Knowledge question and answer game content generation method and device and electronic equipment

Abstract

The invention provides a knowledge question and answer game content generation method and device and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring target knowledge data corresponding to a knowledge question-answer game; determining a semantic network according to the target knowledge data; based on the semantic network, adopting multiple agents to generate a first problem; obtaining a first answer corresponding to the first question by the user; performing feedback evolution on the first answer, and outputting a second question; and obtaining knowledge question-answer game content through the first question, the first answer and the second question. By implementing the technical scheme provided by the invention, the intelligence of knowledge question and answer game content generation can be improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method, apparatus, and electronic device for generating knowledge quiz game content. Background Art

[0002] As an interactive form that combines entertainment and education, knowledge quiz games have gained extensive attention and application globally in recent years. It not only occupies an important position in the entertainment industry but also shows great potential in fields such as education, training, and scientific research.

[0003] Currently, most existing knowledge quiz games rely on pre-set fixed question banks and logical processes for question generation and answer. In this traditional model, the generation of questions and answers is usually static, based on fixed rules or database content. During the game process, the player's choices only determine the order of answering questions, and there is almost no real-time feedback mechanism for the system to generate and adjust questions. Therefore, the intelligence of generating knowledge quiz game content in the prior art is relatively low.

[0004] Therefore, there is an urgent need for a method, apparatus, and electronic device for generating knowledge quiz game content. Summary of the Invention

[0005] This application provides a method, apparatus, and electronic device for generating knowledge quiz game content, which is convenient for improving the intelligence of generating knowledge quiz game content.

[0006] In the first aspect of this application, a method for generating knowledge quiz game content is provided. The method includes: obtaining target knowledge data corresponding to a knowledge quiz game; determining a semantic network according to the target knowledge data; generating a first question by using multiple agents based on the semantic network; obtaining a first answer of a user corresponding to the first question; performing feedback evolution on the first answer to output a second question; and obtaining knowledge quiz game content through the first question, the first answer, and the second question.

[0007] By adopting the above technical solutions, first, constructing a semantic network by using target knowledge data can ensure that the generated questions are highly relevant to the knowledge content, enhancing the educational and effectiveness of the game. By collaborating multiple agents to generate questions, the intelligence and dynamic adjustment of questions can be achieved, avoiding the limitations of traditional question banks, thereby improving the personalization and adaptability of questions. Further, through the feedback evolution mechanism, subsequent questions are adjusted in real time according to the user's answers, ensuring that the difficulty of the questions matches the user's knowledge mastery level and improving the user experience. Generally speaking, this method can provide accurate learning content while maintaining the interactivity, challenge, and entertainment of the game, thereby enhancing the player's participation and learning effect. Therefore, it is convenient for improving the intelligence of generating knowledge quiz game content.

[0008] Optionally, determining a semantic network according to the target knowledge data specifically includes: splitting the target knowledge data into text to obtain target knowledge cells; determining the relationships between the target knowledge cells to obtain semantic relationships; vectorizing the target knowledge cells to obtain a first target knowledge cell and a second target knowledge cell, where the first target knowledge cell and the second target knowledge cell are any two target knowledge cells among the multiple target knowledge cells; calculating the cell similarity between the first target knowledge cell and the second target knowledge cell; and constructing the semantic network according to the cell similarity and the semantic relationship.

[0009] By adopting the above technical solution, first, by splitting the target knowledge data into text, complex knowledge is transformed into finer-grained target knowledge cells, which can make the knowledge representation more refined and facilitate subsequent processing and analysis. Second, by determining the relationships between the target knowledge cells and vectorizing them, the semantic relevance between different knowledge points can be accurately captured, thus providing a solid foundation for subsequent reasoning and question generation. In particular, by calculating the cell similarity, the similarity degree between different knowledge cells can be revealed, helping the model better understand the relationships between knowledge points, and constructing a high-quality semantic network according to these similarities and semantic relationships, improving the relevance and intelligence of question generation. Finally, this method can ensure that the generated questions and answers are more logical, targeted, and personalized, effectively improving the educational nature and user experience of the game, and at the same time providing solid data support for subsequent intelligent feedback evolution.

[0010] Optionally, generating a first question by using multiple agents based on the semantic network specifically includes: extracting a knowledge core according to the semantic network; controlling an expert agent to generate a first draft based on a large language model according to the knowledge core; controlling a student agent to generate a second draft based on a prompting algorithm according to the knowledge core; semantically fusing the first draft and the second draft to obtain a third draft; and adjusting the third draft through a verification agent to generate the first question, where the multiple agents include the expert agent, the student agent, and the verification agent.

[0011] By adopting the above technical solution, by combining semantic networks, it is possible to ensure that the generated questions closely match the core knowledge points, making the questions more accurate and relevant. Using expert agents and student agents to generate drafts based on large language models and prompt algorithms respectively can achieve multi-angle and different-level knowledge expressions, thus ensuring the diversity and richness of the questions, while considering different knowledge depths and difficulties. Through semantic fusion, the advantages of the two drafts can be combined to optimize the question content and improve the quality of the questions. Finally, the verification agent adjusts the draft to ensure that the generated questions are highly logical and accurate, thus avoiding the biases or deficiencies that may occur in a single agent. This multi-agent collaboration method not only enhances the flexibility and intelligence of question generation, but also greatly improves the question quality and adaptability, making the game content more in line with the needs of players, and enhancing the user experience and learning effect.

[0012] Optionally, the feedback evolution of the first answer to output a second question specifically includes: obtaining the preset answer corresponding to the first question; using the BERT model to determine the preset answer vector corresponding to the preset answer; using the BERT model to determine the first answer vector corresponding to the first answer; calculating the answer similarity between the preset answer vector and the first answer vector; if it is determined that the answer similarity is greater than the preset threshold, obtaining the first keyword from the first answer; comparing the first keyword with the preset keyword library to generate a comparison result, and the preset keyword library is constructed according to the preset answer; determining the second question according to the comparison result.

[0013] By adopting the above technical solution, by vectorizing the preset answer and the first answer using the BERT model and calculating the answer similarity between them, the matching degree between the player's answer and the correct answer can be accurately evaluated. This method avoids the limitations of traditional systems relying on fuzzy matching or simple comparison through quantitative similarity calculation, and improves the accuracy and reliability of feedback. If the player's answer is close to the preset answer, the system will further extract keywords and compare them with the preset keyword library, which not only helps to confirm the key points of the answer, but also refines the depth and scope of the question. Finally, the second question generated based on these feedback and analysis results can better adapt to the player's answering status and knowledge mastery, making the difficulty and content of the question more personalized, thereby enhancing the player's sense of participation and learning effect. This intelligent feedback mechanism improves the game interactivity while effectively promoting the realization of personalized learning.

[0014] Optionally, determining the second question according to the comparison result specifically includes: if it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library does not meet the preset quantity, determining the second question as a supplementary question based on the first question; if it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library meets the preset quantity, determining the second question as an expansion question based on the semantic network.

[0015] By adopting the above technical solution, through precise keyword matching and similarity analysis, the generation of the second question becomes more intelligent and personalized. By comparing the matching degree between the first keyword and the preset keyword library, the system can flexibly adjust the type of questions dynamically according to the player's answering performance. If the player's answer fails to cover sufficient core concepts or knowledge points, the system will generate supplementary questions to help the player further master the missing knowledge; while when the answer is relatively accurate, the system will construct expansion questions to guide the player to think deeply and expand the knowledge scope. This dynamic adjustment based on keyword matching and semantic network not only improves the relevance and pertinence of the questions, but also ensures that the player can obtain timely feedback and challenges during the learning process, thereby increasing the depth and breadth of learning, and effectively improving the educational nature and interactivity of the game.

[0016] Optionally, the method further includes: obtaining the second answer corresponding to the second question by the user; determining the first accuracy rate corresponding to the first answer and the second accuracy rate corresponding to the second answer; if it is determined that both the first accuracy rate and the second accuracy rate are higher than the preset accuracy rate, generating a third question, and the difficulty of the third question is greater than the difficulties corresponding to the first question and the second question respectively.

[0017] By adopting the above technical solution, through the accuracy rate evaluation and dynamic difficulty adjustment mechanism, the intelligent and personalized experience of the knowledge quiz game is effectively improved. By comparing the accuracy rates of the first answer and the second answer, the system can objectively evaluate the player's performance in two rounds of answering questions. If the player's answer accuracy is relatively high, the system will automatically generate a third question with a higher difficulty, which can not only meet the player's need for challenge, but also promote the player to continuously improve the knowledge level and avoid getting stuck in repetitive and low-difficulty questions. Through this performance-based progressive difficulty design, the game can dynamically adjust the difficulty according to the player's mastery, ensure that each player can challenge within a suitable difficulty range, thereby maintaining the fun and educational effect of the game, and at the same time stimulating the player's learning interest and sense of achievement. This mechanism can improve the interactivity while ensuring the realization of the personalized learning path.

[0018] Optionally, the method further includes: obtaining training information, where the training information includes a training answer and a training answer vector; inputting the training information into an adaptive word vector fusion network for training to obtain a first training result; performing superposition and normalization processing on the first training result and the training information to obtain a second training result; inputting the second training result into the adaptive word vector fusion network for processing to obtain a third training result; performing superposition and normalization processing on the third training result and the second training result until the training information similarity matrix is output, to obtain the BERT model, where the training information similarity matrix satisfies a preset logistic regression condition.

[0019] By adopting the above technical solution, the adaptive word vector fusion network training method has significant advantages and can effectively improve the answer processing accuracy and model performance in the knowledge quiz game. By repeatedly inputting the training information into the adaptive word vector fusion network for iterative training, the system can gradually optimize the training result, ensuring that the representation of the word vector is more accurate and consistent after multiple rounds of fusion and normalization processing. This process of gradually superposing and normalizing helps to eliminate noise and improve the stability of the vector representation, enabling the generated similarity matrix to accurately reflect the semantic relationship between answers. Finally, by satisfying the preset logistic regression condition, the BERT model can better capture the subtle differences and correlations of answers, thereby improving the intelligence and accuracy of question generation and answer matching in the knowledge quiz game. This method not only enhances the adaptive ability of the model but also ensures that in complex semantic reasoning and multi-round interactions, the game content can accurately adapt to the player's knowledge level and answering performance.

[0020] In a second aspect of the present application, a knowledge quiz game content generation device is provided. The device includes an acquisition module and a processing module. Among them, the acquisition module is used to acquire target knowledge data corresponding to the knowledge quiz game; the processing module is used to determine a semantic network according to the target knowledge data; the processing module is further used to generate a first question based on the semantic network by using multiple agents; the acquisition module is further used to acquire a first answer of the user for the first question; the processing module is used to perform feedback evolution on the first answer and output a second question; the processing module is used to obtain knowledge quiz game content through the first question, the first answer, and the second question.

[0021] In a third aspect of the present application, an electronic device is provided. The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed, perform the method described above.

[0023] In summary, one or more technical solutions provided in the present application have at least the following technical effects or advantages: First, constructing a semantic network using target knowledge data can ensure that the generated questions are highly relevant to the knowledge content, enhancing the educational and effectiveness of the game. By generating questions through multi-agent collaboration, the intelligence and dynamic adjustment of questions can be achieved, avoiding the limitations of traditional question banks, thereby improving the personalization and adaptability of questions. Further, through the feedback evolution mechanism, subsequent questions are adjusted in real time according to the user's answers, ensuring that the question difficulty matches the user's knowledge mastery level and improving the user experience. Generally speaking, this method can provide accurate learning content while maintaining the interactivity, challenge, and entertainment of the game, thereby enhancing the player's participation and learning effect. Therefore, it is convenient to improve the intelligence of generating knowledge Q&A game content. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic flowchart of a method for generating knowledge answering game content provided by an embodiment of the present application; Figure 2 It is another schematic flowchart of a method for generating knowledge answering game content provided by an embodiment of the present application; Figure 3 It is a schematic block diagram of a device for generating knowledge answering game content provided by an embodiment of the present application; Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0025] Description of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] As an interactive form that combines entertainment and education, the quiz game has gained extensive attention and application globally in recent years. It not only occupies an important position in the entertainment industry but also shows great development potential in many fields such as education, training, and scientific research.

[0030] However, most current quiz games still rely on pre-set fixed question banks and logical processes to generate questions and answers. The questions and answers in these traditional models are usually static and are processed based on fixed rules or database content. During the game, the player's choices only determine the answering order, and the system lacks a real-time feedback mechanism for generating and adjusting questions. Therefore, in the prior art, quiz games are weak in terms of intelligence and personalization and cannot make flexible adjustments according to the player's real-time performance and needs.

[0031] To solve the above technical problems, the present application provides a method for generating quiz game content, referring to Figure 1 , Figure 1 is a schematic flowchart of a method for generating quiz game content provided by an embodiment of the present application. This method is applied to a server and includes steps S110 to S160. The above steps are as follows: S110. Obtain the target knowledge data corresponding to the quiz game.

[0032] Specifically, as the core part of the system, the server is responsible for communicating with external resources to obtain the required data. Here, the server is the entity responsible for extracting data from a certain knowledge source. This data can come from a local database, an online open API, or a specific educational resource library, etc. In a knowledge quiz game, the target knowledge data is usually the basis of the game content. For example, each question in the game may involve a specific knowledge point (such as historical events, mathematical theorems, geographical knowledge, etc.), and these knowledge points constitute the core of the game. Target knowledge data refers to the specific information required in a knowledge quiz game, which can be facts, definitions, formulas, historical events, scientific theories, etc. These data are the basis for generating relevant questions and answers.

[0033] For example: Suppose we have a historical knowledge quiz game where the player's task is to answer various questions about world history. Historical events: such as "World War II". Person information: such as "Winston Churchill". Time node: such as "1914". Location: such as "Normandy". In the game, the player may encounter a question like: Question: "Which year was the beginning of World War II?", Answer: "1939". The server obtains relevant data from a historical knowledge database or API to support the game content. In this process, the server extracts relevant data from the historical knowledge base, such as world wars, historical figures, time nodes, etc., and then uses these data to generate specific game questions and answers.

[0034] S120. Determine a semantic network according to the target knowledge data.

[0035] Specifically, in a knowledge Q&A game, the server constructs a semantic network by processing the acquired target knowledge data. A semantic network is a structure that represents knowledge points and their interrelationships. It can help the system understand the connections between different knowledge points and support more intelligent question generation, answer matching, and other functions. The server obtains the specific knowledge data from a certain data source (such as a database or an API). At this stage, the server has obtained knowledge information about a specific field or topic. For example, historical data about "World War II", biological data about "photosynthesis", etc. A semantic network is a knowledge structure represented graphically, where nodes represent knowledge units (such as concepts, events, terms, etc.), and edges represent the relationships between these knowledge units (such as causal relationships, belonging relationships, association relationships, etc.). The semantic network builds the connections between knowledge points through nodes and edges, helping the system better understand and reason. The server analyzes and determines the relationships between these knowledge points based on the acquired target knowledge data. Then, the system connects the knowledge points through semantic relationships (such as "definition", "contains", "occurs before and after", "affects", etc.) to form a semantic network. This semantic network is the basis for subsequent functions such as question generation and answer recommendation.

[0036] In a possible implementation manner, determining a semantic network according to target knowledge data specifically includes: splitting the target knowledge data into text to obtain target knowledge cells; determining the relationships between the respective target knowledge cells to obtain semantic relationships; vectorizing the target knowledge cells to obtain a first target knowledge cell and a second target knowledge cell, where the first target knowledge cell and the second target knowledge cell are any two target knowledge cells among the multiple target knowledge cells; calculating the cell similarity between the first target knowledge cell and the second target knowledge cell; and constructing a semantic network according to the cell similarity and the semantic relationships.

[0037] Specifically, text splitting refers to breaking down the target knowledge data (usually the original text or structured information) into smaller and more basic units called knowledge cells. These knowledge cells can be terms, concepts, definitions, events, formulas, etc., which are the smallest building blocks of the knowledge system. For example, assuming the target knowledge data comes from "The beginning of World War II was in 1939, and the D-Day landing was a turning point in the war situation", after text splitting, the possible target knowledge cells obtained may include: "World War II", "1939", "D-Day landing", "turning point in the war situation". Semantic relationships refer to the mutual connections between these knowledge cells. For example, the relationship between "World War II" and "1939" is "began in", while the relationship between "D-Day landing" and "World War II" is "key event" or "battle". In this step, the system will analyze and mark the relationships between these cells, for example: World War II began in 1939, and the D-Day landing was a key event in World War II.

[0038] Vectorization is the process of converting text or knowledge cells into vectors for subsequent calculations and comparisons. Usually, natural language processing (NLP) methods such as BERT, Word2Vec, or other embedding models are used to generate vector representations of each target knowledge cell. Vectorization converts text information into numerical form, enabling computers to process and analyze it. In this step, the first target knowledge cell (such as "World War II") and the second target knowledge cell (such as "1939") will be respectively converted into vector representations. Cell similarity is used to measure the similarity between target knowledge cells by calculating the vector representations between them. Common methods for calculating similarity include cosine similarity, Euclidean distance, etc. For example, after generating the vector representations of "World War II" and "1939" through the BERT model, the similarity between these two vectors can be calculated. If their similarity is high, it indicates that their relationship is relatively close and they may have a strong semantic association. A semantic network is a graph composed of nodes (target knowledge cells) and edges (the relationships between them). Through cell similarity and semantic relationships, the system connects knowledge cells into a network, where each node represents a knowledge cell and the edges represent the semantic relationships between knowledge cells. For example, "World War II" and "D-Day landing" are connected by a battle relationship, while "D-Day landing" and "1939" are connected by a time point relationship. The semantic network helps the system understand how these knowledge points are interrelated, facilitating the subsequent generation of questions and answers.

[0039] S130. Based on the semantic network, use multiple agents to generate the first question.

[0040] Specifically, the server is the core part of the entire system, and it is responsible for processing and calculating data. The "semantic network" here refers to a network with clear relationships between knowledge points constructed through the processing of target knowledge data. The semantic network can help the server understand the connections between different knowledge points and provide the necessary background and support for generating questions. Multi-agent means that multiple agents collaborate to solve tasks. In the knowledge Q&A game, the multi-agents include: Expert agent: Focusing on the professionalism and accuracy of questions, capable of generating in-depth questions. Student agent: Emphasizing the understandability and popularity of questions to ensure that the questions are acceptable to players. Verification agent: Responsible for checking the logic, grammar, and accuracy of questions to ensure that the questions are unambiguous and conform to the structure of knowledge points. These agents are each responsible for different tasks and collaborate to generate the final questions. Through the collaboration of multi-agents, the system can generate questions that are both in-depth and understandable.

[0041] For example: Suppose we have a biology knowledge Q&A game where players need to answer questions about photosynthesis. Assume that the server constructs the following semantic network based on biology knowledge: Knowledge cells (nodes): Photosynthesis, chloroplast, carbon dioxide, water, chlorophyll, reaction formula. Semantic relationships (edges): Photosynthesis occurs in the chloroplast, photosynthesis requires water and carbon dioxide, chlorophyll helps capture light energy, and the photosynthesis reaction formula is XXX. Among them, the server uses this semantic network and generates the first question through multi-agents: "What are the core steps of the electron transport chain in photosynthesis?"

[0042] In a possible implementation manner, based on the semantic network, the first question is generated by multi-agents, specifically including: extracting the knowledge core according to the semantic network; controlling the expert agent to generate the first draft based on the large language model according to the knowledge core; controlling the student agent to generate the second draft based on the prompt word algorithm according to the knowledge core; semantically fusing the first draft and the second draft to obtain the third draft; and adjusting the third draft through the verification agent to generate the first question. The multi-agents include the expert agent, the student agent, and the verification agent.

[0043] Specifically, the semantic network helps the system understand the structure of knowledge by representing the relationships between different knowledge points. In this step, the system extracts the knowledge core from the semantic network, that is, the most crucial and central knowledge points. For example, if the target knowledge is "photosynthesis", the system may extract keywords such as "photosynthesis reaction formula", "chlorophyll", and "light energy" from the semantic network. The task of the expert agent is to generate a highly professional draft to ensure that the question has sufficient academic depth. Based on the extracted knowledge core, the expert agent generates the first draft of the question through a large language model, and this draft contains detailed and high-level knowledge content. Example: Suppose the knowledge core is "photosynthesis reaction formula", and the expert agent may generate a draft similar to the following: "Please describe in detail the electron transport chain in photosynthesis and its key steps."

[0044] The student agent focuses on generating questions that are more suitable for ordinary players or students and are easy to understand. The student agent uses a prompting algorithm based on the knowledge core to generate the second draft, which will be more concise, easy to understand, and help players understand the core knowledge. Example: Based on the core of "photosynthesis reaction formula", the student agent may generate a more simplified question, such as: "What is the reaction formula of photosynthesis?"

[0045] Next, the server performs semantic fusion on the drafts generated by the expert agent and the student agent, combines the advantages of both, and generates a balanced question suitable for a wide range of players. Semantic fusion refers to integrating the content of the two drafts, removing duplicate or unnecessary parts, and ensuring that the question has both depth and can be understood by most players. Example: After merging the first draft and the second draft, a question similar to the following may be obtained: "What is the reaction formula of photosynthesis? Please explain the key reaction steps therein."

[0046] The task of the verification agent is to perform logical and language verification on the generated third draft to ensure the accuracy, clarity, and unambiguity of the question, and at the same time check whether it meets the design goals of the game (such as difficulty, learning effect, etc.). The verification agent may adjust the wording or content of the question to make it more precise and standardized. Example: If the wording of a certain part in the draft is not clear or the question expression is ambiguous, the verification agent may rewrite the question. For example, it may adjust "Please explain the key reaction steps therein" to "Please briefly describe the key reaction steps in the photosynthesis reaction formula". After the collaborative work of multiple agents, the generated first question will synthesize academic depth, understandability, and accuracy, and become a question that is both challenging and meets the learning goals. Example: The finally generated first question may be: "What is the reaction formula of photosynthesis? Please briefly describe the key reaction steps in the reaction formula." For example: Suppose the goal of a knowledge quiz game is to test players' understanding of photosynthesis. The following is the detailed generation process: Knowledge core: "Photosynthesis reaction formula", "Role of chlorophyll in photosynthesis", "Process of photosynthesis". Draft questions generated by the expert agent: "Please describe in detail the electron transport chain in photosynthesis and its key steps. How is light energy converted into chemical energy? Please give examples." Draft questions generated by the student agent: "What is the reaction formula of photosynthesis? How does photosynthesis utilize light energy?" After fusing the drafts of the expert and the student, the third draft is obtained: "What is the reaction formula of photosynthesis? Please briefly describe the key steps of photosynthesis." The verification agent may find that "briefly describe" is not clear enough and may modify it to: "Please briefly describe the key reaction steps in the photosynthesis reaction formula." After multiple-agent adjustments, the final first question generated is: "What is the reaction formula of photosynthesis? Please briefly describe the key reaction steps in the reaction formula." This passage describes the process of generating questions in a knowledge quiz game through multi-agent collaboration. The expert agent is responsible for generating academic questions, the student agent generates easy-to-understand questions, and the verification agent ensures the accuracy and logic of the questions. Through semantic fusion, the final questions can not only meet the in-depth requirements but also be suitable for the players' understanding ability. This multi-agent cooperation method ensures the intelligence, flexibility, and personalization of question generation, and can greatly improve the educational and entertaining nature of the game.

[0047] S140. Obtain the first answer corresponding to the first question from the user.

[0048] Specifically, during the execution of the knowledge quiz game, the server will receive and obtain in real time the user's answer to the first question, that is, the answer submitted by the user for the first question generated by the system. This answer can be in various forms such as text, voice, or options. Only after the server obtains this first answer can it further analyze, judge, and process, such as judging whether the answer is correct, analyzing the key elements of the answer, or using it for the intelligent generation and feedback evolution of subsequent questions.

[0049] For example: Suppose in a knowledge quiz game, the first question generated by the server is: "Please briefly describe the main processes of the water cycle?" The answer entered by the user in the game is: "The water cycle mainly includes processes such as evaporation, condensation, and precipitation." At this time, the server will automatically obtain and record this answer content entered by the user, that is, this passage is the "first answer" of the user to the first question. Subsequently, the system can perform answer matching, keyword extraction, answer accuracy calculation, and even use it to automatically generate supplementary questions or more challenging questions based on this first answer. The advantage of this process is that it can make the knowledge quiz game more intelligent and dynamic, not simply judging right or wrong, but deeply understanding the content of the user's answer and providing personalized feedback and the design of the next step based on the real answer, greatly enhancing the interactivity and learning effect of the game.

[0050] S150. Perform feedback evolution on the first answer and output the second question.

[0051] Specifically, after the server obtains the user's answer (the first answer) to the first question, it does not simply judge right or wrong or directly move on to the next question, but conducts in-depth analysis and processing of this answer of the user. The server will, based on the content of the user's answer, combine the existing knowledge data and semantic network, and through certain intelligent algorithms (such as answer similarity calculation, keyword extraction, semantic analysis, etc.), perform feedback and evolution on the user's answer, and dynamically generate a more targeted and personalized second question. This second question may be to help the user further understand the knowledge, check for omissions and make up for deficiencies, or increase the difficulty of answering questions, so as to achieve a more in-depth and logical interactive question-and-answer experience.

[0052] It makes the knowledge quiz no longer a mechanical rote memorization, but has the feedback ability of "teaching students in accordance with their aptitude". The server can discover knowledge blind spots or understanding deviations based on the specific answer content of the user, and then intelligently generate supplementary or extended questions to help the user improve the knowledge structure, deepen the understanding, and at the same time enhance the fun and personalized experience of the game. This dynamically evolving question-and-answer mechanism can effectively enhance the learning effect and sense of participation of the user.

[0053] In a possible implementation manner, performing feedback evolution on the first answer and outputting the second question specifically includes: obtaining the preset answer corresponding to the first question; using the BERT model to determine the preset answer vector corresponding to the preset answer; using the BERT model to determine the first answer vector corresponding to the first answer; calculating the answer similarity between the preset answer vector and the first answer vector; if it is determined that the answer similarity is greater than the preset threshold, obtaining the first keyword from the first answer; comparing the first keyword with the preset keyword library to generate a comparison result, and the preset keyword library is constructed according to the preset answer; and determining the second question according to the comparison result.

[0054] Specifically, obtain the standard answer (preset answer): the server has prepared the correct or standard answer to the question in advance. BERT is a deep learning model for natural language understanding. The server uses it to convert the preset answer into a vector (preset answer vector), and also converts the user's first answer into a vector (first answer vector). By comparing the similarity between the two vectors, the degree of closeness between the user's answer and the standard answer is judged. If the answer similarity is greater than a certain set threshold (indicating that the answer is not bad, but may not be comprehensive or detailed enough), the server extracts the core first keyword from the user's first answer. Compare the keywords in the user's answer with the preset keyword library (this is a collection of knowledge points sorted based on the standard answer), analyze which keywords have been mentioned and which have not been involved, and form a comparison result. The server designs the second question in a targeted manner based on the missing or weak parts of the user's answer to supplement the knowledge blind spots or expand related knowledge.

[0055] This "feedback evolution" mechanism breaks the limitations of traditional question-and-answer games that simply judge right or wrong or set fixed questions. Through the BERT semantic model and keyword comparison, it achieves a deep understanding and personalized diagnosis of user answers. This not only stimulates users' thinking and exploration, but also automatically identifies blind spots or weak points in users' knowledge structure, and generates more targeted, inspiring and educational follow-up questions in real time, making the entire knowledge question-and-answer process smarter, more flexible, and more adaptable to the learning paths of different users, greatly enhancing the educational value and user experience of the game.

[0056] In a possible implementation, based on the comparison result, determining the second question specifically includes: if it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library does not meet the preset number, then determining the second question as a supplementary question based on the first question; if it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library meets the preset number, then determining the second question as an extensibility question based on the semantic network.

[0057] Specifically, after the server compares the keywords of the user's first answer, it will determine the type of the second question based on the comparison results. If the number of keywords in the user's answer is quite different from that in the standard answer (indicating that the user's answer is incomplete or key information is omitted), the server will generate a "supplementary question" to continue to guide the user to complete the answer around the original question. On the contrary, if the user's keyword coverage is relatively comprehensive (indicating that the user has a good grasp of it), the server will no longer be limited to the original question, but will generate an "extended question" based on the semantic network to guide the user to explore new content related to the original knowledge that is deeper or broader.

[0058] For example, assume that the first question is "Briefly explain why the Earth has seasonal changes", and the user's answer is "Because the Earth revolves around the sun". After keyword comparison, it is found that the important keyword "axial tilt" is missing and does not meet the preset quantity. Then the server generates a supplementary question: "Do you know if the Earth's axis of rotation affects the seasonal changes?"; If the user's answer is "Because the Earth revolves around the sun and at the same time the Earth's axis is tilted, resulting in changes in the direct sunlight point", the number of keywords has reached the standard, and the server generates an extended question: "Do you know if there are similar seasonal change phenomena on other planets besides the Earth?"

[0059] S160. Obtain the content of the knowledge quiz game through the first question, the first answer, and the second question.

[0060] Specifically, the server will integrate and process the existing three key elements - "the first question", "the user's first answer", and "the second question generated after feedback based on the first answer", and finally generate a complete and personalized knowledge quiz game content. That is to say, the server does not simply stack questions, but dynamically adjusts the question design, content presentation, and answering process according to the user's actual answering situation, so as to make the entire game content more targeted, interactive, and interesting.

[0061] For example, assume that the theme of the knowledge quiz game is "astronomical knowledge". The server first generates the first question: "Please briefly explain the composition of the solar system." The user's answer (the first answer) is: "The sun, the Earth, and Mars." After analysis, the server finds that the user only mentions some of the planets and omits other components, so it generates the second question: "What other planets or celestial bodies are there in the solar system besides the sun, the Earth, and Mars?" Finally, the server combines these two questions and the user's answer to generate the complete content of the knowledge quiz game. This way can make the knowledge quiz game no longer a simple question answering from a question bank, but a teaching assistant like "having ideas, responses, and interactions". It can automatically adjust the game content according to the user's answering situation, truly achieving individualized teaching, and enhancing the fun, educational value, and immersive experience of the game.

[0062] In a possible implementation manner, obtain the second answer corresponding to the second question by the user; determine the first accuracy rate corresponding to the first answer and the second accuracy rate corresponding to the second answer; if it is determined that both the first accuracy rate and the second accuracy rate are higher than the preset accuracy rate, then generate a third question, and the difficulty of the third question is greater than the difficulty of each of the first question and the second question.

[0063] Specifically, the server will continue to obtain the user's answer to the "second question" (i.e., the second answer), and then evaluate the user's answering accuracy for the "first question" and the "second question" respectively. If the evaluation results show that the user's answering accuracy for both questions exceeds the system-set standard (such as a preset accuracy rate of 70% or 80%), it indicates that the user has a relatively high knowledge level and excellent answering performance. At this time, the server will automatically generate a new and more difficult third question to upgrade the challenge of the game and further examine and improve the user's knowledge level.

[0064] In a possible implementation manner, referring to Figure 2 , Figure 2 is another flowchart of a method for generating knowledge quiz game content provided by an embodiment of the present application. It includes steps S210 to S250, and the above steps are as follows: S210, obtain training information, where the training information includes a training answer and a training answer vector; S220, input the training information into an adaptive word vector fusion network for training to obtain a first training result; S230, after superimposing and normalizing the first training result with the training information, obtain a second training result; S240, input the second training result into the adaptive word vector fusion network for processing to obtain a third training result; S250, superimpose and normalize the third training result with the second training result until a training information similarity matrix is output to obtain a BERT model, and the training information similarity matrix satisfies a preset logistic regression condition.

[0065] Specifically, training information is the core data for model training, including two parts: training answers, which are the correct answers or preset standard answers; and training answer vectors, which are the vector representations of training answers. Usually, through some word embedding methods (such as Word2Vec or BERT), the answers are transformed into numerical vector forms so that the computer can process them. The adaptive word vector fusion network is a network model for optimizing word vector learning. Through training, the network gradually adjusts the weights and relationships of each word vector, making the calculation of answers and similarities more accurate. In this step, the training information is input into the network for the first training to obtain the first training result, that is, the adjustment of the word vector obtained after network processing. The first training result will be subjected to "superposition and normalization processing" with the original training information. This means that after the first iteration of the network, through some mathematical operations (such as weighted summation, normalization, etc.), the result is adjusted to make it more stable and accurate, obtaining the second training result, that is, the optimized and adjusted word vector. The second training result is input into the adaptive word vector fusion network for the second round of processing to obtain the third training result. This process is to further finely adjust the accuracy of the model. Through repeated training and adjustment, a training information similarity matrix is finally output. This matrix is used to measure the similarity between different training information. The similarity matrix is a matrix calculated by the model, and each element in it represents the similarity degree between two training information (usually calculated by algorithms such as cosine similarity). This matrix will finally meet certain preset conditions, such as the logistic regression condition, indicating that the prediction and calculation accuracy of the model has reached a certain standard. Finally, through this adaptive training process, the obtained similarity matrix and training results will be used to optimize the BERT model, enabling BERT to more accurately understand and process natural language in subsequent tasks.

[0066] The present application also provides a device for generating knowledge quiz game content. Referring to Figure 3 , Figure 3 is a schematic diagram of the modules of a device for generating knowledge quiz game content provided by an embodiment of the present application. The device is a server, including an acquisition module 31 and a processing module 32. Among them, the acquisition module 31 acquires target knowledge data corresponding to the knowledge quiz game; the processing module 32 determines a semantic network according to the target knowledge data; the processing module 32 generates a first question based on the semantic network using multiple agents; the acquisition module 31 acquires the first answer of the user corresponding to the first question; the processing module 32 performs feedback evolution on the first answer and outputs a second question; the processing module 32 obtains the knowledge quiz game content through the first question, the first answer, and the second question.

[0067] In a possible implementation, the processing module 32 determines a semantic network according to the target knowledge data, specifically including: the processing module 32 splits the target knowledge data into texts to obtain target knowledge cells; the processing module 32 determines the relationships between the respective target knowledge cells to obtain semantic relationships; the processing module 32 vectorizes the target knowledge cells to obtain a first target knowledge cell and a second target knowledge cell, where the first target knowledge cell and the second target knowledge cell are any two target knowledge cells among the multiple target knowledge cells; the processing module 32 calculates the cell similarity between the first target knowledge cell and the second target knowledge cell; the processing module 32 constructs a semantic network according to the cell similarity and the semantic relationship.

[0068] In a possible implementation, the processing module 32 generates a first question by using multiple agents based on the semantic network, specifically including: the processing module 32 extracts a knowledge core according to the semantic network; the processing module 32 controls an expert agent to generate a first draft based on a large language model according to the knowledge core; the processing module 32 controls a student agent to generate a second draft based on a prompting algorithm according to the knowledge core; the processing module 32 semantically fuses the first draft and the second draft to obtain a third draft; the processing module 32 adjusts the third draft through a verification agent to generate a first question, and the multiple agents include an expert agent, a student agent, and a verification agent.

[0069] In a possible implementation, the processing module 32 performs feedback evolution on the first answer and outputs a second question, specifically including: the acquisition module 31 acquires a preset answer corresponding to the first question; the processing module 32 uses a BERT model to determine a preset answer vector corresponding to the preset answer; the processing module 32 uses a BERT model to determine a first answer vector corresponding to the first answer; the processing module 32 calculates the answer similarity between the preset answer vector and the first answer vector; if the processing module 32 determines that the answer similarity is greater than a preset threshold, it acquires a first keyword from the first answer; the processing module 32 compares the first keyword with a preset keyword library to generate a comparison result, and the preset keyword library is constructed according to the preset answer; the processing module 32 determines a second question according to the comparison result.

[0070] In a possible implementation, the processing module 32 determines a second question according to the comparison result, specifically including: if the processing module 32 determines that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library does not meet a preset quantity, it determines that the second question is a supplementary question based on the first question; if the processing module 32 determines that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library meets the preset quantity, it determines that the second question is an expansion question based on the semantic network.

[0071] In a possible implementation, the obtaining module 31 obtains a second answer corresponding to a second question of a user; the processing module 32 determines a first accuracy rate corresponding to a first answer and a second accuracy rate corresponding to the second answer; if the processing module 32 determines that both the first accuracy rate and the second accuracy rate are higher than a preset accuracy rate, a third question is generated, and the difficulty corresponding to the third question is greater than the difficulties corresponding to the first question and the second question respectively.

[0072] In a possible implementation, the obtaining module 31 obtains training information, where the training information includes a training answer and a training answer vector; the processing module 32 inputs the training information into an adaptive word vector fusion network for training to obtain a first training result; the processing module 32 performs superposition and normalization processing on the first training result and the training information to obtain a second training result; the processing module 32 inputs the second training result into the adaptive word vector fusion network for processing to obtain a third training result; the processing module 32 performs superposition and normalization processing on the third training result and the second training result until a training information similarity matrix is output to obtain a BERT model, and the training information similarity matrix satisfies a preset logistic regression condition.

[0073] It should be noted that: when the device provided in the above embodiments implements its functions, only the division of the above-mentioned functional modules is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments and will not be elaborated here.

[0074] This application also provides an electronic device. Refer to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 41, at least one network interface 44, a user interface 43, a memory 45, and at least one communication bus 42.

[0075] Among them, the communication bus 42 is used to realize the connection and communication between these components.

[0076] Among them, the user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may further include a standard wired interface and a wireless interface.

[0077] Among them, the network interface 44 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface).

[0078] Among them, the processor 41 may include one or more processing cores. The processor 41 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 45, and by calling data stored in the memory 45, it performs various functions of the server and processes data. Optionally, the processor 41 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 41 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 41 and may be implemented separately by a single chip.

[0079] Among them, the memory 45 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 45 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments. Optionally, the memory 45 may further be at least one storage device located far from the aforementioned processor 41. As Figure 4 shown, the memory 45, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a method of generating content for a knowledge quiz game.

[0080] In Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an interface for the user to input and obtain the data input by the user; while the processor 41 can be used to call the application program stored in the memory 45 for a method of generating content for a knowledge quiz game, which, when executed by one or more processors, causes the electronic device to execute one or more of the methods in the above embodiments.

[0081] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0082] This application also provides a computer-readable storage medium storing instructions which, when executed by one or more processors, cause the electronic device to execute one or more of the methods described in the above embodiments.

[0083] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] In the several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, in each embodiment of this application, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0087] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0088] The foregoing are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and the practice of the disclosed truth. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for generating content of a question-and-answer game, characterized in that, The method includes: Obtaining target knowledge data corresponding to a knowledge Q&A game; Determining a semantic network according to the target knowledge data; Based on the semantic network, generating a first question by using multiple agents; Obtaining a first answer corresponding to the first question from the user; Performing feedback evolution on the first answer and outputting a second question; Obtaining the content of the knowledge Q&A game through the first question, the first answer, and the second question.

2. The method for generating knowledge Q&A game content according to claim 1, wherein The determining of the semantic network according to the target knowledge data specifically includes: Performing text splitting on the target knowledge data to obtain target knowledge cells; Determining the relationships between the target knowledge cells to obtain semantic relationships; Vectorizing the target knowledge cells to obtain a first target knowledge cell and a second target knowledge cell, where the first target knowledge cell and the second target knowledge cell are any two target knowledge cells among the multiple target knowledge cells; Calculating the cell similarity between the first target knowledge cell and the second target knowledge cell; Constructing the semantic network according to the cell similarity and the semantic relationships.

3. The method for generating the knowledge Q&A game content according to claim 1, wherein The generating of the first question by using multiple agents based on the semantic network specifically includes: Extracting a knowledge core according to the semantic network; Controlling an expert agent to generate a first draft based on a large language model according to the knowledge core; Controlling a student agent to generate a second draft based on a prompting algorithm according to the knowledge core; Performing semantic fusion on the first draft and the second draft to obtain a third draft; Adjusting the third draft through a verification agent to generate the first question, and the multiple agents include the expert agent, the student agent, and the verification agent.

4. The method for generating knowledge quiz game content according to claim 1, characterized in that The performing of feedback evolution on the first answer and outputting a second question specifically includes: Obtaining a preset answer corresponding to the first question; Using a BERT model to determine a preset answer vector corresponding to the preset answer; Using the BERT model to determine a first answer vector corresponding to the first answer; Calculating the answer similarity between the preset answer vector and the first answer vector; If it is determined that the answer similarity is greater than a preset threshold, obtaining a first keyword from the first answer; Comparing the first keyword with a preset keyword library to generate a comparison result, and the preset keyword library is constructed according to the preset answer; Determining the second question according to the comparison result.

5. The method for generating knowledge quiz game content according to claim 4, characterized in that, The determining of the second question according to the comparison result specifically includes: If it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library does not meet a preset number, determining the second question as a supplementary question based on the first question; If it is determined that the comparison result indicates that the number of identical keywords between the first keyword and the preset keyword library meets the preset number, determining the second question as an extended question based on the semantic network.

6. The method for generating knowledge Q&A game content according to claim 1, characterized in that The method further includes: Obtaining a second answer corresponding to the second question from the user; Determine the first accuracy rate corresponding to the first answer and the second accuracy rate corresponding to the second answer; If it is determined that both the first accuracy rate and the second accuracy rate are higher than a preset accuracy rate, generate a third question, and the difficulty corresponding to the third question is greater than the difficulties corresponding to the first question and the second question respectively.

7. The method for generating knowledge quiz game content according to claim 4, wherein The method further includes: Obtain training information, where the training information includes training answers and training answer vectors; Input the training information into an adaptive word vector fusion network for training to obtain a first training result; After superimposing and normalizing the first training result with the training information, obtain a second training result; Input the second training result into the adaptive word vector fusion network for processing to obtain a third training result; Superimpose and normalize the third training result with the second training result until the training information similarity matrix is output, and obtain the BERT model, where the training information similarity matrix satisfies a preset logistic regression condition.

8. A device for generating content of a question-and-answer game, characterized in that, The device includes an acquisition module (31) and a processing module (32), where The acquisition module (31) is configured to acquire target knowledge data corresponding to a knowledge quiz game; The processing module (32) is configured to determine a semantic network according to the target knowledge data; The processing module (32) is further configured to generate a first question based on the semantic network using multiple agents; The acquisition module (31) is further configured to acquire a first answer of a user for the first question; The processing module (32) is configured to perform feedback evolution on the first answer and output a second question; The processing module (32) is configured to obtain knowledge quiz game content through the first question, the first answer, and the second question.

9. An electronic device, characterized in that, The electronic device includes a processor (41), a memory (45), a user interface (43), and a network interface (44). The memory (45) is used to store instructions. Both the user interface (43) and the network interface (44) are used to communicate with other devices. The processor (41) is configured to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images