A training content generation method, device, equipment and storage medium

Abstract

The application discloses a training content generation method and device, equipment and a storage medium. The method comprises the following steps: obtaining target training demand information and user skill level information corresponding to a target energy storage user to be trained; performing knowledge graph mapping based on the target training demand information and the user skill level information, and determining a target training label set corresponding to the target energy storage user; inputting the target training label set into a training content generation model to generate training content, and obtaining target training content information corresponding to the target energy storage user. The application can realize efficient generation of training content for energy storage equipment, greatly improve the efficiency and flexibility of training content generation, improve the explainability of personalized needs of users, and thus cannot guarantee the accurate matching and safe adaptation of training content in complex user scenarios, improve the training efficiency and satisfaction of users.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for generating training content. Background Technology

[0002] With the increasing diversification and sophistication of user training needs for energy storage equipment, the requirements for the accuracy, dynamic adaptability, and personalized matching capabilities of training content generation have significantly increased. Energy storage training, as a core means to enable users to efficiently master equipment operation, safety regulations, and operational optimization capabilities, directly impacts users' confidence in the actual application effectiveness and long-term use of energy storage equipment.

[0003] Currently, traditional methods for generating energy storage training content often rely on generic textbook templates or fixed scenario course designs, using manual experience rules or static data to determine the training content. However, traditional methods are inefficient and inflexible, and have poor interpretability for personalized user needs. Consequently, they cannot guarantee the accurate matching and safe adaptation of training content in complex user scenarios, resulting in low training efficiency and poor user satisfaction for energy storage users. Summary of the Invention

[0004] This invention provides a training content generation method, apparatus, device, and storage medium to achieve efficient generation of training content for energy storage devices, greatly improving the efficiency and flexibility of training content generation, enhancing the interpretability of personalized user needs, thereby ensuring accurate matching and safe adaptation of training content in complex user scenarios, and improving user training efficiency and satisfaction.

[0005] According to one aspect of the present invention, a method for generating training content is provided, the method comprising:

[0006] Obtain information on the target training needs and user skill levels of the target energy storage users to be trained;

[0007] Based on the target training needs information and the user skill level information, a knowledge graph mapping is performed to determine the target training tag set corresponding to the target energy storage user;

[0008] The target training tag set is input into the training content generation model to generate training content, thereby obtaining the target training content information corresponding to the target energy storage user.

[0009] According to another aspect of the present invention, a training content generation apparatus is provided, the apparatus comprising:

[0010] The information acquisition module is used to acquire the target training needs information and user skill level information of the target energy storage users to be trained;

[0011] The training tag determination module is used to perform knowledge graph mapping based on the target training needs information and the user skill level information to determine the target training tag set corresponding to the target energy storage user;

[0012] The content information acquisition module is used to input the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the training content generation method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the training content generation method according to any embodiment of the present invention.

[0018] The technical solution of this invention provides a basis for the personalized generation of subsequent user training content by acquiring the target training needs information and user skill level information corresponding to the target energy storage user to be trained, which helps to accurately locate user training needs. Based on the target training needs information and the user skill level information, knowledge graph mapping is performed to determine the target training tag set corresponding to the target energy storage user, which helps to ensure that the training content covers all key knowledge points required by the user, avoiding omissions and improving the relevance of the training content. The target training tag set is input into the training content generation model to generate training content, obtaining the target training content information corresponding to the target energy storage user, greatly improving the efficiency and accuracy of training content generation and meeting the learning preferences of different users. This invention, through a personalized design of the entire process from needs collection to content generation, ensures that the training content is highly aligned with the user's actual needs and skill level, achieving efficient generation of training content for energy storage devices, greatly improving the efficiency and flexibility of training content generation, enhancing the interpretability of personalized user needs, thereby ensuring accurate matching and safe adaptation of training content in complex user scenarios, and improving user training efficiency and satisfaction.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a training content generation method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a training content generation method provided in Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of a training content generation device according to Embodiment 3 of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the training content generation method of this invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This is a flowchart illustrating a training content generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to generating training content for users who have purchased energy storage equipment. The method can be executed by a training content generation device, which can be implemented in hardware and / or software. This training content generation device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S110. Obtain the target training needs information and user skill level information corresponding to the target energy storage users to be trained.

[0030] Among these, target energy storage users refer to specific users who have purchased or are about to use energy storage equipment (such as residential / industrial energy storage systems) and need to acquire skills in equipment operation and maintenance through training. Target training needs information can refer to the specific requirements of users regarding training content, including constraints such as scenarios, time, and depth. User skill level information can refer to the user's graded assessment of their existing knowledge level and operational capabilities regarding energy storage equipment, used to match the training difficulty.

[0031] Specifically, the target training needs of the target energy storage user can be obtained through active input from the user (e.g., filling in a text box), pre-set questionnaires (e.g., "Which functions would you like to focus on learning about?"), or voice interaction. For example, the target training needs input by the user could be "I just installed 10kWh of home energy storage and want to quickly learn about it in 5 minutes." Skill levels (e.g., beginner / junior / intermediate / advanced / expert) can be determined using tiered questionnaires (e.g., "Do you understand the basic parameters of energy storage equipment?"), operational behavior analysis (e.g., whether the user has completed basic setup), or historical data inference (e.g., past training completion rates). This provides the user's skill level information. By providing target training needs information, redundant training can be avoided, providing a basis for personalized training content. Skill level information ensures that the difficulty of the content matches the user's ability, avoiding information overload or oversimplification.

[0032] For example, "obtaining target training requirement information corresponding to the target energy storage user to be trained" in S110 may include: in response to the information input operation of the target energy storage user to be trained, obtaining the original training requirement information corresponding to the target energy storage user, wherein the information input operation includes at least one of text input operation and voice input operation; performing a preprocessing operation on the original training requirement information to obtain the target training requirement information corresponding to the target energy storage user, wherein the preprocessing operation includes at least one of noise reduction and filtering.

[0033] Among them, raw training needs information can refer to the raw, unprocessed expression of needs by users through text / voice input, which may contain noise or redundant information.

[0034] Specifically, text input can be achieved by capturing the user's direct text input through a front-end interactive interface (such as an input box or chatbot dialog box); voice input can be achieved by integrating a speech recognition engine (such as a speech recognition plugin) to convert the user's speech into text. By supporting both text and voice input modes, it can adapt to different user habits and improve operational convenience. Responding to the information input operations of the target energy storage user to be trained, the system obtains the original training requirement information corresponding to the target energy storage user, thereby directly capturing the user's original expression, avoiding information transmission loss, and providing a complete context for subsequent processing. Preprocessing operations are performed on the original training requirement information. For example, preprocessing operations can include denoising and filtering. For different information input operations, denoising can include text denoising and speech denoising, and filtering can include keyword extraction and intent recognition. The preprocessed original training requirement information is used as the target training requirement information corresponding to the target energy storage user, providing a reliable data foundation for subsequent operations.

[0035] S120. Based on the target training needs information and user skill level information, perform knowledge graph mapping to determine the target training tag set corresponding to the target energy storage user.

[0036] Among them, the target training tag set can refer to the final tag set after filtering based on user needs, which directly guides the generation of training content and can ensure accurate matching of user needs.

[0037] Specifically, a knowledge graph for the energy storage field can be pre-built. Graph nodes can contain concepts such as "energy storage type," "operation process," and "safety specifications," with edge relationships defining the logic between concepts (e.g., "10kWh energy storage" is associated with "charging strategy" and "discharge efficiency"). Target training needs information corresponding to the target energy storage user (e.g., "quick understanding") can be mapped to the "basic concepts" and "core functions" nodes in the knowledge graph. Low-complexity tags (e.g., "energy storage equipment composition" and "basic operating steps") can be filtered based on skill level (e.g., beginner), while high-level tags (e.g., "grid connection strategy optimization") are excluded. This determines a set of target training tags that match the target energy storage user's target training needs and user skill level, ensuring logical coherence of the tag set, avoiding omissions of key knowledge points, and facilitating the generation of personalized training content.

[0038] S130. Input the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user.

[0039] The training content generation model can refer to a generative intelligent system used to transform a set of tags into specific training content. The target training content information can refer to the final training materials generated by the training content generation model, which may take the form of text tutorials, video scripts, interactive guides, etc.

[0040] Specifically, the target training tag set can be input into the training content generation model. The training content generation model constructs structured prompts about the training content based on the target training tag set, and generates training content based on these structured prompts. This obtains the target training content information corresponding to the target energy storage user, thereby generating customized content that meets the user's needs, greatly improving the efficiency of training content generation and enhancing the user experience.

[0041] For example, the training content generation model includes a training framework determination module and a training content generation module. S130 may include: inputting the target training tag set into the training framework determination module to generate a framework, and determining the target training framework information corresponding to the target energy storage user; inputting the target training framework information into the training content generation module to generate training content, and obtaining the target training content information corresponding to the target energy storage user.

[0042] The training framework determination module can refer to a core component that generates a training content framework using a structured Prompt template, transforming user requirements into executable LLM generation rules. The training content generation module can refer to a core component that generates specific training content using a large language model, transforming the structured framework into customized content that users can understand. The target training framework information can refer to the output of the training framework determination module; it is a structured framework document that guides subsequent content generation, defining the structure, format, and focus of the training content.

[0043] Specifically, the target training tag set can be input into the training framework determination module to build a framework using a modular Prompt template, and the target training framework information corresponding to the target energy storage user can be output, thereby ensuring that the training content is logically coherent and closely aligned with user needs; the target training framework information can be input into the training content generation module to be parsed and specific training content generated through a Large Language Model (LLM), obtaining the target training content information corresponding to the target energy storage user, thereby quickly generating customized content that meets user needs.

[0044] For example, the target training framework information could be: "Role: Energy Storage Consultant; Objective: Introduction to Residential LiFePO4 Energy Storage Systems; Length: No more than 300 Chinese characters; Structure: Paragraphs + Simple Tables + 3 Multiple Choice Questions." The target training content information could be: "Paragraphs explaining SOC and BMS basics; SVG illustration of unidirectional inverter and grid connection; Quiz: Safe storage temperature range?...."

[0045] In this embodiment, by acquiring the target training needs and skill level information of the target energy storage users to be trained, a basis is provided for the personalized generation of subsequent user training content, which helps to accurately locate user training needs. Based on the target training needs and user skill level information, knowledge graph mapping is performed to determine the target training tag set corresponding to the target energy storage users. This helps ensure that the training content covers all key knowledge points required by the users, avoiding omissions and improving the relevance of the training content. The target training tag set is input into the training content generation model to generate training content, obtaining the target training content information corresponding to the target energy storage users. This greatly improves the efficiency and accuracy of training content generation and meets the learning preferences of different users. This invention, through a personalized design of the entire process from needs acquisition to content generation, ensures that the training content highly matches the actual needs and skill levels of users, achieving efficient generation of training content for energy storage devices. This greatly improves the efficiency and flexibility of training content generation, enhances the interpretability of personalized user needs, and thus ensures accurate matching and safe adaptation of training content in complex user scenarios, improving user training efficiency and satisfaction.

[0046] For example, after step S130, the method may further include: in response to the target energy storage user's completion of learning the target training content information, obtaining the training content completion information corresponding to the target energy storage user; and determining the training efficiency information corresponding to the target energy storage user based on the training content completion information.

[0047] Among these, training content completion information refers to the structured records generated by the system after a user completes the target training content, reflecting the user's progress and behavioral data in mastering the specific training content. Training efficiency information refers to the user's learning effectiveness and speed indicators quantified based on the training content completion information, reflecting the actual effectiveness of the training content and the efficiency of user skill improvement.

[0048] Specifically, in response to a user clicking the "Complete Learning" button on the learning interface, indicating completion of the learning process, the system can capture the operation and learning behavior data through front-end event listeners to obtain the training content completion information for the target energy storage user. Based on this information and a pre-defined training effectiveness model, the system determines the training efficiency information for the target energy storage user. This achieves an intelligent transformation from user learning behavior to training effectiveness evaluation, ensuring the traceability of the learning process while improving the accuracy and practicality of training through efficiency quantification. Ultimately, this supports the personalization, efficiency, and intelligence of energy storage user training.

[0049] For example, a pre-defined training utility model can be shown below:

[0050]

[0051]

[0052]

[0053] Where R represents the total learning benefit score of the target training content information, and T represents the total learning time of the target training content information. The learning gain score for the k-th label. The learning time for the k-th label. For the target training tag set, , To learn the utility weight parameters, The total training effectiveness score represents the training efficiency information corresponding to the target energy storage user.

[0054] It should be noted that the training content completion information also includes test result information for the corresponding test questions. Furthermore, based on the test result information and the preset update formula, the learning utility weight parameters corresponding to the preset training utility model can be updated. The preset update formula is as follows:

[0055]

[0056]

[0057]

[0058] in, Let be the accuracy at time t. For the test response vector, To correctly answer the question about vectors, The learning rate is 0.05. , For the updated learning utility weight parameters, This represents the actual click-through rate. Targeted click-through rate.

[0059] Example 2

[0060] Figure 2 This is a flowchart of a training content generation method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the step of "determining the target training tag set corresponding to the target energy storage user by performing knowledge graph mapping based on target training demand information and user skill level information". Explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0061] See Figure 2 Another training content generation method provided in this embodiment specifically includes the following steps:

[0062] S210. Obtain the target training needs information and user skill level information corresponding to the target energy storage users to be trained.

[0063] S220. Based on the target training needs information and user skill level information, perform knowledge graph mapping to determine the original training tag set corresponding to the target energy storage user.

[0064] The original training tag set can refer to all potential tags related to user needs that are initially extracted through knowledge graph mapping, without undergoing demand screening.

[0065] Specifically, based on target training needs and user skill level information, a graph database or semantic network framework can be used to query nodes in the knowledge graph that are strongly associated with user needs through predefined mapping rules. For example, the user need "quick understanding of 10kWh home energy storage" is mapped to the "home energy storage equipment" node, associated with sub-nodes such as "equipment composition," "basic operation," and "safety specifications." For users with a skill level of "beginner," low-complexity tag filtering is triggered, such as excluding advanced tags like "grid connection strategy optimization" and retaining basic tags like "charging steps" and "discharge efficiency." This generates the original training tag set corresponding to the target energy storage user, ensuring that the original tag set covers the user's core needs and avoids missing key knowledge points.

[0066] For example, S220 may include: extracting features from the target training demand information and the user skill level information respectively to determine the training demand features corresponding to the target training demand information and the skill level features corresponding to the user skill level information; and performing knowledge graph mapping based on the training demand features and skill level features to determine the original training tag set corresponding to the target energy storage user.

[0067] Among them, training demand characteristics can refer to structured and quantifiable core elements extracted from users' target training demand information, reflecting users' specific requirements for training content (such as scenario, time, depth, priority, etc.). Skill level characteristics can refer to numerical and measurable ability indicators extracted from users' skill level information, reflecting users' existing knowledge level and operational capabilities of energy storage equipment, used to match the difficulty and depth of training content.

[0068] Specifically, for target training needs information, feature extraction tools (such as spaCy and BERT models) can be used to analyze the user's input target training needs information from multiple dimensions to determine the corresponding training needs features. For user skill level information, classification models (such as logistic regression and decision trees) can be used to transform skill levels into numerical feature vectors to determine the skill level features corresponding to the user's skill level information. Based on the training needs features and skill level features, graph databases (such as Neo4j) or semantic network frameworks can be used to query nodes in the knowledge graph that are strongly correlated with user features, i.e., training needs features and skill level features, through predefined mapping rules. Knowledge graph embedding is then used to determine the original training label set corresponding to the target energy storage user, thereby ensuring that the original training label set is highly relevant to user needs and skill levels and avoiding interference from redundant or irrelevant labels.

[0069] S230. Based on the target training needs information, filter the original training tag set to determine the target training tag set corresponding to the target energy storage user.

[0070] Specifically, the selection criteria for the original training tag set can be time-constrained or scenario-based. For example, based on time constraints in the target training needs (such as the need for "quick understanding in 5 minutes"), tag priority rules can be pre-set (e.g., operation steps > technical principles), and the number of tags can be limited (e.g., ≤ 5 core tags). High-priority tags such as "device startup steps" and "safe charging specifications" can be selected from the original training tag set, while time-consuming content such as "battery lifespan calculation" can be excluded, thus determining the target training tag set for the target energy storage user. Alternatively, based on the specific user scenario in the target training needs (e.g., "home energy storage"), scenario-related tags can be further selected. For example, tags related to "industrial energy storage" can be excluded, retaining only tags such as "daily maintenance" and "emergency handling" under the "home scenario," thus determining the target training tag set for the target energy storage user. Demand-driven selection ensures that the target tag set perfectly matches the user's actual needs, avoiding interference from redundant information.

[0071] For example, S230 may include: sorting each candidate training tag in the original training tag set based on a preset topic selection algorithm to determine the candidate tag sorting result; and filtering the original training tag set based on the target training demand information and the candidate tag sorting result to determine the target training tag set corresponding to the target energy storage user.

[0072] The preset topic selection algorithm can refer to a ranking model designed based on user needs, used to prioritize candidate tags in the original training tag set. Candidate training tags can be specific tags in the original training tag set obtained from knowledge graph mapping, with each tag representing a training topic or knowledge point (such as concepts like "charging steps" or "safety regulations"). The candidate tag ranking result can refer to a tag priority list generated after applying the preset topic selection algorithm, arranged from high to low based on comprehensive score, used to guide subsequent screening.

[0073] Specifically, based on a preset topic selection algorithm, the comprehensive score corresponding to each candidate training tag in the original training tag set is calculated, and the tags are sorted from high to low according to the comprehensive score to determine the candidate tag ranking result. Based on the training time corresponding to each candidate training tag in the candidate tag ranking result, combined with the user's required time in the target training needs information (e.g., wanting to quickly understand in 5 minutes), tags are selected sequentially from front to back from the ranked candidate tags, so that the total training time corresponding to all selected tags does not exceed the user's required time. This determines the target training tag set corresponding to the target energy storage user, thereby ensuring that the target tag set fully matches the user's actual needs, avoiding redundant information interference, and improving training efficiency.

[0074] For example, a preset topic selection algorithm can be as follows:

[0075]

[0076] in, The overall score for the k-th label. The learning gain score for the k-th label. The learning time is for the k-th label.

[0077] S240. Input the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user.

[0078] The technical solution of this embodiment determines the original training tag set corresponding to the target energy storage user by performing knowledge graph mapping based on target training needs information and user skill level information. This ensures that the original tag set covers the user's core needs and avoids omitting key knowledge points. Filtering the original training tag set based on target training needs information to determine the target training tag set corresponding to the target energy storage user ensures that the target tag set fully matches the user's actual needs and avoids interference from redundant information. This invention, by filtering the original training tag set to obtain the target training tag set, achieves intelligent conversion from user needs to training tags. This ensures both the comprehensiveness and accuracy of the tags, and improves the relevance and practicality of the tags through demand-driven filtering, ultimately supporting the personalization and efficiency of the entire training content generation process.

[0079] Example 3

[0080] Figure 3 This is a schematic diagram of a training content generation device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an information acquisition module 310, a training tag determination module 320, and a content information acquisition module 330;

[0081] Among them, the information acquisition module 310 is used to acquire the target training needs information and user skill level information corresponding to the target energy storage users to be trained;

[0082] The training tag determination module 320 is used to perform knowledge graph mapping based on the target training needs information and the user skill level information to determine the target training tag set corresponding to the target energy storage user.

[0083] The content information acquisition module 330 is used to input the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user.

[0084] In this embodiment, by acquiring the target training needs information and user skill level information corresponding to the target energy storage user to be trained, a basis is provided for the personalized generation of subsequent user training content, which helps to accurately locate user training needs. Based on the target training needs information and the user skill level information, knowledge graph mapping is performed to determine the target training tag set corresponding to the target energy storage user. This helps ensure that the training content covers all key knowledge points required by the user, avoiding omissions and improving the relevance of the training content. The target training tag set is input into the training content generation model to generate training content, obtaining the target training content information corresponding to the target energy storage user, greatly improving the efficiency and accuracy of training content generation and meeting the learning preferences of different users. This invention, through a personalized design of the entire process from needs acquisition to content generation, ensures that the training content highly matches the actual needs and skill levels of users, achieving efficient generation of training content for energy storage devices, greatly improving the efficiency and flexibility of training content generation, enhancing the interpretability of personalized user needs, thereby ensuring accurate matching and safe adaptation of training content in complex user scenarios, and improving user training efficiency and satisfaction.

[0085] Optionally, the information acquisition module 310 is specifically configured to: in response to the information input operation of the target energy storage user to be trained, acquire the original training requirement information corresponding to the target energy storage user, wherein the information input operation includes at least one of text input operation and voice input operation; perform a preprocessing operation on the original training requirement information to acquire the target training requirement information corresponding to the target energy storage user, wherein the preprocessing operation includes at least one of noise reduction and filtering.

[0086] Optionally, the training label determination module 320 includes:

[0087] The original label determination unit is used to perform knowledge graph mapping based on the target training demand information and the user skill level information to determine the set of original training labels corresponding to the target energy storage user;

[0088] The target tag determination unit is used to filter the original training tag set based on the target training demand information to determine the target training tag set corresponding to the target energy storage user.

[0089] Optionally, the original label determination unit is specifically used to: extract features from the target training demand information and the user skill level information respectively, and determine the training demand features corresponding to the target training demand information and the skill level features corresponding to the user skill level information; and perform knowledge graph mapping based on the training demand features and the skill level features to determine the original training label set corresponding to the target energy storage user.

[0090] Optionally, the target tag determination unit is specifically used to: sort each candidate training tag in the original training tag set based on a preset topic selection algorithm to determine the candidate tag sorting result; and filter the original training tag set based on the target training demand information and the candidate tag sorting result to determine the target training tag set corresponding to the target energy storage user.

[0091] Optionally, the training content generation model includes a training framework determination module and a training content generation module. The content information acquisition module 330 is specifically used for: inputting the target training tag set into the training framework determination module to generate a framework, and determining the target training framework information corresponding to the target energy storage user; inputting the target training framework information into the training content generation module to generate training content, and obtaining the target training content information corresponding to the target energy storage user.

[0092] Optionally, the above device further includes: a training efficiency determination module.

[0093] The training efficiency determination module is specifically used to: in response to the target energy storage user's completion of learning the target training content information, obtain the training content completion information corresponding to the target energy storage user; and determine the training efficiency information corresponding to the target energy storage user based on the training content completion information.

[0094] The above-described apparatus can execute the training content generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the training content generation method.

[0095] Example 4

[0096] Figure 4 This is a schematic diagram of the structure of an electronic device implementing the training content generation method of this invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0097] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0098] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0099] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as training content generation methods.

[0100] In some embodiments, the training content generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the training content generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the training content generation method by any other suitable means (e.g., by means of firmware).

[0101] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0102] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0103] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0104] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0105] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0106] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0107] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0108] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0109] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating training content, characterized in that, include: Obtain information on the target training needs and user skill levels of the target energy storage users to be trained; Based on the target training needs information and the user skill level information, a knowledge graph mapping is performed to determine the target training tag set corresponding to the target energy storage user; The target training tag set is input into the training content generation model to generate training content, thereby obtaining the target training content information corresponding to the target energy storage user; The step of performing knowledge graph mapping based on the target training needs information and the user skill level information to determine the target training tag set corresponding to the target energy storage user includes: Based on the target training needs information and the user skill level information, a knowledge graph mapping is performed to determine the original training tag set corresponding to the target energy storage user; According to the preset topic selection algorithm, the comprehensive score corresponding to each candidate training tag in the original training tag set is calculated, and the candidate tags are sorted from high to low according to the comprehensive score to determine the candidate tag sorting result; according to the training time corresponding to each candidate training tag in the candidate tag sorting result, combined with the user demand time in the target training demand information, the tags are selected sequentially from front to back in the sorted candidate tag result, so that the total training time corresponding to all selected tags does not exceed the user demand time, and the target training tag set corresponding to the target energy storage user is determined. The step of inputting the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user includes: The target training tag set is input into the training framework determination module, and the framework is constructed using a modular Prompt template. The target training framework information corresponding to the target energy storage user is output. The target training framework information is input into the training content generation module, parsed by a large language model, and specific training content is generated to obtain the target training content information corresponding to the target energy storage user.

2. The method according to claim 1, characterized in that, The step of obtaining the target training needs information corresponding to the target energy storage users to be trained includes: In response to the information input operation of the target energy storage user to be trained, the original training requirement information corresponding to the target energy storage user is obtained, wherein the information input operation includes at least one of text input operation and voice input operation; The original training demand information is preprocessed to obtain the target training demand information corresponding to the target energy storage user. The preprocessing operation includes at least one of noise reduction and filtering.

3. The method according to claim 1, characterized in that, The step of performing knowledge graph mapping based on the target training needs information and the user skill level information to determine the original training tag set corresponding to the target energy storage user includes: Feature extraction is performed on the target training demand information and the user skill level information respectively to determine the training demand features corresponding to the target training demand information and the skill level features corresponding to the user skill level information; Based on the training demand characteristics and skill level characteristics, a knowledge graph mapping is performed to determine the original training tag set corresponding to the target energy storage user.

4. The method according to claim 1, characterized in that, The step of filtering the original training tag set based on the target training demand information to determine the target training tag set corresponding to the target energy storage user includes: The candidate training tags in the original training tag set are sorted based on a preset topic selection algorithm to determine the candidate tag sorting result; Based on the target training needs information and the candidate tag ranking results, the original training tag set is filtered to determine the target training tag set corresponding to the target energy storage user.

5. The method according to claim 1, characterized in that, The training content generation model includes a training framework determination module and a training content generation module. The step of inputting the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user includes: The target training tag set is input into the training framework determination module to generate a framework and determine the target training framework information corresponding to the target energy storage user. The target training framework information is input into the training content generation module to generate training content, thereby obtaining the target training content information corresponding to the target energy storage user.

6. The method according to claim 1, characterized in that, After obtaining the target training content information corresponding to the target energy storage user, the method further includes: In response to the target energy storage user's completion of learning the target training content information, obtain the training content completion information corresponding to the target energy storage user; Based on the training content completion information, the training efficiency information corresponding to the target energy storage user is determined.

7. A training content generation device, characterized in that, include: The information acquisition module is used to acquire the target training needs information and user skill level information of the target energy storage users to be trained; The training tag determination module is used to perform knowledge graph mapping based on the target training needs information and the user skill level information to determine the target training tag set corresponding to the target energy storage user; The content information acquisition module is used to input the target training tag set into the training content generation model to generate training content and obtain the target training content information corresponding to the target energy storage user. The training tag determination module is specifically used for: performing knowledge graph mapping based on the target training demand information and the user skill level information to determine the original training tag set corresponding to the target energy storage user; calculating the comprehensive score corresponding to each candidate training tag in the original training tag set according to a preset topic selection algorithm, and arranging them from high to low according to the comprehensive score to determine the candidate tag ranking result; selecting tags sequentially from front to back based on the training time corresponding to each candidate training tag in the candidate tag ranking result, combined with the user demand time in the target training demand information, so that the total training time corresponding to all selected tags does not exceed the user demand time, and determining the target training tag set corresponding to the target energy storage user; The content information acquisition module is specifically used for: inputting the target training tag set into the training framework determination module to construct a framework using a modular Prompt template, and outputting the target training framework information corresponding to the target energy storage user; inputting the target training framework information into the training content generation module to parse it using a large language model and generate specific training content, thereby obtaining the target training content information corresponding to the target energy storage user.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the training content generation method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the training content generation method according to any one of claims 1-6.

Images