Power industry training method and system based on knowledge graph
By building the first training model and reinforcement learning in the power industry, and generating a training knowledge graph, the problems of large amount of computing and inability to meet personalized training needs in the existing technology are solved, and efficient power industry training is achieved.
Patent Information
- Application Number
- CN202411050868.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-12-13
AI Technical Summary
The existing power industry training methods are difficult to meet the training needs of individuals or groups, and the calculation volume is large and cannot be effectively reduced.
By building a first training model based on big data, obtaining training feature sets and performing reinforcement learning, generating training knowledge graphs, and providing personalized power industry training.
It has achieved the reduction of the amount of big data sorting and computing, met the adaptive training needs of individuals or groups, and provided an efficient training platform.
Smart Images
Figure CN119128167A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electric power training technology, and specifically to an electric power industry training method and system based on a knowledge graph. Background Art
[0002] The power industry is technically complex and highly dangerous, with a large number of employees. Training can improve employee skills, ensure standardized operations, and reduce accidents. At the same time, it can help employees adapt to new technologies, improve work efficiency, ensure stable operation of the power system, meet the growing demand for electricity, and promote industry development. Therefore, it is necessary to study the training methods of the power industry.
[0003] Chinese patent number CN202111064267.3 discloses a system and method for learning electric power knowledge based on heterogeneous resource fusion, the system includes a resource layer, a business layer and an application layer; the resource layer is used to obtain electric power resource information; the business layer is used to construct an electric power knowledge base and an electric power knowledge graph based on the electric power resource information, and to construct employee portraits in different positions based on employee information; the application layer is used to provide personalized services for each employee, and the personalized services include electric power knowledge recommendations and electric power knowledge test paper evaluation. However, it is inevitable that there will be a huge amount of calculation due to the large number of practitioners, and the invention recommends corresponding electric power knowledge based on job requirements and preference characteristics, which cannot meet the training needs of individuals or groups.
[0004] In summary, there is an urgent need for a technical solution that can meet the power training needs of individuals or groups without requiring extensive calculations. Summary of the invention
[0005] The purpose of this application is to provide a knowledge graph-based power industry training method and system to solve the technical problems raised in the above background technology.
[0006] To achieve the above objectives, this application discloses the following technical solutions:
[0007] In a first aspect, the present application discloses a power industry training method based on a knowledge graph, the method comprising:
[0008] S1: Collect training data of the power industry through big data and build the first training model;
[0009] S2: Obtain a training feature set, and perform reinforcement learning on the first training model based on the training feature set to obtain a reinforcement learning result;
[0010] S3: Import the required training materials into the reinforcement learning results to generate a knowledge graph for training;
[0011] S4: Conduct power industry training using the training knowledge graph.
[0012] By constructing the first training model, it is possible to organize big data, provide a data basis for reinforcement learning, and reduce unnecessary calculations in the later stage; by obtaining the training feature set and performing reinforcement learning on the first training model, it is possible to adapt to the needs of individuals or groups, and achieve the technical effect of reducing the amount of calculation; by importing training materials and generating a knowledge graph for training, a training platform is provided for individuals or groups to conduct power training.
[0013] Preferably, the power industry training data includes:
[0014] Course data, including course content, course duration, and course difficulty level;
[0015] Teacher data, including teacher background, teacher teaching style and teacher evaluation;
[0016] Student data, including student education and student positions;
[0017] Effect data, including skill improvement and satisfaction survey results;
[0018] Resource data, including teaching materials and teaching equipment.
[0019] Through the above, the corresponding training data is comprehensively obtained through big data, which provides a data basis for power training and provides more training options for the individuals or groups being trained.
[0020] Preferably, the construction of the first training model specifically includes:
[0021] Obtaining the power industry training data;
[0022] Extracting features from the power industry training data to obtain a training feature set, wherein the training feature set includes course features, teacher features, student features, effect features, and resource features;
[0023] The power industry training data is reorganized by using the training feature set to obtain a training link set, wherein the training link set includes a course link, a teacher link, a student link, an effect link, and a resource link;
[0024] The training feature set and the training link set are stored and uploaded to obtain the first training model.
[0025] Through the above, by constructing the first training model, a data basis is provided for reinforcement learning, and the reorganization of the power industry training data in the first training model provides the necessary technical means for subsequently reducing the amount of calculation.
[0026] Preferably, the obtaining of the training feature set specifically includes:
[0027] Obtaining the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the individual, and defining them as the individual training characteristic set;
[0028] Obtaining the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the group, and defining them as the group training characteristic set;
[0029] The individual training feature set and the group training feature set are defined as the training feature sets.
[0030] Through the above, obtaining a training feature set provides a data reference for meeting the training needs of individuals or groups, and provides the necessary technical means for optimizing the amount of calculation by limiting the features.
[0031] Preferably, the performing reinforcement learning on the first training model based on the training feature set to obtain the reinforcement learning result specifically includes:
[0032] Acquire and parse the training feature set;
[0033] Calculating the similarity between the training feature set and the training feature set, and obtaining the training feature set corresponding to the maximum value of the similarity, and defining the training feature set as a reinforcement learning object;
[0034] Obtaining a training link set corresponding to the reinforcement learning object and defining it as a reinforcement learning link;
[0035] Using the difference between the training feature set and the training feature set, a corresponding training link set is obtained and defined as reinforcement learning data;
[0036] The reinforcement learning link is updated using the reinforcement learning data to obtain the reinforcement learning result.
[0037] Through the above, by calculating the similarity between the training feature set and the training feature set, repeated and unnecessary calculations are reduced, so that the screening results directly point to the reinforcement learning object, which greatly reduces the amount of calculation; by utilizing the difference between the training feature set and the training feature set on the basis of obtaining the reinforcement learning link, the increase in the amount of calculation caused by too many links participating in the calculation is further avoided, and the adaptive performance to individual or group needs is improved.
[0038] Preferably, the step of importing the required training materials into the reinforcement learning results specifically includes:
[0039] Obtaining the reinforcement learning result;
[0040] Analyze the reinforcement learning results and match corresponding training materials, wherein the training materials include course video materials, course audio materials and course manuscript materials;
[0041] The matched training materials are uploaded and imported into the reinforcement learning results.
[0042] Through the above, by completing the training materials after obtaining the reinforcement learning results, the phenomenon of mixing a large amount of data for calculation is avoided, and the accuracy of the training materials is improved.
[0043] Preferably, the generating of the knowledge graph for training specifically includes:
[0044] Obtain and parse the reinforcement learning results after importing the training materials, and obtain the corresponding graph link set and the corresponding graph feature set;
[0045] The graph link set includes the course link, teacher link, student link, effect link and resource link corresponding to the reinforcement learning result, and the graph feature set includes the corresponding course features, teacher features, student features, effect features and resource features matched based on the graph link set;
[0046] The training data, the graph feature set and the graph link set are uploaded and entities, relationships and hierarchical structures of the training knowledge graph are generated respectively.
[0047] Through the above, the optimization of the training content of the power industry is provided by generating a knowledge graph for training, which is unfolded in the form of graph links, improves the systematic nature of the training, and provides technical support for improving the training effect of individuals or groups.
[0048] Preferably, the individuals who use the training knowledge graph to conduct power industry training use the training knowledge graph to conduct power industry training, specifically including the following steps:
[0049] A1: Select corresponding course features, teacher features, student features, effect features and resource features based on personal needs, and generate the personal training feature set;
[0050] A2: using the personal training feature set in step A1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result;
[0051] A3: Import the matched training materials to be used into the reinforcement learning results in step A2 to generate the training knowledge graph corresponding to the individual.
[0052] Through the above, a high degree of adaptability to individual training needs is achieved by generating a training knowledge graph corresponding to the individual.
[0053] Preferably, the use of the training knowledge graph for power industry training specifically includes:
[0054] B1: Select corresponding course features, teacher features, student features, effect features and resource features based on group needs, and generate the group training feature set;
[0055] B2: using the group training feature set in step B1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result;
[0056] B3: Import the matched training materials to be used into the reinforcement learning results in step B2 to generate the training knowledge graph corresponding to the group.
[0057] Through the above, a high degree of adaptability to group training needs is achieved by generating a training knowledge graph corresponding to the group.
[0058] In a second aspect, the present application discloses a knowledge graph-based power industry training system, which is applicable to the knowledge graph-based power industry training method as described above, and the system includes:
[0059] A model building module, wherein the model building module is configured to: collect power industry training data through big data to build a first training model;
[0060] A reinforcement learning module, wherein the reinforcement learning module is configured to: obtain a training feature set, perform reinforcement learning on the first training model based on the training feature set, and obtain a reinforcement learning result;
[0061] A knowledge graph module, wherein the knowledge graph module is configured to: import the training materials to be used into the reinforcement learning results to generate a knowledge graph for training;
[0062] An electric power training module, wherein the electric power training module is configured to: use the training knowledge graph to conduct electric power industry training.
[0063] Beneficial effects: The knowledge graph-based power industry training method and system of the present application realizes the organization of big data by constructing a first training model, provides a data basis for reinforcement learning, and reduces unnecessary calculations in the later stage; by obtaining a training feature set and performing reinforcement learning on the first training model, it realizes adaptation to individual or group needs and achieves the technical effect of reducing the amount of calculation; by importing training materials and generating a knowledge graph for training, a training platform is provided for individuals or groups to conduct power training. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.
[0065] Figure 1 A flowchart of a knowledge graph-based power industry training method provided in an embodiment of the present application;
[0066] Figure 2 A structural block diagram of the knowledge graph-based power industry training system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0067] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0068] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0069] The first aspect of this embodiment discloses Figure 1 A power industry training method based on knowledge graph is shown, the method comprising:
[0070] S1: Collect training data of the power industry through big data and build the first training model;
[0071] S2: Obtain a training feature set, and perform reinforcement learning on the first training model based on the training feature set to obtain a reinforcement learning result;
[0072] S3: Import the required training materials into the reinforcement learning results to generate a knowledge graph for training;
[0073] S4: Use training knowledge graphs to conduct power industry training.
[0074] By constructing the first training model, it is possible to organize big data, provide a data basis for reinforcement learning, and reduce unnecessary calculations in the later stage; by obtaining the training feature set and performing reinforcement learning on the first training model, it is possible to adapt to the needs of individuals or groups, and achieve the technical effect of reducing the amount of calculation; by importing training materials and generating a knowledge graph for training, a training platform is provided for individuals or groups to conduct power training.
[0075] Specifically, the power industry training data includes:
[0076] Course data, including course content, course duration and course difficulty level;
[0077] Teacher data, including lecturer background, lecturer teaching style and lecturer evaluation;
[0078] Student data, including student education and positions;
[0079] Effect data, including skill improvement and satisfaction survey results;
[0080] Resource data, resource data includes teaching materials and teaching equipment.
[0081] Comprehensively acquiring corresponding training data through big data provides a data basis for power training and provides more training options for individuals or groups being trained.
[0082] Specifically, constructing the first training model includes:
[0083] Access to power industry training data;
[0084] Extract features from the power industry training data to obtain a training feature set, which includes course features, teacher features, student features, effect features, and resource features;
[0085] The training data of the power industry are reorganized using the training feature set to obtain a training link set, which includes course link, teacher link, student link, effect link and resource link.
[0086] The training feature set and the training link set are stored and uploaded to obtain a first training model.
[0087] By constructing the first training model, a data basis is provided for reinforcement learning, and the reorganization of the power industry training data in the first training model provides the necessary technical means for subsequently reducing the amount of calculation.
[0088] Specifically, obtain the training feature set, including:
[0089] Obtain the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the individual, and define them as a personal training characteristic set;
[0090] Obtain the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the group, and define them as a group training characteristic set;
[0091] The individual training feature set and the group training feature set are defined as training feature sets.
[0092] By obtaining a set of training features, data reference is provided to meet the training needs of individuals or groups, and by limiting features, necessary technical means are provided to optimize the amount of calculation.
[0093] Specifically, reinforcement learning is performed on the first training model based on the training feature set to obtain a reinforcement learning result, which specifically includes:
[0094] Obtain and parse the training feature set;
[0095] Calculate the similarity between the training feature set and the training feature set, and obtain the training feature set corresponding to the maximum similarity, and define the training feature set as a reinforcement learning object. It should be noted that the similarity calculation in this embodiment is intended to screen out the training feature set that is most similar to the training feature set in terms of text or value, and the calculation method can be any one of the existing similarity calculation methods that can meet this purpose;
[0096] Obtain a set of training links corresponding to the reinforcement learning object and define it as a reinforcement learning link;
[0097] Using the difference between the training feature set and the training feature set, the corresponding training link set is obtained and defined as reinforcement learning data;
[0098] The reinforcement learning link is updated using reinforcement learning data, that is, different features are replaced to obtain reinforcement learning results.
[0099] By calculating the similarity between the training feature set and the training feature set, repeated and unnecessary calculations are reduced, so that the screening results directly point to the reinforcement learning object, which greatly reduces the amount of calculation; by utilizing the difference between the training feature set and the training feature set on the basis of obtaining the reinforcement learning link, the increase in the amount of calculation caused by too many links participating in the calculation is further avoided, and the adaptive performance to individual or group needs is improved.
[0100] Specifically, the training materials to be used are imported into the reinforcement learning results, including:
[0101] Get reinforcement learning results;
[0102] Analyze the reinforcement learning results and match the corresponding training materials, including course video materials, course audio materials and course manuscript materials;
[0103] Upload the matched training materials and import the reinforcement learning results.
[0104] By completing the training materials after obtaining the reinforcement learning results, the phenomenon of mixing a large amount of data for calculation is avoided, and the accuracy of the training materials is improved.
[0105] Specifically, the knowledge graph for training is generated, including:
[0106] Obtain and parse the reinforcement learning results after importing the training materials, and obtain the corresponding graph link set and the corresponding graph feature set;
[0107] Among them, the graph link set includes the course link, teacher link, student link, effect link and resource link corresponding to the reinforcement learning results, and the graph feature set includes the corresponding course features, teacher features, student features, effect features and resource features obtained by matching the graph link set;
[0108] The training data, graph feature set and graph link set are uploaded and the entities, relationships and hierarchical structures of the knowledge graph for training are generated respectively.
[0109] By generating knowledge graphs for training, the training content of the power industry is optimized and unfolded in the form of graph links, which improves the systematicness and repeatability of the training and provides technical support for improving the training effects of individuals or groups.
[0110] Specifically, using the training knowledge graph for training for individuals in the power industry training using the training knowledge graph for training includes the following steps:
[0111] A1: Select corresponding course features, teacher features, student features, effect features and resource features based on personal needs, and generate a personal training feature set;
[0112] A2: using the individual training feature set in step A1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result;
[0113] A3: Import the matched training materials to be used into the reinforcement learning results in step A2 to generate a training knowledge graph corresponding to the individual.
[0114] By generating a knowledge graph for training corresponding to the individual, a high degree of adaptability to individual training needs is achieved.
[0115] Specifically, using the training knowledge graph for power industry training includes:
[0116] B1: Select corresponding course features, teacher features, student features, effect features and resource features based on group needs, and generate a group training feature set;
[0117] B2: using the group training feature set in step B1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result;
[0118] B3: Import the matched training materials to be used into the reinforcement learning results in step B2 to generate a training knowledge graph corresponding to the group.
[0119] By generating a training knowledge graph corresponding to the group, a high degree of adaptability to group training needs is achieved.
[0120] The second aspect of this embodiment discloses Figure 2 A power industry training system based on knowledge graph is shown, and the system is applicable to the power industry training method based on knowledge graph as described above, and the system includes:
[0121] The model building module is configured to: collect power industry training data through big data to build a first training model;
[0122] A reinforcement learning module, wherein the reinforcement learning module is configured to: obtain a training feature set, perform reinforcement learning on the first training model based on the training feature set, and obtain a reinforcement learning result;
[0123] The knowledge graph module is configured to: import the required training materials into the reinforcement learning results to generate a knowledge graph for training;
[0124] Electric power training module, the configuration of the electric power training module is: using the training knowledge graph to conduct electric power industry training.
[0125] It should be noted that the knowledge graph-based power industry training system of this embodiment corresponds to the aforementioned knowledge graph-based power industry training method. Therefore, the contents not specifically described in the knowledge graph-based power industry training system of this embodiment, including but not limited to specific functional definitions, working principles and technical effects, are the same as the aforementioned knowledge graph-based power industry training method, and this text will not go into details here.
[0126] In summary, the knowledge graph-based power industry training method and system of this embodiment realizes the organization of big data by constructing a first training model, provides a data basis for reinforcement learning, and reduces unnecessary calculations in the later stage; by obtaining a training feature set and performing reinforcement learning on the first training model, it realizes adaptation to individual or group needs and achieves the technical effect of reducing the amount of calculation; by importing training materials and generating a knowledge graph for training, it provides a training platform for individuals or groups to conduct power training.
[0127] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.
[0128] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. A power industry training method based on knowledge graph, characterized in that: The method includes: S1: Collect training data of the power industry through big data and build the first training model; S2: Obtain a training feature set, and perform reinforcement learning on the first training model based on the training feature set to obtain a reinforcement learning result; S3: Import the required training materials into the reinforcement learning results to generate a knowledge graph for training; S4: Conduct power industry training using the training knowledge graph.
2. The power industry training method based on knowledge graph according to claim 1 is characterized in that: The power industry training data includes: Course data, including course content, course duration, and course difficulty level; Teacher data, including teacher background, teacher teaching style and teacher evaluation; Student data, including student education and student positions; Effect data, including skill improvement and satisfaction survey results; Resource data, including teaching materials and teaching equipment.
3. The power industry training method based on knowledge graph according to claim 2 is characterized in that: The constructing of the first training model specifically includes: Obtaining the power industry training data; Extracting features from the power industry training data to obtain a training feature set, wherein the training feature set includes course features, teacher features, student features, effect features, and resource features; The power industry training data is reorganized by using the training feature set to obtain a training link set, wherein the training link set includes a course link, a teacher link, a student link, an effect link, and a resource link; The training feature set and the training link set are stored and uploaded to obtain the first training model.
4. The power industry training method based on knowledge graph according to claim 3 is characterized in that: The obtaining of the training feature set specifically includes: Obtaining the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the individual, and defining them as the individual training characteristic set; Obtaining the course characteristics, teacher characteristics, student characteristics, effect characteristics and resource characteristics required by the group, and defining them as the group training characteristic set; The individual training feature set and the group training feature set are defined as the training feature sets.
5. The power industry training method based on knowledge graph according to claim 4 is characterized in that: The performing reinforcement learning on the first training model based on the training feature set to obtain a reinforcement learning result specifically includes: Acquire and parse the training feature set; Calculating the similarity between the training feature set and the training feature set, and obtaining the training feature set corresponding to the maximum value of the similarity, and defining the training feature set as a reinforcement learning object; Obtaining a training link set corresponding to the reinforcement learning object and defining it as a reinforcement learning link; Using the difference between the training feature set and the training feature set, a corresponding training link set is obtained and defined as reinforcement learning data; The reinforcement learning link is updated using the reinforcement learning data to obtain the reinforcement learning result.
6. The power industry training method based on knowledge graph according to claim 5 is characterized in that: The step of importing the required training materials into the reinforcement learning results specifically includes: Obtaining the reinforcement learning result; Analyze the reinforcement learning results and match corresponding training materials, wherein the training materials include course video materials, course audio materials and course manuscript materials; The matched training materials are uploaded and imported into the reinforcement learning results.
7. The power industry training method based on knowledge graph according to claim 6 is characterized in that: The generation of the knowledge graph for training specifically includes: Obtain and parse the reinforcement learning results after importing the training materials, and obtain the corresponding graph link set and the corresponding graph feature set; The graph link set includes the course link, teacher link, student link, effect link and resource link corresponding to the reinforcement learning result, and the graph feature set includes the corresponding course features, teacher features, student features, effect features and resource features matched based on the graph link set; The training data, the graph feature set and the graph link set are uploaded and entities, relationships and hierarchical structures of the training knowledge graph are generated respectively.
8. The power industry training method based on knowledge graph according to claim 7 is characterized in that: The individuals who use the training knowledge graph for power industry training use the training knowledge graph for power industry training, specifically The following steps are involved: A1: Select corresponding course features, teacher features, student features, effect features and resource features based on personal needs, and generate the personal training feature set; A2: using the personal training feature set in step A1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result; A3: Import the matched training materials to be used into the reinforcement learning results in step A2 to generate the training knowledge graph corresponding to the individual.
9. The power industry training method based on knowledge graph according to claim 8 is characterized in that: The use of the training knowledge graph for power industry training specifically includes: B1: Select corresponding course features, teacher features, student features, effect features and resource features based on group needs, and generate the group training feature set; B2: using the group training feature set in step B1 to perform reinforcement learning on the first training model to obtain a reinforcement learning result; B3: Import the matched training materials to be used into the reinforcement learning results in step B2 to generate the training knowledge graph corresponding to the group.
10. A power industry training system based on knowledge graph, the system is applicable to the power industry training method based on knowledge graph as described in any one of claims 1 to 9, characterized in that: The system includes: A model building module, wherein the model building module is configured to: collect power industry training data through big data to build a first training model; A reinforcement learning module, wherein the reinforcement learning module is configured to: obtain a training feature set, perform reinforcement learning on the first training model based on the training feature set, and obtain a reinforcement learning result; A knowledge graph module, wherein the knowledge graph module is configured to: import the training materials to be used into the reinforcement learning results to generate a knowledge graph for training; An electric power training module, wherein the electric power training module is configured to: use the training knowledge graph to conduct electric power industry training.