit the data obtained from the third-party training equipment to the cloud rendering central platform system.

[0034] In a further implementation plan, the new energy training basic course data set includes structured course resources, virtual simulation programs and peripheral driver components;

[0035] The structured course resources include digital files of new energy training principle courseware, new energy training equipment operation videos and new energy training regulation test papers;

[0036] The virtual simulation programs include new energy training process virtual simulation software and non-standard training scenario simulators;

[0037] The peripheral driver components include dynamic link library files and automated deployment scripts required by the third-party training equipment training software.

[0038] In a further embodiment, the virtual-real fusion module includes a data coupling unit, a force feedback operation unit, and a virtual-real update unit;

[0039] The data coupling unit is used to establish a data communication link with the on-site training device through an industrial communication protocol, and to obtain in real time the operation parameters of the new energy training device, the training environment parameters, and the new energy training indicators, so as to form the operation data of the on-site training device;

[0040] The force feedback operation unit is used to generate force feedback operation data that is synchronously updated with the real operation training scenario according to the operation data of the on-site training device through a force feedback device;

[0041] The virtual-real update unit is used to dynamically update the basic course content of new energy training according to the operation data of the on-site training device and the current virtual scene parameters.

[0042] In a second aspect, the present invention provides a new energy intelligent training and assessment method based on cloud rendering. The method includes the following steps:

[0043] Perform virtualization integration processing on the graphics computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, and generate a computing resource allocation plan;

[0044] Based on the computing resource allocation plan and the course type characteristics, use different transmission strategies to transmit the rendered image of the virtual simulation environment to the front-end interface of the trainee terminal device;

[0045] Quantitatively evaluate the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the abnormal condition handling data according to the course interaction data and the trainee learning behavior data of the trainee in the virtual simulation environment, and generate personalized learning assessment data including the positioning of ability shortboards;

[0046] According to the personalized learning assessment data and the operation data of the on-site training device collected in real time, fuse the virtual training environment with the real operation training scenario through a data coupling engine, and generate force feedback operation data that is synchronously updated with the real operation training scenario;

[0047] Feed the force feedback operation data back to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan.

[0048] The present invention provides a new energy intelligent training and assessment system and method based on cloud rendering. The system includes a cloud rendering central platform system for virtualizing and integrating graphic computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, generating a computing resource allocation scheme, and based on the computing resource allocation scheme and the course type characteristics, using different transmission strategies to transmit the rendered image of the virtual simulation environment to the front-end interface of the trainee terminal device; a post skill training and assessment module for quantitatively evaluating the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the abnormal condition handling data according to the course interaction data and the trainee learning behavior data of the trainee in the virtual simulation environment, generating personalized learning assessment data including the positioning of ability shortboards; a virtual-real fusion module for fusing the virtual training environment with the real operation training scenario according to the personalized learning assessment data and the real-time collected operation data of the on-site training equipment through a data coupling engine, generating force feedback operation data that is synchronized and updated with the real operation training scenario, and feeding back the force feedback operation data to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation scheme. Compared with the prior art, through the collaborative work of the cloud rendering central platform system, the post skill training and assessment module, and the virtual-real fusion module, the system realizes a new energy training system with seamless integration of virtual and real operation scenarios, significantly improving the utilization efficiency and precise allocation of cloud rendering platform resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a block diagram of a new energy intelligent training and assessment system based on cloud rendering provided by an embodiment of the present invention;

[0050] Figure 2 is a specific embodiment diagram of a new energy intelligent training and assessment system provided by an embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of the course recommendation process for trainee space positioning provided by an embodiment of the present invention;

[0052] Figure 4 is a schematic diagram of the process for generating personalized learning assessment data provided by an embodiment of the present invention;

[0053] Figure 5 is a schematic diagram of the process of a new energy intelligent training and assessment method based on cloud rendering provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The embodiments of the present invention will be specifically described below in conjunction with the drawings. The given embodiments are only for illustrative purposes and should not be construed as a limitation of the present invention. The drawings are only for reference and illustration and do not constitute a limitation on the protection scope of the present invention patent, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0055] Reference Figure 1 , an embodiment of the present invention provides a new energy intelligent training and assessment system based on cloud rendering, as Figure 1 shown, the system includes a cloud rendering central platform system 101, a post skill training and assessment module 102, and a virtual-real fusion module 103.

[0056] In some embodiments, the cloud rendering central platform system is used to perform virtualization integration processing on graphics computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, generate a computing resource allocation plan, and based on the computing resource allocation plan and the course type characteristics, use different transmission strategies to transmit the virtual simulation environment rendering screen to the front-end interface of the trainee terminal device, as Figure 2 shown, the cloud rendering central platform system includes a computing resource dynamic scheduling module, a cloud rendering course image transmission module, a human-environment-device data integration module, and a spatial computing course recommendation module. The specific function descriptions are as follows:[[]]

[0057] The spatial computing course recommendation module is used to recommend a list of training project courses with the shortest straight-line distance in space according to the geographical location information or spatial distribution information of the trainees, and generate course learning request data when the trainees select the target training project course according to all the training project course lists;

[0058] The computing resource dynamic scheduling module is used to identify the trainee access terminal type according to the course learning request data uploaded by the trainee terminal device, and based on the trainee access terminal type and the computing resource requirements of various basic courses, dynamically schedule graphics computing resources from the server resource pool to run various basic courses, and generate a computing resource allocation plan;

[0059] The cloud rendering course image transmission module is used to perform streaming media encoding processing on the virtual simulation environment rendering screen according to the characteristics of the course to be learned, generate an encrypted rendering data stream, and transmit the encrypted rendering data stream to the front-end interface of the trainee terminal device through the computing resource allocation plan;

[0060] The human-environment-device data integration module is used to perform real-time update and structured knowledge integration on the dynamic background data and trainee learning association information involved in the post training and assessment courses.

[0061] Specifically, when the cloud rendering central platform system receives learning requests from students for different basic courses, in this embodiment, the system first intelligently identifies the type of access terminal used by the students. Subsequently, the system flexibly schedules corresponding computing resources from the server resource pool to run the courses. The courses that can be specifically run include diverse basic courses such as courseware display, video tutorials, online tests, virtual simulation training, and third-party peripheral hands-on operations. Each course content is equipped with a specific instantiated script to ensure its efficient operation. The real-time images during the course operation are transmitted through the network to the front-end interface of the student terminal device. After the students complete various interaction operations, the system immediately collects relevant human-environment-equipment course learning data. After synchronizing, filtering, integrating, and analyzing and evaluating these human-environment-equipment course learning data, an evaluation result is generated to guide the students to strengthen their learning of the courses they have mastered poorly, and it can quickly respond to the students' questions at any time, providing instant question-answering services, comprehensively improving the learning efficiency and experience of the students. Based on the above embodiment, in a more specific embodiment, the spatial computing course recommendation module includes a spatial positioning unit, a distance calculation unit, and a course recommendation unit. The functions of each unit of the spatial computing course recommendation module are specifically as follows:

[0062] The spatial positioning unit is used to extract new energy training equipment instrument feature information, parameter identification information, and operation environment information from the current environment information uploaded by the student terminal device, generate a structured device positioning feature data set, and associate and match the structured device positioning feature data set with a preset new energy training equipment parameter database to generate positioning point data;

[0063] The distance calculation unit is used to determine the shortest straight-line distance in space between the student and the new energy training equipment according to the new energy training equipment spatial coordinate information and the student terminal IP address in the positioning point data;

[0064] The course recommendation unit is used to retrieve the job skill training and assessment course database according to the shortest straight-line distance in space and sort the retrieval results according to the equipment association degree weight to obtain a training project course list.

[0065] Specifically, the spatial computing course recommendation module establishes a two-way communication connection with the job skill training and assessment module and the human-environment-equipment data integration module through data interfaces respectively. For example, when the course recommendation unit retrieves relevant courses, it can directly access the course database in the job skill training and assessment module, such as Figure 3As shown, when a trainee uses a terminal device to access the cloud rendering center platform system, the trainee can upload photos, videos, or text information of the current on-site environment through the terminal device (such as a mobile phone, tablet, or computer), or the system obtains the geographical location information of the trainee through the positioning function (such as GPS, Wi-Fi positioning, etc.) or IP address resolution of the terminal device. The spatial positioning unit performs image recognition and text analysis on the photos, videos, or text information of the current on-site environment uploaded by the trainee, identifies the new energy training equipment feature information, parameter identification information, and operating environment information from the photos, videos, and text, saves the identified information as a structured device positioning feature data set, and associates and matches the structured device positioning feature data set with a preset new energy training equipment parameter database to generate positioning point data. The positioning point data includes human-environment-equipment association data such as the spatial coordinate information of the new energy training equipment, the parameters of the new energy training equipment, and the associated courses of the new energy training equipment. For example, after successful matching, it is determined that the new energy training equipment near the trainee's location is a certain specific model of new energy training performance tester, and its spatial coordinates are (X, Y, Z).

[0066] Then the distance calculation unit reads the positioning point data generated by the spatial positioning unit, simultaneously reads the IP address and its positioning information of the trainee's terminal device (which can be obtained through IP address resolution), and calculates the shortest straight-line distance in space between the new energy training equipment and the trainee's location in combination with the positioning point data, the IP address of the trainee's terminal, and its positioning information. The course recommendation unit retrieves relevant courses in the post skill training assessment module according to the shortest straight-line distance in space provided by the distance calculation unit, and the retrieval results are sorted according to the equipment association degree weight to form a training project course list, that is, the higher the association degree of the course with the new energy training equipment near the trainee's current location, the higher the ranking. The sorted course list is displayed to the trainee in a highlighted display or sorted by priority, etc. The trainee views the recommended course list on the access page and selects the target training project course according to personal interests and needs. After selecting the target training project course, the system generates course learning request data including information such as course ID, trainee ID, and trainee terminal type, and sends the course learning request data to the computing resource dynamic scheduling module.

[0067] Based on the above embodiments, in a more specific embodiment, the computing resource dynamic scheduling module includes a computing cluster unit, a resource pool unit, and a dynamic scheduling unit composed of multiple cloud rendering servers. The functions of each unit of the computing resource dynamic scheduling module are specifically as follows:

[0068] The resource pool unit is used to virtualize and integrate the physical server cluster in the computing cluster unit according to the pre-obtained server performance parameters to form a dynamically allocable resource pool;

[0069] The dynamic scheduling unit is used to generate an initial resource allocation plan according to the historical training scale and the single-course resource demand matrix through an iterative optimization algorithm, and monitor the number of people waiting in the course reservation queue and the current resource utilization rate in real time according to the initial resource allocation plan. When it detects that the current resource utilization rate exceeds the resource pool capacity, it reallocates resources according to the course weight priority and sends an elastic expansion instruction to the administrator.

[0070] Specifically, due to the fragmentation, unpredictability of computing resource scheduling requirements, and randomness of peripheral access, in this embodiment, the server computing resource capacity can be preset for various basic courses first. After receiving the learning requests submitted by students and their possible third-party peripheral input data, computing resources are called from the preset resource pool, and the learning situation of students is evaluated after a fixed time interval, and the server computing resource capacity is re-divided. Among them, the computing resource dynamic scheduling module analyzes the student terminal type information in the course learning request data to determine the device type used by the student, and according to the type of the selected course (such as new energy training foundation, advanced test technology, etc.) and the pre-defined amount of graphics computing resources required for each course (such as CPU, GPU, memory, etc.), corresponding graphics computing resources are dynamically allocated from the server resource pool to ensure that the selected course can run smoothly, and a computing resource allocation plan including information such as resource ID, allocation time, and expected usage duration is generated. In this embodiment, the computing cluster unit is a server cluster composed of multiple cloud rendering servers, and each server is equipped with computing resources such as a large-capacity CPU, a high-performance GPU, sufficient memory, and high-speed network bandwidth. According to the server performance parameters obtained in advance (such as CPU frequency, GPU computing power, memory size, and network bandwidth, etc.), this embodiment virtualizes and merges the computing resources in the server cluster through the resource pool unit to form a dynamically allocable resource pool, which is convenient for the dynamic scheduling unit to perform unified allocation and scheduling.

[0071] The dynamic scheduling unit collects the computing resource requirements of existing basic courses. For example, a courseware display course requires relatively low GPU computing power and medium network bandwidth, while a virtual simulation course requires relatively high GPU computing power and large-capacity memory. The dynamic scheduling unit constructs a dynamic scheduling relationship based on the computing resource requirements of these existing basic courses, that is, the corresponding relationship between the types of computing resources virtualized by the resource pool unit and various basic courses. Among them, in this embodiment, it is assumed that the set of computing resources virtualized by the resource pool unit is X = {x1, x2,..., x p}, and the number of various basic courses that support simultaneous online operation is S = {s1, s2,..., s r}, and the demand for each course is A = {a1, a2,... a m} computing resources. In this embodiment, an initial resource pool S1 = M0(X, S0, A, K) is preset, where S0 represents the number of various basic courses that run online simultaneously, which is evaluated by the administrator according to the number of trainees to be trained and the distribution of training courses; M0(*) is the initial planning algorithm of the resource scheduling unit, and the number S1 of courses that are close to S0 and run online simultaneously supported by the computing cluster unit is obtained through iterative optimization based on the initial parameters; K represents a preset course category weight table to ensure the lower limit of the number of each type of basic course that can run simultaneously.

[0072] The dynamic scheduling unit constructs a dynamic scheduling relationship according to the computing resource requirements of the existing basic courses, that is, determines the types and quantities of computing resources virtualized by the resource pool unit, as well as the number of various basic courses that support simultaneous online operation. According to the number of various basic courses that run online simultaneously evaluated by the administrator, based on S0 and course requirements A, the number S1 of courses that are close to S0 and run online simultaneously supported by the computing cluster unit is obtained through iterative optimization using the initial planning algorithm M0(*). The initial planning algorithm can find the number S1 of courses that are closest to S0 and can support simultaneous online operation under the existing computing cluster resources by simulating different resource allocation combinations. At the same time, a preset course category weight table K is introduced to ensure the lower limit of the number of each type of basic course that can run simultaneously. For example, for important virtual simulation courses, the weight is higher to ensure that at least a certain number of instances can run simultaneously. In this embodiment, an initial resource allocation plan is generated according to the optimized S1. The initial resource allocation plan includes the computing resource quantity and corresponding server resources allocated to each course. For example, a certain number of CPU cores and network bandwidth are allocated to the courseware display course, and more GPU computing power and memory are allocated to the virtual simulation course.

[0073] After the dynamic scheduling unit starts the course learning service according to the initial resource allocation plan, it real-time monitors the number of waiting people in the course reservation queue. During the real-time monitoring stage, when it is detected that the current resource utilization rate exceeds the resource pool capacity, for example, the CPU usage rate reaches more than 90%, and the memory usage rate is also close to saturation, the resources are reallocated according to the course weight priority. According to the preset course category weight table K, the resource requirements of important courses (such as virtual simulation courses) are preferentially guaranteed, and some resources are appropriately recycled from other non-critical courses (such as courseware display courses). At the same time, between adjacent reservation periods, the reservation quantities W n ={s1, s2,..., s q} of various basic courses in the next reservation period are collected. According to the reservation requirements in the next reservation period and the computing resource requirements B = {b1, b2,..., b t} of each course, the number S n of courses that are close to W n and run online simultaneously supported by the computing cluster unit is calculated using the dynamic programming algorithm., if the dynamic programming algorithm can be used to solve S n , then according to S n Re-adjust resource allocation. If the dynamic programming algorithm cannot solve S n , indicating that the current resources are insufficient to meet all reservation needs, a resource pool that meets the resources will be set according to the preset course category weight table for students to make reservations. The reservation needs that exceed the limit will remind the administrator to urgently expand the computing cluster unit. If the expansion fails, the reservations will be canceled in order and the corresponding students will be reminded to make reservations for a later time period.

[0074] Based on the above embodiments, in a more specific embodiment, the cloud rendering course image transmission module is connected to the job skills training and assessment module. When the student initiates a learning demand on the front-end interface of the cloud rendering central platform system, the cloud rendering course image transmission module receives the request, and determines the type of course selected by the student by analyzing the course identification information in the request. For example, if the student selects a new energy battery structure principle courseware course, the module identifies it as a courseware type; if the selected course is a new energy battery troubleshooting virtual simulation course, it is identified as a virtual simulation course; then the corresponding image transmission method is determined according to the identified course type. When the type of course to be learned is characterized as a theoretical course, the encrypted rendering is transmitted through the remote encrypted access mode. The data stream is transmitted to the front-end interface of the student terminal device; when the type feature of the course to be studied is a practical course, the encrypted rendering data stream is transmitted to the front-end interface of the student terminal device through the cloud rendering mode; when the type feature of the course to be studied is an assessment course, the encrypted rendering data stream is transmitted to the front-end interface of the student terminal device through the front-end encrypted display mode. For example, for courseware and video courses, the cloud rendering course image transmission module adopts remote encrypted access; for test paper courses, the student terminal device front-end encrypted display is adopted to ensure that the test paper content is not leaked; peripheral training courses and virtual simulation courses require real-time rendering and high-performance computing resources, so cloud rendering is used to remotely transmit images.

[0075] The cloud rendering central platform launches the corresponding virtual simulation environment according to the learning needs of the trainees. The rendered images of the environment are captured in real time by a specific capture tool. The captured rendered images are processed by a streaming media encoder, and the continuous image frames are encoded into a streaming media format (such as H.264, H.265, etc.) to reduce the transmission bandwidth and improve the playback fluency. After the streaming media encoding is completed, the generated rendered data stream is encrypted. An encryption algorithm (such as the AES encryption algorithm) is used to encrypt the video stream data to generate an encrypted rendered data stream to ensure the security of the data during transmission. The encryption key is uniformly managed by the cloud rendering central platform system and transmitted to the trainee terminal device through a secure channel. In this embodiment, according to the computing resource allocation scheme generated by the computing resource dynamic scheduling module, the priority of data transmission and bandwidth allocation are determined. For example, for a virtual simulation course with a higher allocated priority, it is ensured that its encrypted rendered data stream can obtain sufficient network bandwidth during transmission to ensure a smooth transmission effect. The encrypted rendered data stream is transmitted to the front-end interface of the trainee terminal device through a network transmission protocol and a data distribution strategy. The trainee can watch the rendered images of the virtual simulation environment in real time and conduct interactive learning and training.

[0076] Based on the above embodiment, in a more specific embodiment, the human-environment-device data integration module includes a data integration unit, a data mapping unit, a data update unit, and a large model intelligent unit. The functions of each unit of the human-environment-device data integration module are specifically as follows:

[0077] The data integration unit is used to collect the basic information of the trainees, the post curriculum system, the course learning status data, the new energy training equipment parameters, and the training environment parameters to form a structured data set;

[0078] The data mapping unit is used to perform real-time update and structured knowledge integration on the dynamic background data and trainee learning association information involved in the post training assessment course according to the structured data set, and generate a standardized long text question based on the new energy training scenario;

[0079] The large model intelligent unit is used to analyze the standardized long text question and generate a new energy training solution;

[0080] The data update unit is used to update all the materials of the people, equipment, and environment involved in the post training assessment course according to the new energy training solution.

[0081] Specifically, the human-environment-equipment data integration module is connected to the job skill training and assessment module. This human-environment-equipment data integration module mainly includes four core units: a data integration unit, a data mapping unit, a data update unit, and a large model intelligent unit. Among them, the data update unit is connected to the job skill training and assessment module. The data update unit receives in real time data such as course update information, student learning dynamics, and work environment changes from the job skill training and assessment module. At the same time, the data update unit checks and updates in real time all background materials of people, equipment, and environment involved in the job training and assessment courses to ensure the accuracy and timeliness of the background materials; the data mapping unit pre-establishes the mapping relationship between job training and assessment courses and relevant information, including the association between courses and equipment, the association between courses and work environments, the association between courses and students' positions, etc. When a student starts learning a certain job training and assessment course, the data mapping unit quickly retrieves all information associated with this course according to the course identification information, providing a basis for subsequent data integration and analysis; the data integration unit organizes knowledge such as students' basic information, job course systems, course learning situations, and work environments into several long text questions. For example, the following long text questions are generated:

[0082] [Prompt words restricting the capabilities of the large model], student basic information H is learning job course J for new energy battery maintenance. The learning situation of this student is Q, and the work background, equipment, and process knowledge involved are V. Please summarize the current learning situation of this student, [prompt words restricting the capabilities of the large model].

[0083] [Prompt words restricting the capabilities of the large model], student basic information H is learning job course J for new energy battery maintenance. The learning situation of this student is Q, and the work background, equipment, and process knowledge involved are V. Please analyze the reasons for the mistakes made by this student and suggestions for improvement, [prompt words restricting the capabilities of the large model].

[0084] [Prompt words restricting the capabilities of the large model], student basic information H is learning job course J for new energy battery maintenance. The learning situation of this student is Q, and the work background, equipment, and process knowledge involved are V. If the ability and accomplishment of this student to hold this position are represented by scores from 0 to 100, please accurately evaluate the current score of this student and give the evaluation basis, [prompt words restricting the capabilities of the large model].

[0085] [Prompt words restricting the capabilities of the large model], student basic information H is learning job course J for new energy battery maintenance. The learning situation of this student is Q, and the work background, equipment, and process knowledge involved are V. Currently, problem T is encountered. Please help me analyze the possible reasons for the formation of problem T, which courses need to be learned, and give all possible methods to solve this problem, [prompt words restricting the capabilities of the large model].

[0086] After receiving the long-text question generated by the large model intelligent unit, the data integration unit first performs semantic analysis and key information extraction on the question. For example, for the question of summarizing the learning situation of students, the large model intelligent unit extracts key information such as the basic information of the students, the course learning situation, and the relevant work background, and conducts in-depth analysis and answers to the long-text question. The output result of the large model intelligent unit will be directly fed back to the students or instructors to help them better understand the learning situation, discover problems, and seek solutions.

[0087] In some embodiments, the post skill training assessment module is used to quantitatively evaluate the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the data for handling abnormal conditions based on the course interaction data and the learning behavior data of students in the virtual simulation environment, and generate personalized learning assessment data including the positioning of ability shortboards. In this embodiment, the post skill training assessment module includes a post course pool unit, a peripheral compatibility unit, and a learning evaluation unit. The specific function descriptions are as follows:

[0088] The post course pool unit is connected to the cloud rendering central platform system, and is used to store the new energy training basic course data set based on the distributed database architecture, add different post tags to the new energy training basic course data set, and set a dependency unlocking relationship for the new energy training basic courses with the same post tag;

[0089] The learning evaluation unit is used to calculate the learning activity, learning points, and grade ranking of students based on the learning behavior data of students in each learning link, and generate personalized learning assessment data including the analysis of ability shortboards based on the learning behavior data, learning activity, learning points, and grade ranking;

[0090] The peripheral compatibility unit establishes a two-way data channel with the third-party training device and the cloud rendering central platform. The peripheral compatibility unit is used to automatically load the corresponding new energy training device driver according to the communication protocol type of the third-party training device, communicate with the cloud rendering central platform system, and transmit the data obtained from the third-party training device to the cloud rendering central platform system.

[0091] Specifically, the post skill training and assessment module is connected to the cloud rendering course image transmission module, the computing resource dynamic scheduling module, and the human-environment-equipment data integration module. The post course pool unit stores the new energy training basic course data set using a distributed database architecture. This architecture can efficiently process a large amount of course data and ensure the high availability and scalability of the data. The new energy training basic course data set includes structured course resources, virtual simulation programs, and peripheral driver components. The structured course resources include new energy training principle courseware (in PDF format), new energy training equipment operation videos, and digitalized files of new energy training regulation test papers. The virtual simulation programs include new energy training process virtual simulation software and non-standard training scenario simulators. The peripheral driver components include dynamic link library files and automated deployment scripts required for third-party training equipment training software. Specifically, these new energy training basic course data sets include courseware, videos, test papers, process virtual simulation software, third-party peripheral training software, scenario simulator software, etc. The administrator will add different post tags to various basic courses. For example, for the new energy battery maintenance post, post tags such as "Battery Maintenance Basics", "Battery Performance Testing", and "Battery Fault Troubleshooting" are set, and a dependency unlocking relationship is set for courses with the same post tag, so that students must complete the previous stage of the course to unlock the next stage of the course. For example, when a student completes the "New Energy Production Basic Knowledge" course, the system will unlock the "New Energy Production Operation Process" course. Only when the previous stage of the basic course is completed can the unlocking condition for the next stage of the basic course be met, and students can start learning the next stage of the course, avoiding knowledge gaps caused by skipping learning.

[0092] The running program of the peripheral compatibility unit, that is, the data transceiver plug-in, is installed on the student terminal device. This plug-in can establish a communication relationship for interactive input data with third-party peripherals and the cloud rendering central platform system. When a student uses a third-party training device for training, the peripheral compatibility unit automatically loads the corresponding new energy training device driver according to the communication protocol type of the third-party training device. After loading the driver, the peripheral compatibility unit communicates with the cloud rendering central platform system, so that the data obtained by the student during the training can be transmitted to the cloud rendering central platform system in real time for subsequent analysis and evaluation.

[0093] Such as Figure 4As shown, the learning evaluation unit is a key part of the on-the-job skill training assessment module. It calculates the learning activity, learning points, and performance ranking of students based on the learning behavior data of students in each learning session. These data not only reflect the learning progress and performance of students but also provide a basis for subsequent personalized learning assessment. To generate personalized learning assessment data including an analysis of ability shortfalls, the learning evaluation unit uses the data integration unit and the large model intelligent unit to generate the current learning report of students in real time. Among them, the data integration unit is responsible for integrating the course interaction data, learning behavior data of students in the virtual simulation environment, as well as the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the data of abnormal condition handling. The large model intelligent unit will conduct in-depth analysis of these data, identify the ability shortfalls of students, and generate personalized learning suggestions. For example, it points out that students have ability shortfalls such as non-standard operations and inaccurate parameter settings in handling a certain specific type of battery fault diagnosis. In summary, when generating personalized learning assessment data, the learning evaluation unit comprehensively considers the learning activity, learning points, performance ranking of students, and the analysis results of the large model intelligent unit to obtain a comprehensive learning report, which shows the learning progress, performance, ability shortfalls, and improvement suggestions of students. Administrators can view the learning reports of all students through the system background to understand the overall learning situation and existing problems of students. Students can also view their own learning reports at any time to understand their learning situation and make adjustments and improvements according to the suggestions.

[0094] In some embodiments, the virtual-real fusion module is used to fuse the virtual training environment with the real operation training scenario through a data coupling engine according to the personalized learning assessment data and the real-time collected operation data of on-site training equipment, generate force feedback operation data that is synchronized and updated with the real operation training scenario, and feedback the force feedback operation data to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation scheme. In this embodiment, the virtual-real fusion module includes a data coupling unit, a force feedback operation unit, and a virtual-real update unit. The specific function descriptions are as follows:

[0095] The data coupling unit is used to establish a data communication link with on-site training equipment through an industrial communication protocol and obtain the operation parameters of new energy training equipment, training environment parameters, and new energy training indicators in real time to form on-site training equipment operation data;

[0096] The force feedback operation unit is used to generate force feedback operation data that is synchronized and updated with the real operation training scenario through a force feedback device according to the on-site training equipment operation data;

[0097] The virtual-real update unit is used to dynamically update the basic course content of new energy training according to the on-site training equipment operation data and the current virtual scene parameters.

[0098] Specifically, the data coupling unit is software that runs on the cloud rendering platform in the long term and can only be operated by the administrator. The data coupling unit establishes a stable communication link with on-site new energy training equipment through industrial communication protocols. It can integrate the virtual training environment with the real operation training scenario through data synchronization and scenario mapping technologies. The administrator can configure parameters such as device addresses and communication protocols on the data coupling interface to ensure the smooth transmission of data. Then, in this embodiment, the data coupling unit parses the data received from the on-site training equipment in real time, extracts the operation parameters of the new energy training equipment, training environment parameters, and new energy training indicators, and organizes these data into the operation data of the on-site training equipment. At the same time, the data coupling unit can integrate the received personalized learning evaluation data and the operation data of the on-site training equipment. Through technologies such as data cleaning, data conversion, and data association, the data in the virtual training environment is matched and supplemented with the data in the real operation training scenario.

[0099] The force feedback operation unit depends on the force feedback virtual simulation software loaded by the cloud rendering central platform system and the force feedback device connected to the force feedback virtual simulation software. The trainee terminal device is interconnected with the cloud rendering platform through the force feedback device (such as a force feedback handle, force feedback glove, etc.). The force feedback operation unit generates force feedback operation data that is synchronized and updated with the real operation training scenario according to the operation data of the on-site training equipment through the force feedback device. For example, when the on-site training equipment detects the reaction force generated during battery maintenance, the force feedback operation unit converts information such as the magnitude and direction of this force into force feedback simulation data. The force feedback virtual simulation software controls the force feedback device to simulate the corresponding operation feel based on these data. For example, when a trainee uses a force feedback handle to simulate battery maintenance in the virtual simulation environment, the handle will apply a corresponding force to the trainee's hand according to the force feedback data in the virtual scenario, allowing the trainee to feel the real maintenance operation feel. These force feedback operation data are synchronized and updated with the real operation training scenario to ensure that the trainee can experience the same operation feel as the real scenario. In this embodiment, the generated force feedback operation data is transmitted through the network and fed back to the cloud rendering central platform system. After receiving these data, the cloud rendering central platform system can use them as new inputs to analyze factors such as the operation complexity of the trainee in the virtual simulation environment and the real-time requirements of the force feedback data, and re-evaluate the current computing resource allocation plan. The computing resource dynamic scheduling module iteratively optimizes the computing resource allocation plan according to the fed-back force feedback operation data. By analyzing the operation situation of the trainee in the virtual simulation environment and the real-time requirements of the force feedback data, the allocation of computing resources is adjusted to better meet the training needs.

[0100] The virtual-real update unit is software that runs on the cloud rendering platform in the long term and can only be operated by administrators. The administrator logs in to the management interface of the cloud rendering platform through the security authentication mechanism and starts the virtual-real update unit. The virtual-real update unit virtualizes the on-site operation environment into a virtual scene, constructs a virtual simulation scene consistent with the real environment. Each virtual simulation course is a local operation process of the virtual scene. When there is a deviation between the course system of the cloud rendering central platform system and the on-site operation environment, the virtual-real update unit starts the course system update process. For example, a new type of battery testing device is added to the on-site operation environment, but there is no corresponding training content in the course system of the cloud rendering platform. At this time, the virtual-real update unit analyzes the course content that needs to be updated based on the on-site training device operation data and the current virtual scene parameters, and then uses the large model intelligent unit to automatically update the new energy training basic course content in the virtual simulation course to ensure the synchronous update of the training system and the on-site operation environment.

[0101] In summary, in this embodiment, by adopting the dynamic scheduling method, computing resources are automatically allocated to various basic courses within each reservation period, thus significantly increasing the number of concurrent online courses on the cloud rendering platform. At the same time, students can now access the cloud rendering platform to learn relevant courses through any configured terminal device and third-party peripherals, breaking traditional restrictions such as venue scale, device performance, and students' free time, making learning more flexible and convenient. Secondly, by introducing the human-environment-device data integration module, this embodiment can uniformly describe the learning situation of students during the learning process of different post course systems in text and generate exclusive learning analysis, evaluation, answers, and suggestion reports in real time. These reports can enable students to timely discover and make up for learning gaps during the theoretical knowledge, virtual simulation, and practical learning and training processes, so as to conduct targeted intensive learning at the weak points of skill mastery. Finally, when students encounter problems, the space calculation course recommendation module in this embodiment can parse this information by using the human-environment-device data integration module through the photos, videos recorded, or text descriptions uploaded by the students about the problems they encounter, and use the space positioning unit and distance calculation unit to determine the positional relationship between the students and the problems, and then recommend relevant post course system content for the students to learn and solve problems on-site.

[0102] An embodiment of the present invention provides a new energy intelligent training and assessment system based on cloud rendering. The system includes a cloud rendering central platform system for virtualizing and integrating graphic computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, and generating a computing resource allocation plan; a job skill training and assessment module for quantitatively evaluating the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the abnormal condition handling data based on the course interaction data and trainee learning behavior data of the trainee in the virtual simulation environment, and generating personalized learning assessment data including the positioning of ability shortboards; a virtual-real fusion module for fusing the virtual training environment with the real operation training scenario through a data coupling engine according to the personalized learning assessment data and the real-time collected operation data of on-site training equipment, generating force feedback operation data that is synchronized and updated with the real operation training scenario, and feeding back the force feedback operation data to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan. Compared with the prior art, through the collaborative work of the cloud rendering central platform system, the job skill training and assessment module, and the virtual-real fusion module, the system realizes a new energy intelligent training and assessment system with seamless integration of virtual and real operation scenarios, significantly improving the utilization efficiency and precise allocation of cloud rendering platform resources.

[0103] In one embodiment, as Figure 5 shown, an embodiment of the present invention provides a new energy intelligent training and assessment method based on cloud rendering. The method includes the following steps:

[0104] S1. Virtualize and integrate graphic computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, and generate a computing resource allocation plan;

[0105] S2. Based on the computing resource allocation plan and course type characteristics, use different transmission strategies to transmit the rendered image of the virtual simulation environment to the front-end interface of the trainee terminal device;

[0106] S3. Quantitatively evaluate the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the abnormal condition handling data based on the course interaction data and trainee learning behavior data of the trainee in the virtual simulation environment, and generate personalized learning assessment data including the positioning of ability shortboards;

[0107] S4. According to the personalized learning assessment data and the real-time collected operation data of on-site training equipment, fuse the virtual training environment with the real operation training scenario through a data coupling engine, and generate force feedback operation data that is synchronized and updated with the real operation training scenario;

[0108] S5. Feed back the force feedback operation data to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan.

[0109] It should be noted that the sequence numbers of the above processes do not indicate the order of execution. The execution order of each process should be determined by its function and internal logic, and should not impose any limitation on the implementation process of the embodiments of this application.

[0110] For the specific limitations on a new energy intelligent training and assessment method based on cloud rendering, reference can be made to the above limitations on a new energy intelligent training and assessment system based on cloud rendering, which will not be elaborated here. Those of ordinary skill in the art can realize that, in combination with the various modules and steps described in the embodiments disclosed in this application, they can be implemented by hardware, software, or a combination of both. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0111] The embodiment of the present invention provides a new energy intelligent training and assessment method based on cloud rendering. The method performs virtualization integration processing on graphic computing resources according to the course learning request data uploaded by the student terminal device and the student access terminal type, and generates a computing resource allocation plan; based on the computing resource allocation plan and the course type characteristics, different transmission strategies are used to transmit the rendered images of the virtual simulation environment to the front-end interface of the student terminal device; according to the course interaction data and the student learning behavior data of the student in the virtual simulation environment, the standardization of new energy training parameter operations, the compliance rate of standard parameters, and the data for handling abnormal working conditions are quantitatively evaluated, and personalized learning assessment data including the positioning of ability shortboards is generated; according to the personalized learning assessment data and the on-site training equipment operation data collected in real time, the virtual training environment and the real operation training scene are fused through a data coupling engine to generate force feedback operation data that is synchronized and updated with the real operation training scene; the force feedback operation data is fed back to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan. Compared with the prior art, this method realizes the seamless integration of the virtual and real operation scenarios of the new energy intelligent training and assessment system through virtualized resource allocation, personalized learning positioning, and virtual-real fusion, and significantly improves the utilization efficiency and precise allocation of the resources of the cloud rendering platform.

[0112] The above embodiments only represent several preferred implementation manners of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art of this technology, without departing from the technical principle of the present invention, several improvements and replacements can still be made, and these improvements and replacements should also be regarded as the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the protection scope of the claims.

Claims

1. A new energy intelligent training and assessment system based on cloud rendering, characterized in that, Including: A cloud rendering central platform system, which is used to perform virtualization integration processing on graphic computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, generate a computing resource allocation plan, and based on the computing resource allocation plan and course type characteristics, adopt different transmission strategies to transmit the virtual simulation environment rendering screen to the front-end interface of the trainee terminal device; A post skill training assessment module, which is used to quantitatively evaluate the operation standardization of new energy training parameters, the compliance rate of standard parameters, and the abnormal condition handling data according to the course interaction data and trainee learning behavior data of the trainee in the virtual simulation environment, and generate personalized learning assessment data including the positioning of ability shortboards; A virtual-real fusion module, which is used to fuse the virtual training environment with the real operation training scenario according to the personalized learning assessment data and the real-time collected operation data of on-site training equipment through a data coupling engine, generate force feedback operation data that is synchronized and updated with the real operation training scenario, and feedback the force feedback operation data to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan.

2. The new energy intelligent training and assessment system based on cloud rendering according to claim 1, wherein: The cloud rendering central platform system includes a computing resource dynamic scheduling module, a cloud rendering course image transmission module, a human-environment-equipment data integration module, and a spatial computing course recommendation module; The spatial computing course recommendation module is used to recommend a list of training project courses with the shortest straight-line distance in space according to the geographical location information or spatial distribution information of the trainee, and generate course learning request data when the trainee selects a target training project course according to all the training project course lists; The computing resource dynamic scheduling module is used to identify the trainee access terminal type according to the course learning request data uploaded by the trainee terminal device, and based on the trainee access terminal type and the computing resource requirements of various basic courses, dynamically schedule graphic computing resources from the server resource pool to run various basic courses, and generate a computing resource allocation plan; The cloud rendering course image transmission module is used to perform streaming media encoding processing on the virtual simulation environment rendering screen according to the characteristics of the course to be learned, generate an encrypted rendering data stream, and transmit the encrypted rendering data stream to the front-end interface of the trainee terminal device through the computing resource allocation plan; The human-environment-equipment data integration module is used to perform real-time update and structured knowledge integration on the dynamic background data and trainee learning correlation information involved in the post training assessment course.

3. The new energy intelligent training and assessment system based on cloud rendering according to claim 2, characterized in that: When the characteristics of the course to be learned are theoretical courses, the encrypted rendering data stream is transmitted to the front-end interface of the trainee terminal device through a remote encryption access mode; When the characteristics of the course to be learned are practical operation courses, the encrypted rendering data stream is transmitted to the front-end interface of the trainee terminal device through a cloud rendering mode; When the characteristics of the course to be learned are assessment courses, the encrypted rendering data stream is transmitted to the front-end interface of the trainee terminal device through a front-end encryption display mode.

4. The new energy intelligent training and assessment system based on cloud rendering according to claim 2, characterized in that: The spatial computing course recommendation module includes a spatial positioning unit, a distance calculation unit, and a course recommendation unit; The spatial positioning unit is used to extract new energy training equipment instrument feature information, parameter identification information, and operating environment information from the current environment information uploaded by the trainee terminal device, generate a structured device positioning feature data set, and associate and match the structured device positioning feature data set with a preset new energy training equipment parameter database to generate positioning point data; The distance calculation unit is used to determine the shortest straight-line distance in space between the trainee and the new energy training equipment according to the spatial coordinate information of the new energy training equipment and the trainee terminal IP address in the positioning point data; The course recommendation unit is used to retrieve the post skill training assessment course database according to the shortest straight-line distance in space, and sort the retrieval results according to the equipment association degree weight to obtain a training project course list.

5. The new energy intelligent training and assessment system based on cloud rendering according to claim 2, characterized in that: The computing resource dynamic scheduling module includes a computing cluster unit, a resource pool unit, and a dynamic scheduling unit composed of multiple cloud rendering servers; The resource pool unit is used to virtualize and integrate the physical server cluster in the computing cluster unit according to the server performance parameters obtained in advance to form a dynamically allocable resource pool; The dynamic scheduling unit is used to generate an initial resource allocation plan through an iterative optimization algorithm according to the historical training scale and the single-course resource demand matrix, and real-time monitor the number of people waiting in the course reservation queue and the current resource utilization rate according to the initial resource allocation plan. When it detects that the current resource utilization rate exceeds the resource pool capacity, it reallocates resources according to the course weight priority and sends an elastic expansion instruction to the administrator.

6. The new energy intelligent training and assessment system based on cloud rendering according to claim 2, characterized in that: The human-environment-equipment data integration module includes a data integration unit, a data mapping unit, a data update unit, and a large model intelligent unit; The data integration unit is used to collect trainee basic information, post curriculum systems, curriculum learning status data, new energy training equipment parameters, and training environment parameters to form a structured data set; The data mapping unit is used to perform real-time update and structured knowledge integration on the dynamic background data and trainee learning association information involved in the post training assessment course according to the structured data set to generate a standardized long text question based on the new energy training scenario; The large model intelligent unit is used to analyze the standardized long text question to generate a new energy training solution; The data update unit is used to update all the materials of people, equipment, and environment involved in the post training assessment course according to the new energy training solution.

7. The new energy intelligent training and assessment system based on cloud rendering according to claim 1, characterized in that: The post skill training assessment module includes a post curriculum pool unit, a peripheral compatibility unit, and a learning evaluation unit; The post curriculum pool unit is connected to the cloud rendering central platform system and is used to store the new energy training basic curriculum data set based on a distributed database architecture, add different post tags to the new energy training basic curriculum data set, and set a dependency unlocking relationship for the new energy training basic curriculum with the same post tag; The learning evaluation unit is used to calculate the learning activity, learning points and grade ranking of the trainee based on the learning behavior data of the trainee in each learning session, and generate personalized learning evaluation data including an analysis of ability shortfalls based on the learning behavior data, learning activity, learning points and grade ranking; The peripheral compatibility unit establishes a two-way data channel with third-party training devices and the cloud rendering central platform. The peripheral compatibility unit is used to automatically load the corresponding new energy training device drivers according to the communication protocol type of the third-party training devices, communicate with the cloud rendering central platform system, and transmit the data obtained from the third-party training devices to the cloud rendering central platform system.

8. The new energy intelligent training and assessment system based on cloud rendering according to claim 7, wherein: The new energy training basic course data set includes structured course resources, virtual simulation programs and peripheral driver components; The structured course resources include digital files of new energy training principle courseware, new energy training device operation videos and new energy training regulation test papers; The virtual simulation programs include new energy training process virtual simulation software and non-standard training scenario simulators; The peripheral driver components include dynamic link library files and automated deployment scripts required for third-party training device training software; 9. The new energy intelligent training and assessment system based on cloud rendering according to claim 1, wherein: The virtual-real integration module includes a data coupling unit, a force feedback operation unit and a virtual-real update unit; The data coupling unit is used to establish a data communication link with on-site training devices through an industrial communication protocol, and real-time obtain the operation parameters of new energy training devices, training environment parameters and new energy training indicators to form on-site training device operation data; The force feedback operation unit is used to generate force feedback operation data that is synchronized and updated with the real operation training scenario through a force feedback device according to the on-site training device operation data; The virtual-real update unit is used to dynamically update the content of the new energy training basic course according to the on-site training device operation data and the current virtual scene parameters; 10. A new energy intelligent training and assessment method based on cloud rendering, characterized in that, The method includes the following steps: Perform virtualization integration processing on the graphics computing resources according to the course learning request data uploaded by the trainee terminal device and the trainee access terminal type, and generate a computing resource allocation plan; Based on the computing resource allocation plan and the course type characteristics, use different transmission strategies to transmit the rendered image of the virtual simulation environment to the front-end interface of the trainee terminal device; Quantitatively evaluate the operation standardization of new energy training parameters, the compliance rate of standard parameters and the abnormal condition handling data according to the course interaction data of the trainee in the virtual simulation environment and the trainee learning behavior data, and generate personalized learning evaluation data including ability shortfall positioning; According to the personalized learning evaluation data and the on-site training device operation data collected in real time, fuse the virtual training environment with the real operation training scenario through a data coupling engine to generate force feedback operation data that is synchronized and updated with the real operation training scenario; Feed the force feedback operation data back to the cloud rendering central platform system to trigger the iterative optimization of the computing resource allocation plan.

Images