Guided learning assistance method, system and device and computer readable storage medium

Abstract

The invention relates to the field of computer data processing, in particular to a guided learning assistance method, system and device and a computer readable storage medium. The method comprises the steps of obtaining to-be-learned knowledge content corresponding to a target user, wherein the to-be-learned knowledge content comprises a plurality of knowledge elements; sequentially displaying the plurality of knowledge elements to the target user in multiple rounds, so that the target user can learn the plurality of knowledge elements; wherein the display process of each knowledge element in the plurality of knowledge elements comprises the following steps: acquiring user behavior data of a target user for the currently displayed knowledge element; analyzing the user behavior data according to a preset evaluation index corresponding to the currently displayed knowledge element to obtain an evaluation result of the currently displayed knowledge element by the target user; and adjusting the knowledge elements displayed in the next round according to the evaluation result. The method can better assist the user in learning based on the feedback of the user.

Description

Technical Field

[0001] The present application relates to the technical field of computer data processing, and in particular to a guided learning assistance method, system, device and computer-readable storage medium. Background Art

[0002] With the rapid development of science and technology, people's learning needs are growing, and the learning methods adopted by different groups of people are also constantly changing. Children are a group of people with relatively large learning needs but relatively weak learning ability and subjective initiative. How to improve the effectiveness of children's learning is an urgent problem to be solved.

[0003] In the related art, the education methods for children mainly include cramming education and didactic education. They usually follow a unified syllabus, teaching materials and evaluation standards, focus on the inculcation of knowledge and the cultivation of test-taking ability, adopt a one-size-fits-all teaching method, and are teacher-centered. Therefore, the related auxiliary learning methods for children have the problem of poor learning effects for children.

[0004] Therefore, a learning assistance solution with better learning effect is needed. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a guided learning assistance method, system, device and computer-readable storage medium, which can solve the problem of poor effectiveness of existing learning assistance solutions.

[0006] In a first aspect, an embodiment of the present application provides a learning assistance method, the guided learning assistance method comprising: Acquire knowledge content to be learned corresponding to the target user, wherein the knowledge content to be learned includes multiple knowledge elements; Multiple knowledge elements are sequentially displayed to the target user in multiple rounds, and the target user is guided to learn the multiple knowledge elements through pre-generated guidance information; wherein the guidance information includes multiple first guidance information; each of the first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element; the display process of each of the multiple knowledge elements includes: displaying the knowledge element and the first guidance information corresponding to the knowledge element; obtaining the user behavior data of the target user for the currently displayed knowledge element; analyzing the user behavior data according to the preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user for the currently displayed knowledge element; adjusting the knowledge elements and the first guidance information for the next round of display according to the evaluation result.

[0007] By adopting the above technical scheme, based on the mental characteristics of children and other people with low learning ability and subjective initiative, the knowledge content to be learned is divided into multiple knowledge elements and the multiple knowledge elements are displayed in multiple rounds, so as to facilitate users to digest and understand knowledge, avoid the learning curve being too steep, and cause users to be afraid of difficulties and lead to poor learning effects. On this basis, in the process of displaying each round of knowledge elements, the user is guided to learn the currently displayed knowledge elements through pre-generated guidance information, wherein the target user is guided to output user behavior for the knowledge element through the first guidance information, thereby prompting the user to display the learning results of the current round, improving the user's learning initiative and promoting the user to think, which can improve the user's learning effect. Finally, the user behavior data is evaluated based on the evaluation indicators corresponding to each knowledge element, and the knowledge elements and guidance information displayed in the next round are adjusted according to the evaluation results, so as to realize that each round of learning process is combined with the user's actual learning situation, so that the learning assistance method is closer to the user, has better feedback and guidance for the user, and makes the user's learning effect better.

[0008] In some embodiments, the guidance information further includes second guidance information; the second guidance information is used to guide the target user to display the overall learning results of the multiple knowledge elements after the multiple rounds of display are completed; The method further comprises: In response to an event that the display of the plurality of knowledge elements is completed, guiding the target user through the second guidance information; Acquire the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements; Analyze the overall learning results and / or learning status to obtain the target user's overall evaluation information on the knowledge content to be learned; The knowledge base corresponding to the target user is updated according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

[0009] In some embodiments, the method further comprises: Collecting the current behavior and scene information of the target user; Acquire user portrait information and a knowledge base of the target user; the knowledge base includes the target user's historical learning situation, applicable knowledge content, and at least one of the evaluation indicators; The knowledge content to be learned is determined according to the current behavior, the scene information, the user portrait information and at least one item in the knowledge base.

[0010] In some embodiments, the method further comprises: Acquiring the learning goal of the target user for the knowledge content to be learned; Performing semantic analysis on the knowledge content to be learned to obtain knowledge structure features corresponding to the knowledge content to be learned; Collecting user portrait information of the target user and current learning scenario information of the target user; The knowledge content to be learned is split and processed according to at least one of the learning objectives, the knowledge structure characteristics, and the learning scenario information to obtain the multiple knowledge elements.

[0011] In some embodiments, the method further comprises: Performing association analysis on the currently displayed knowledge element and other knowledge elements to obtain associated knowledge elements corresponding to the currently displayed knowledge element; Acquire historical learning data of the target user for the associated knowledge element; Obtaining a mastery level reference value corresponding to the currently displayed knowledge element; The historical learning data and the mastery level reference value are aggregated and analyzed to determine the evaluation index corresponding to the currently displayed knowledge element.

[0012] In some embodiments, the method further comprises: If the evaluation result does not meet the preset standard condition, generating learning guidance information corresponding to the currently displayed knowledge element; Analyze the evaluation results based on big data technology to obtain the user community to which the target user belongs; The knowledge elements to be displayed in the next round are adjusted according to the applicable knowledge content corresponding to the user community and at least one of the learning guidance information.

[0013] In some embodiments, the method further comprises: Generate a digital work according to the user behavior data, and import the digital work into a preset virtual reality scene for display; Creating a non-fungible token for the digital work and publishing the non-fungible token to a blockchain; configuring a digital model corresponding to the physical work corresponding to the target user in the virtual reality scene; Detecting interactive operations input by the target user in the virtual reality scene and the real scene; The knowledge elements to be displayed in the next round and the evaluation indicators corresponding to the knowledge elements to be displayed in the next round are adjusted according to the interactive operation.

[0014] In some embodiments, the method further comprises: Collecting the physiological state and current scene of the target user; Selecting a target virtual role from a plurality of preset optional virtual roles according to the physiological state and the current scene; the preset virtual role includes at least one of an educator role, a caregiver role, and a partner role; The target virtual character interacts with the target user; the interaction process between the target virtual character and the target user includes presenting the knowledge element to the target user.

[0015] In some embodiments, the method further comprises: Detecting a first interaction operation sent by the target user and a second interaction operation sent by an associated device and / or associated user corresponding to the target user; The target virtual character is controlled based on the first interaction operation and the second interaction operation.

[0016] In some embodiments, the method further comprises: The optional virtual characters are stored in a preset digital image database; the digital image database also stores the usage scenario information of the target user for each optional virtual character. The method further comprises: Matching the target user's current scene in the digital image database to obtain a recommended virtual character; The recommended virtual character is displayed to the target user.

[0017] In some embodiments, the method further comprises: The usage scenario information includes at least one historical login device corresponding to the selectable virtual character; The method further comprises: Detecting historical interaction data of the target user with respect to each of the selectable virtual characters; The digital image database is updated according to the historical interaction data.

[0018] In some embodiments, the method further comprises: Collecting physiological data of the target user; determining a learning status of the target user according to the physiological data; The knowledge elements to be presented in the next round are adjusted according to the learning status and the evaluation result.

[0019] In some embodiments, the method further comprises: Obtaining a control operation sent by a supervisor corresponding to the target user; The display process of the knowledge content to be learned is adjusted according to the control operation.

[0020] In a second aspect, an embodiment of the present application further provides a guided learning assistance system, the guided learning assistance system comprising: The first acquisition module is used to acquire the knowledge content to be learned corresponding to the target user; A splitting module is used to split the knowledge content to be learned to obtain multiple knowledge elements; A display module, used to display multiple knowledge elements to the target user in multiple rounds, and guide the target user to learn the multiple knowledge elements through pre-generated guidance information; wherein the guidance information includes multiple first guidance information; each of the first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element; the display process of each of the multiple knowledge elements includes: displaying the knowledge element and the first guidance information corresponding to the knowledge element; A second acquisition module is used to acquire user behavior data of the target user on the currently displayed knowledge element; A first analysis module is used to analyze the user behavior data according to a preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user on the currently displayed knowledge element; An adjustment module is used to adjust the knowledge elements and the first guidance information to be displayed in the next round according to the evaluation result.

[0021] In some embodiments, the guidance information further includes second guidance information; the second guidance information is used to guide the target user to display the overall learning results of the multiple knowledge elements after the multiple rounds of display are completed; the system further includes: a response module, configured to guide the target user through the second guidance information in response to the event that the display of the plurality of knowledge elements is completed; A third acquisition module is used to acquire the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements; A second analysis module is used to analyze the overall learning results and / or learning status to obtain the overall evaluation information of the target user on the knowledge content to be learned; An updating module is used to update the knowledge base corresponding to the target user according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

[0022] In a third aspect, an embodiment of the present application further provides a guided learning assistance device, comprising: a processor and a memory, the memory being used to store instructions, the processor being used to call the instructions in the memory, so that the guided learning assistance device executes the guided learning assistance method as described in the first aspect.

[0023] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed on a processor, the processor executes the guided learning assistance method as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The present invention is a flowchart of the steps of a guided learning assistance method provided according to an embodiment of the present application.

[0025] Figure 2 The present invention is a flowchart of a sub-step of a guided learning assistance method provided according to an embodiment of the present application.

[0026] Figure 3 The present invention is a flowchart of the steps of a guided learning assistance method provided according to another embodiment of the present application.

[0027] Figure 4 The present invention is a flowchart of the steps of a guided learning assistance method provided according to another embodiment of the present application.

[0028] Figure 5 It is a structural diagram of a guided learning assistance system provided according to an embodiment of the present application.

[0029] Figure 6 It is a schematic diagram of the structure of a guided learning auxiliary device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the implementation methods of the present application and the features in the implementation methods can be combined with each other without conflict.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present application. The described implementations are only part of the implementations of the present application, rather than all the implementations.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0033] It should be further noted that, in this article, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0034] In this application, "at least one" means one or more, and "more" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0035] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0036] In the relevant technologies, the educational theories for children's learning assistance are generally directly transferred from the existing classroom education and textbook education. However, the existing educational theories are generally teacher-led and exam-oriented, and cannot be designed according to the individual characteristics of each student. In the process of transfer and application, with the development of science and technology such as artificial intelligence technology, there is the existing use of artificial intelligence to assist users in learning, thereby replacing the role of traditional teachers with artificial intelligence and improving the efficiency of learning assistance.

[0037] However, the inventors found that in the existing AI-based learning assistance process, the AI ​​subject generally outputs knowledge unilaterally and mechanically. This indoctrination-style teaching cannot fully stimulate the learning enthusiasm and learning potential of users, especially for user groups such as children, whose learning enthusiasm and subjective initiative are relatively low.

[0038] It can be seen from the above that the existing learning assistance has the problem of poor assistance effect.

[0039] Existing personalized learning systems mainly use machine learning algorithms to analyze user answers, and provide personalized learning content recommendations by analyzing data such as correct answers and answer time, thereby achieving the purpose of improving learning efficiency. However, existing methods and technologies have the following problems, such as: The amount of knowledge is large and the graphic resources are in a single form, making it difficult to understand and learn: When there is too much content to learn and the learning resources are often presented in the form of graphics and text, it is difficult for young users or users with reading disabilities to understand and master the knowledge.

[0040] Failure to guide users to express themselves and provide immediate feedback: Young users prefer to learn through games and experiences. If only questions are provided as an exam method, it will put pressure on users and make them feel bored with learning. It will also be impossible to collect learning behavior data from user feedback, reducing the efficiency of personalized learning plans. If users cannot be given immediate feedback, they will not be able to feel their own progress, which will also reduce their interest in new things and their learning efficiency.

[0041] Directly providing answers cannot guide users to think: Directly providing answers instead of guiding users to think and understand the problem, and mechanically memorizing the answers deprives users of the opportunity to think independently and experience the sense of accomplishment that comes from solving problems through thinking, thus reducing learning efficiency.

[0042] Failure to provide appropriate scenarios and objects when users share the knowledge and skills they have learned: When users are willing to show and share what they have learned, if appropriate scenarios and sharing objects are not provided, it will dampen their desire to share and reduce their enthusiasm for learning.

[0043] In view of this, the embodiments of the present application provide a guided learning assistance method, system, device and computer-readable storage medium, which can better dynamically adjust the displayed knowledge elements based on the user's learning behavior, so as to provide users with the most suitable learning content. On the basis of achieving a personalized learning experience, the learning assistance method is adjusted based on the user's feedback behavior, which can better stimulate the user's learning enthusiasm and learning potential, and achieve better learning assistance effects.

[0044] See also Figure 1 , is a flowchart of the steps of the guided learning assistance method provided in one embodiment of the present application. This embodiment is executed based on a preset computer processing device. The computer processing device includes a mobile phone, a laptop computer, a smart wearable device, a virtual reality device, etc., which is not limited in the embodiment of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0045] See also Figure 1 As shown, the guided learning assistance method of the embodiment of the present invention may include the following steps: Step 101: Acquire knowledge content to be learned corresponding to a target user, where the knowledge content to be learned includes multiple knowledge elements.

[0046] The target user may be a user with learning needs, such as a student, a preschooler, etc. The knowledge content to be learned may be obtained based on the knowledge content acquisition request sent by the target user. Optionally, the real-time behavior and the scene in which the target user is located may also be monitored, and when the monitoring result meets the preset learning start condition, the action of acquiring the knowledge to be learned is executed. The preset learning start condition may be detecting a user asking a question or asking for help, or the appearance of a new scene, etc.

[0047] Considering that the target user can learn or need to learn a large amount of knowledge content, if the knowledge content to be learned is displayed to the target user at one time for learning, it will cause a large learning burden to the target user, and it is difficult for the target user to process and digest the knowledge content to be learned, and may even cause the user to feel afraid of difficulties and feel frustrated because of the inability to complete all learning tasks, thereby affecting the effect of learning assistance. Therefore, in this embodiment, the knowledge content to be learned is pre-divided into multiple knowledge elements, which is convenient for the target user to learn one knowledge element at a time. On the basis of reducing the learning difficulty, it is also convenient to dynamically adjust the knowledge elements provided to the target user for learning in the next round according to the target user's learning situation of the knowledge elements in the current round in the subsequent steps, so as to ensure that the knowledge elements displayed in each round are most suitable for the current level and state of the target user, and finally achieve the best learning effect for the overall knowledge content to be learned.

[0048] In order to obtain knowledge content that is more suitable for the target user's current learning, so that it can stimulate the target user's learning motivation and the target user will not reduce the learning motivation or even give up learning because the knowledge content is too difficult or too easy, step 101 may include: First, the current behavior and scene information of the target user are collected.

[0049] Among them, the current behavior includes the target user's current voice, expression, action and other data, and may also include the target user's current emotional state, physiological state, etc. The action can be the action used by the user to interact with other objects or devices, and the physiological state can be used to characterize whether the target user is currently in a positive or negative emotional state, and / or whether he is tired or unwell. The scene information includes the target user's physical environment information, the target user's logged in / used learning device information, the user's social network information, etc. The physical environment information includes the environmental parameters surrounding the target user and the user's location parameters, etc.

[0050] Secondly, the user portrait information and knowledge base of the target user are obtained; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

[0051] The user portrait information is used to describe the characteristics of the target user, which may include the target user's age, gender, educational background, personality preference, region, etc. The knowledge base may be a non-relational database, a relational database, or a knowledge graph, which includes multiple knowledge elements, the target user's historical learning status for each knowledge element, and the relationship between each knowledge element.

[0052] The historical learning situation includes the learning records and mastery of specific knowledge content by the target user. Applicable knowledge content is knowledge content available for learning, such as primary school textbook content. Evaluation indicators are used to measure the mastery level of knowledge content. Specifically, applicable knowledge content and the evaluation indicators can be predicted based on big data technology or machine learning models.

[0053] Subsequently, the knowledge content to be learned is determined based on the current behavior, the scene information, the user portrait information, and at least one item in the knowledge base.

[0054] Specifically, user intent analysis is performed based on the current behavior, and the knowledge content to be learned is determined based on the intent analysis result. For example, when the intent analysis result indicates that the target user wants to know information about fruits, the knowledge content to be learned is knowledge related to fruits. The objects that can be learned included in the scene are determined based on the scene information, and the knowledge content corresponding to the objects that can be learned is determined as the knowledge content to be learned. For example, when the scene in which the target user is located includes a dog, the knowledge content to be learned may be knowledge content about dogs. Mining is performed based on user portrait information based on big data technology or artificial intelligence to obtain knowledge content to be learned that is suitable for the target user. Based on the historical learning situation and evaluation indicators in the knowledge base, the current knowledge level of the target user is determined, and the knowledge content to be learned is selected from the applicable knowledge content based on the knowledge level.

[0055] It can be understood that when the knowledge content to be learned is determined based on the current behavior, scene information, user portrait information and multiple items in the knowledge base, corresponding selection weights can be set for the current behavior, scene information, user portrait information and knowledge base, respectively, and the knowledge content selected by the current behavior, scene information, user portrait information and knowledge base respectively is voted according to the selection weights to obtain the knowledge content to be learned.

[0056] In some embodiments, in order to make the split of learning knowledge content more reasonable and more in line with the learning curve and learning goals of the target user, so that a single knowledge element is not too difficult or too easy for the target user, thereby affecting the user's learning experience and effect, step 101 also includes: First, the learning goal of the target user for the knowledge content to be learned is obtained.

[0057] The learning goal is used to represent the degree to which the target user should recognize and master the knowledge content to be learned under ideal conditions. For example, when the knowledge content to be learned is elementary school algebra, the learning goal can be to calculate the addition, subtraction, multiplication and division of two-digit numbers proficiently and correctly.

[0058] Subsequently, semantic analysis is performed on the knowledge content to be learned to obtain knowledge structure features corresponding to the knowledge content to be learned.

[0059] Specifically, semantic analysis is used to analyze the semantic information and grammatical structure of the knowledge content to be learned based on natural language processing technology, and the knowledge structure features are used to characterize the multiple knowledge elements included in the knowledge content to be learned and the association relationship between the multiple knowledge elements. For example, for the knowledge content to be learned, such as elementary school algebra, the knowledge structure features include the identification of numbers, the identification of operation symbols, and the application relationship between numbers and operation symbols.

[0060] Furthermore, the user portrait information of the target user and the current learning scenario information of the target user are collected.

[0061] Specifically, the user portrait information can be obtained by searching and analyzing the target user's identification information and historical interaction data, and the user's current learning scene information can be obtained by detecting through a preset sensor device.

[0062] Finally, the knowledge content to be learned is split according to at least one of the learning objectives, the knowledge structure characteristics, and the learning scenario information to obtain the multiple knowledge elements.

[0063] Specifically, a learning plan corresponding to a target user is determined according to the learning goal. The learning plan includes multiple learning stages. The knowledge content to be learned is divided according to the multiple learning stages to facilitate users to complete the learning goals step by step.

[0064] The knowledge content to be learned is divided into multiple related knowledge elements according to the knowledge structure characteristics, wherein the correlation can be expressed as the inclusion relationship, causal relationship, progressive relationship of difficulty, etc. of the knowledge content. Optionally, the knowledge content to be learned can also be divided into knowledge elements according to the user portrait characteristics of the user. Among them, the user portrait characteristics can include personal characteristics and environmental characteristics for division. Personal characteristics can include: curiosity and desire for exploration, sensory stimulation, emotional drive and cognitive development stage, etc. Environmental characteristics can include: the influence of family education and environment, social communication and imitation learning, etc.

[0065] According to the current learning scenario information, the knowledge elements that are most relevant to the current scenario and have the highest learning efficiency in the current scenario are selected as the currently displayed knowledge elements, and the other contents in the knowledge content to be learned are used as the remaining knowledge elements, so as to facilitate real-time adjustments based on the learning situation of the target users.

[0066] Step 102: Present multiple knowledge elements to the target user in sequence in multiple rounds, and guide the target user to learn the multiple knowledge elements through pre-generated guidance information.

[0067] In order to refine the granularity of learning assistance for users and facilitate more refined and flexible learning assistance and adjustment of learning assistance plans for users, the guidance information includes multiple first guidance information, wherein each first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element. While displaying the knowledge elements, the target user is guided to output his learning results through the first guidance information, thereby prompting the target user to display the learning results of the current round, enhancing the learning initiative of the target user and promoting the user to think, which can improve the learning effect of the target user.

[0068] Specifically, the display process of each of the multiple knowledge elements includes: First, the knowledge element and the first guidance information corresponding to the knowledge element are displayed. Specifically, the knowledge element and the first guidance information can be displayed synchronously, or the first guidance information can be displayed based on a preset trigger condition after the knowledge element is displayed. Among them, the preset trigger condition can detect the instruction input by the user indicating that the learning of the knowledge element of the current round is completed, or detect that the display time of the knowledge element of the current round is greater than the preset time threshold. Among them, one knowledge element can be displayed in one round for the target user to learn. While displaying the knowledge element, the guidance information can also be generated according to the knowledge element using reasoning topologies such as thinking chains and thinking trees, such as indicating the sequential process of user learning or the learning method process and places that need attention, etc., thereby improving the learning efficiency of the target user.

[0069] Subsequently, the user behavior data of the target user on the currently displayed knowledge element is obtained. Specifically, the user behavior data may include learning notes, test results, and feedback information input by the user. Then, the user behavior data is analyzed according to the preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user on the currently displayed knowledge element. Among them, the evaluation result is used to characterize the target user's mastery of the currently displayed knowledge element and the good degree of learning experience. The good degree of learning experience can be obtained by analyzing and statistics based on the proportion of negative information in the feedback information of the target user, the error rate in the test results, etc. Finally, the knowledge elements displayed in the next round and the first guidance information are adjusted according to the evaluation result. Among them, the adjustment strategy for the knowledge elements displayed in the next round includes making the learning difficulty of the knowledge elements displayed in the next round not too large or too small for the target user, thereby stimulating and maintaining the learning enthusiasm of the target user, helping the target user to maintain continuous learning behavior, and thus forming good learning habits. Correspondingly, the adjustment strategy for the first guidance information can determine the target user's preferred learning method and cognitive level in combination with the evaluation result, and adjust the first guidance information according to the preferred learning method and cognitive level, so that it can better guide and promote the target user to learn.

[0070] Specifically, in order to enhance the learning enthusiasm of target users and create a relaxed and friendly learning atmosphere, thereby improving the learning experience and learning motivation of users, in some embodiments, the display process of knowledge elements may include: First, the physiological state and current scene of the target user are collected.

[0071] The physiological state of the target user may include the physiological parameter values ​​of the target user, and the physiological state may represent the user's stress, emotions, fatigue level and other parameters that affect the user's efficient and normal learning. The scene information includes the physical environment information of the target user, the learning device information logged in / used by the target user, the social network information of the user, etc. The physical environment information includes the environmental parameters surrounding the target user and the user's location parameters, etc.

[0072] Then, a target virtual role is selected from a plurality of preset optional virtual roles according to the physiological state and the current scene; the preset virtual role includes at least one of an educator role, a caregiver role and a partner role.

[0073] Among them, the target user's current companionship need type is determined according to the physiological state and the current scene, such as answering questions, educating, supervising, playing, comforting, caring, etc. According to the companionship need type and the functional type corresponding to each optional virtual character, the target virtual character is selected from multiple preset optional virtual characters.

[0074] The educator role may include roles such as parents and teachers, the caregiver role may include roles such as parents, relatives, and older friends, and the partner role may include roles such as classmates, friends, siblings, and pets.

[0075] In this embodiment, the image of a virtual character with specific characteristics, behaviors or attributes is created through computer technology and specific algorithms. The virtual character can provide emotional support and companionship, accompany the user to grow gradually, and have more skills and knowledge. Through the real-time changes or feedback of the virtual character, the user also feels his own growth and shortcomings, which can provide users with a more immersive and humanized learning experience. Specifically, in the process of interaction with the target user, the digital avatar and digital twin technology are used to generate a virtual character. The virtual character can automatically run according to preset conditions in the virtual world, explore different places, and interact with different characters to help the target user learn knowledge, cultivate a sense of responsibility and social skills.

[0076] In order to maintain the consistency of the virtual characters in the virtual reality environment and create a cross-environment, all-round sense of companionship and reality for the target user, the optional virtual characters are stored in a preset digital image database; the digital image database also stores the target user's usage scenario information for each optional virtual character. The usage scenario information includes at least one historical login device corresponding to the optional virtual character.

[0077] In some embodiments, in order to enhance the learning interest of the target user, the guided learning assistance method further includes: First, a match is performed in the digital image database according to the current scene of the target user to obtain a recommended virtual character.

[0078] The current scene is matched with the applicable scenes corresponding to each optional virtual character in the digital image database, and the optional virtual character that best suits the current scene is selected as the recommended virtual character according to the matching result. For example, when the current scene of the target user is sitting at a desk doing homework, the recommended virtual character can be an educator, so as to answer questions for the target user and supervise him to complete his homework and concentrate on learning.

[0079] Thereby, the recommended virtual character is displayed to the target user.

[0080] Optionally, a digital avatar of the target user can be created in a virtual reality environment based on the target user's behavior and image. The target user can control the digital avatar to complete tasks that he or she cannot complete in the real world in the virtual reality environment, and can understand its movements at any time and interact with it. This not only provides users with more experimental opportunities, but also reduces their trial and error costs and improves their social abilities.

[0081] In some embodiments, the method of guided learning assistance further includes: First, the historical interaction data of the target user with respect to each of the selectable virtual characters is detected.

[0082] Considering that the scenarios in which the target users are located and their learning motivations may be varied, the target users' interaction frequencies and preferences for each optional virtual character may also differ. In order to better develop the functions of the virtual characters based on such differences, the target users' historical interaction data for each of the optional virtual characters are detected.

[0083] Subsequently, the digital image database is updated according to the historical interaction data.

[0084] Specifically, the selectable virtual characters and the historical interaction data corresponding to the selectable virtual data are associated and stored in the digital image database.

[0085] Finally, the target virtual character interacts with the target user; the interaction process between the target virtual character and the target user includes displaying the knowledge element to the target user.

[0086] By interacting with the target users through the target virtual characters, the target users are helped to complete learning tasks, and knowledge elements are displayed to the target users through the target virtual characters, avoiding the cold and mechanical knowledge display method, enhancing the learning interest of the target users, and better assisting users in learning to achieve better learning effects.

[0087] Specifically, the process of interacting with the target user through the target virtual character may include: First, a first interaction operation sent by the target user and a second interaction operation sent by an associated device and / or associated user corresponding to the target user are detected.

[0088] The associated device may be a device used by the target user or a device used by an associated user of the target user, and the associated user may be a user who pays attention to and / or influences the learning behavior of the target user, such as the target user's teacher, relative, classmate, friend, etc. On the basis of the target user interacting with the target virtual character to combine education with entertainment and promote the target user's learning, considering the characteristics of children's easy imitation and following, the second interactive operation of the associated user of the target user is introduced to create a sense of companionship and supervision for the target user, which can better mobilize the target user's enthusiasm for learning and stimulate better learning effects and learning experience.

[0089] Then, the target virtual character is controlled based on the first interaction operation and the second interaction operation.

[0090] Specifically, the first interactive operation and the second interactive operation may be voted on according to the control weights corresponding to the associated user and the target user, respectively, and the target virtual character may be controlled according to the interactive operation selected by the vote.

[0091] Optionally, the target virtual character can be controlled according to the first interactive operation, and the companion virtual character can be controlled according to the second interactive operation, and the companion virtual character can be controlled according to the second interactive operation to interact with the target virtual character in the virtual reality environment, thereby simulating the interaction between the target user and the associated user in reality.

[0092] Among them, Figure 2 As shown, the display process of each knowledge element in the multiple knowledge elements includes: Step 1021: Display the knowledge element and the first guidance information corresponding to the knowledge element.

[0093] Among them, the first guidance information is used to guide the user to output learning behaviors for the currently displayed knowledge elements, such as taking notes, answering questions, and providing feedback.

[0094] Step 1022: Obtain user behavior data of the target user on the currently displayed knowledge element.

[0095] Among them, user behavior data may include the behavior data of the target user after the current round of knowledge elements are presented, such as actions, voices, expressions, etc., such as writing text, drawing, repeating, asking and answering, following, etc., and may also be data on changes in physiological states that are invisible to the naked eye.

[0096] Step 1023: Analyze the user behavior data according to the preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user on the currently displayed knowledge element.

[0097] Among them, the evaluation index is used to characterize the behavior and status that users should exhibit when they have mastered the knowledge elements to a qualified level. Different knowledge elements correspond to different evaluation indicators, so as to evaluate the learning progress of target users in a more fine-grained manner and provide a basis for real-time adjustment of learning assistance plans.

[0098] Step 1024: adjusting the knowledge elements to be displayed in the next round and the first guidance information according to the evaluation result.

[0099] Among them, according to the target user's mastery of the currently displayed knowledge elements represented by the evaluation results, the difficulty of the knowledge elements displayed in the next round is adjusted, that is, the knowledge elements that best suit the target user's cognitive level and knowledge storage are displayed for their next round of learning. While avoiding the target user from feeling bored and repetitive, it also avoids setting the learning curve too steep, causing the target user to give up and reduce enthusiasm, affecting the learning effect.

[0100] In some embodiments, the process of adjusting the knowledge elements and the first guidance information displayed in the next round further includes: If the evaluation result does not meet the preset standard condition, the learning guidance information corresponding to the currently displayed knowledge element is generated.

[0101] Among them, the learning guidance information can be information on learning methods and learning skills for users to learn the currently displayed knowledge elements. Optionally, the currently displayed knowledge elements can be further divided into sub-elements that are easier to understand and learn, and the sub-elements and the learning methods of the sub-elements are displayed to the target users. It should be noted that in order to avoid the drawbacks of the existing cramming education, the learning guidance information in this embodiment generally does not include the complete answers or problem-solving examples corresponding to the currently displayed knowledge elements, thereby leaving room for thinking and progress for the target users, which is more conducive to the growth and potential mining of the target users.

[0102] And, the evaluation results are analyzed based on big data technology to obtain the user community to which the target user belongs.

[0103] Specifically, the user community to which the target user belongs includes other users who are at the same knowledge level and learning ability as the target user. By analyzing the learning process of a large number of users through big data technology, user communities corresponding to different learning abilities and knowledge levels are obtained, and then the target user's knowledge level and learning ability are determined based on the target user's corresponding evaluation results, and the user community to which the target user belongs is determined based on the target user's knowledge level and learning ability.

[0104] Finally, the knowledge elements to be displayed in the next round are adjusted according to the applicable knowledge content corresponding to the user community and at least one of the learning guidance information.

[0105] Determine the applicable knowledge content corresponding to the user community and at least one of the learning guidance information based on big data technology. Specifically, the applicable knowledge content corresponding to the user community can be disassembled to obtain the knowledge elements to be displayed in the next round. Or the learning guidance information can be disassembled to obtain the knowledge elements to be displayed in the next round.

[0106] In some embodiments, the knowledge element adjustment process further includes: First, the physiological data of the target user is collected.

[0107] Among them, physiological data includes various physiological index data of the target user. Considering that the learning process of the target user needs to be based on the user's physiological response and support, the physiological data of the target user can be collected in real time when the knowledge elements are adjusted round by round. Specifically, the physiological data is collected through the device worn by the target user, such as a smart watch.

[0108] Then, the learning status of the target user is determined according to the physiological data.

[0109] At least one of the health status, emotional state, fatigue level, and stress level of the target user is determined based on the physiological data of the target user. The learning state of the target user is determined based on at least one of the health status, emotional state, fatigue level, and stress level. Among them, the health status is used to characterize whether the target user is currently sick or feeling unwell. It is understandable that the lower the health value of the target user, the worse the learning state. The emotional state can characterize that the target user is currently in a positive emotion, a neutral emotion, or a negative emotion, wherein when the target user is in a negative emotion, his learning state is not good, and the closer the target user's emotion is to a positive emotion, the better his learning state. Similarly, when the target user is in a state of fatigue or high pressure, it is obviously not suitable for learning, so it is determined that the learning state of the target user is not good at this time.

[0110] Finally, the knowledge elements to be displayed in the next round are adjusted according to the learning status and the evaluation results.

[0111] Specifically, the difficulty of the knowledge elements to be displayed in the next round is adjusted according to the quality of the learning status and the quality of the evaluation results. For example, when at least one of the learning status and the evaluation results is excellent, the knowledge elements with greater difficulty can be displayed in the next round. Correspondingly, when at least one of the learning status and the evaluation results is poor, the knowledge elements with easier difficulty can be displayed in the next round. Alternatively, the display of knowledge elements is suspended and the target user is prompted to rest, relax, or seek medical treatment. While assisting the user's learning, it reflects the humanistic care for the target user, which is more conducive to gaining the trust of the target user and eliminating their bad experience.

[0112] Specifically, the process of determining the preset evaluation index corresponding to the currently displayed knowledge element includes: First, the currently displayed knowledge element is subjected to association analysis with other knowledge elements to obtain associated knowledge elements corresponding to the currently displayed knowledge element.

[0113] Specifically, the learning difficulty of the target user for the currently displayed knowledge element is affected by the target user's mastery level of the associated knowledge elements. The learning process of a large number of other users for multiple knowledge elements can be analyzed based on big data technology to obtain the associated knowledge elements that affect the learning difficulty of the currently displayed knowledge element. For example, if the currently displayed knowledge element can be two-digit multiplication, its associated knowledge elements can include one-digit multiplication, two-digit addition, two-digit subtraction, two-digit division, etc.

[0114] Then, historical learning data of the target user for the associated knowledge element is obtained.

[0115] The historical learning data may include the target user's historical learning process and learning results of the associated knowledge elements.

[0116] Then, a mastery level reference value corresponding to the currently displayed knowledge element is obtained.

[0117] Specifically, big data technology can be used to obtain the average mastery of the currently displayed knowledge elements by the user group to which the target user belongs, and obtain a reference value of the mastery level.

[0118] Finally, the historical learning data and the mastery level reference value are aggregated and analyzed to determine the evaluation index corresponding to the currently displayed knowledge element.

[0119] Among them, the target user's historical learning data is combined to predict his or her mastery of the currently displayed knowledge elements, and the evaluation index is adjusted based on the mastery level reference value according to the mastery level to obtain the evaluation index. Therefore, the evaluation result based on the evaluation index can better reflect the target user's real level and provide guidance for assisting the target user's learning.

[0120] In some embodiments, after obtaining the user behavior data of the target user on the currently displayed knowledge element, the adjustment process for the evaluation index may further include: First, a digital work is generated according to the user behavior data, and the digital work is imported into a preset virtual reality scene for display; a digital model corresponding to the physical work corresponding to the target user is configured in the virtual reality scene.

[0121] Among them, considering that traditional learning generally takes place in the classroom based on textbooks, its learning methods and locations are relatively fixed and single, and it is difficult to stimulate the learning enthusiasm of target users, in this embodiment, user behavior data is integrated into the virtual reality environment in the form of data works, and by collecting the data of the physical products corresponding to the target users in the real environment, a digital model corresponding to the physical product is generated, and the digital model is imported into the virtual scene, so that the user's learning experience in the two dimensions of reality and virtuality can be seamlessly connected, providing an immersive experience for the target users. On this basis, learning in the virtual reality environment can also use more interactive technologies to better enrich the learning experience of the target users and increase the fun of learning.

[0122] The physical product corresponding to the user may be a physical prop item made according to the digital work, or a physical product used by the user, such as a toy, furniture, stationery, etc. It should be noted that the physical product in this embodiment is not limited to commodities, but may also be living things such as plants and animals in the user's environment, such as the target user's pet, etc. By virtualizing the partner or item used by the target user in the real environment into the virtual reality environment, a more simulated and familiar learning environment is provided for the target user, which helps the target user to learn in a more relaxed and preferred way.

[0123] Optionally, a unique identifier (such as a hash value) can be generated for the digital work, and the digital work can be minted into a non-homogeneous token through a smart contract and published on the blockchain network to achieve sharing and traceability of the learning process of the target user. Optionally, considering the compliance and usability of the generated digital work, the digital work can also be reviewed by a preset regulator. The digital work can only be published after the regulator has reviewed and approved it.

[0124] And, detecting an interactive operation input by the target user in the virtual reality scene.

[0125] Among them, the interactive operation can be a control operation performed by the target user on an object in the virtual reality scene, such as opening a book displayed in the virtual reality scene, playing and talking with a virtual pet displayed in the virtual reality scene, etc.

[0126] Finally, the knowledge elements to be displayed in the next round and the evaluation indicators corresponding to the knowledge elements to be displayed in the next round are adjusted according to the interactive operation.

[0127] The interactive operations are analyzed according to the preset behavioral analysis dimensions to extract the learning behaviors of the target users in the virtual reality scene, where the learning behaviors include the behaviors of users learning knowledge and the behaviors of users outputting their learning results. The evaluation indicators are adjusted according to the learning behaviors of users in the virtual reality environment, so that the learning process of the target users in the real environment is integrated with the virtual reality environment, providing more comprehensive and effective assistance for the learning of the target users.

[0128] See also Figure 3 , is a flowchart of the steps of the guided learning assistance method provided by another embodiment of the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. Figure 3 As shown, the guided learning assistance method may include the following steps: Step 201: Acquire knowledge content to be learned corresponding to a target user, where the knowledge content to be learned includes multiple knowledge elements.

[0129] Step 201 of the embodiment of the present application is similar to step 101 of the aforementioned embodiment, and will not be described again here to avoid repetition.

[0130] Step 202: Display multiple knowledge elements to the target user in multiple rounds in sequence, so that the target user can learn the multiple knowledge elements; wherein the display process of each of the multiple knowledge elements includes: obtaining user behavior data of the target user for the currently displayed knowledge element; analyzing the user behavior data according to preset evaluation indicators corresponding to the currently displayed knowledge element to obtain the evaluation results of the target user for the currently displayed knowledge element; and adjusting the knowledge elements to be displayed in the next round according to the evaluation results.

[0131] Step 202 of the embodiment of the present application is similar to step 102 of the aforementioned embodiment, and will not be described again here to avoid repetition.

[0132] Step 203: In response to the event that the display of the plurality of knowledge elements is completed, guiding the target user through second guidance information.

[0133] The second guiding information is used to guide the target user to present the overall learning results of the multiple knowledge elements after the multiple rounds of presentation are completed.

[0134] Based on the personalized adjustment of the knowledge elements displayed in each round according to user behavior to make it more suitable for the target users, after all the knowledge elements are displayed, considering that the target users should have a holistic and more comprehensive grasp of the knowledge content to be learned at this time, the second guidance information is used to guide the target users to provide feedback on the overall learning results of the knowledge content to be learned. For example, the guidance information can be a question to the target user, guiding the user to recombine and process the decomposed knowledge elements, and use deductive reasoning, inductive summary and analogical reasoning to show the learning process and results. When the user is ready to show and share, a safe and familiar scene is built for him, and through sharing sessions, community discussions, role-playing games, experimental practices, etc., the user can express more of the knowledge and skills he has learned. Optionally, artificial intelligence digital human technology can also be used to generate interactive virtual objects to provide a rich, vivid and intuitive multimodal interactive experience.

[0135] Step 204: Obtain the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements.

[0136] Specifically, the target user's feedback information may be detected within a preset time period after the guidance information is displayed to the target user, and the learning result display information may be extracted from the feedback information.

[0137] Furthermore, considering that the target user may not actively output feedback information based on the guidance information for some reasons, that is, the initiative and probability of the target user to display the learning results are uncertain, therefore, in order to avoid the lack of data to evaluate the user's overall learning outcomes, it is also possible to actively obtain the target user's learning status for each round of knowledge elements displayed in the previous steps, summarize and analyze the historical learning status, and obtain a predictive analysis of the target user's overall mastery of the knowledge content to be learned.

[0138] Step 205: Analyze the overall learning achievement and / or learning situation to obtain the target user's overall evaluation information on the knowledge content to be learned.

[0139] Specifically, the learning result display information and / or learning status can be analyzed according to preset evaluation dimensions to obtain overall evaluation information, wherein the evaluation dimensions may include, for example, the displayed learning results and / or the accuracy, fluency, stability, etc. of the learning process for all knowledge elements.

[0140] Step 206: updating the knowledge base corresponding to the target user according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

[0141] In order to make the subsequent auxiliary learning for the target user more suitable for the target user's situation, the knowledge base corresponding to the target user is updated according to the total evaluation information. Specifically, the total evaluation information can be recorded in the historical learning situation, and the scope of applicable knowledge content can be adjusted according to the total evaluation information. For example, when the user's total evaluation information indicates that the target user has reached the preset knowledge level, new and more difficult knowledge content is added to the applicable knowledge content. Correspondingly, when the total evaluation information indicates that the target user's knowledge level is low, the adaptability of the evaluation index can be reduced to avoid the target user from having negative emotions such as frustration and giving up, which affects his enthusiasm for learning.

[0142] See also Figure 4 , is a flowchart of the steps of the guided learning assistance method provided by another embodiment of the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. Figure 4 As shown, the guided learning assistance method may include the following steps: Step 301: Acquire knowledge content to be learned corresponding to a target user, where the knowledge content to be learned includes multiple knowledge elements.

[0143] Step 301 of the embodiment of the present application is similar to step 101 of the aforementioned embodiment, and will not be described again here to avoid repetition.

[0144] Step 302: Display multiple knowledge elements to the target user in multiple rounds in sequence, so that the target user can learn the multiple knowledge elements; wherein the display process of each of the multiple knowledge elements includes: obtaining user behavior data of the target user for the currently displayed knowledge element; analyzing the user behavior data according to preset evaluation indicators corresponding to the currently displayed knowledge element to obtain the evaluation results of the target user for the currently displayed knowledge element; and adjusting the knowledge elements to be displayed in the next round according to the evaluation results.

[0145] Step 302 of the embodiment of the present application is similar to step 102 of the aforementioned embodiment, and will not be described again here to avoid repetition.

[0146] Step 303: Obtain the control operation sent by the supervisor corresponding to the target user.

[0147] In order to make the learning assistance for the target user more personalized and to promote the learning of the target user more effectively, the supervisor can be the target user's parents, teachers, relatives and other close people. The control operation can be used to control the knowledge content to be learned, the evaluation index, the knowledge elements to be displayed, etc.

[0148] Step 304: adjusting the display process of the knowledge content to be learned according to the control operation.

[0149] Specifically, the knowledge content to be learned is adjusted according to the control operation, the knowledge elements displayed in each round are adjusted, the evaluation indicators corresponding to each knowledge element are adjusted, etc.

[0150] The role and authority of the supervisor in learning assistance are illustrated by example: Setting goals and expectations through control operations: clarifying the learning goals that you want to achieve within a specific time period, such as mastering a certain life skill or improving language expression ability. Feedback on the characteristics of the target user through control indicators: such as providing information about the target user's learning style, interests, hobbies, personality characteristics, etc., so that the guided learning assistance method of this embodiment can adjust the tutoring method more personally. Propose requirements and suggestions through control operations: If it is found that the target user encounters difficulties in some aspects or the tutoring effect is not ideal, parents and other supervisors can put forward their own ideas, such as adding more examples to explain, adjusting the difficulty of exercises, etc. The supervisor monitors the progress and effect: regularly check the learning report generated according to the learning tutoring method of this embodiment to understand the learning progress and mastery of the target user, and judge whether the tutoring method needs to be improved. Adjust the learning time and rhythm through control operations: according to the state and daily schedule of the target user, control the learning time and rest interval of multiple rounds of knowledge elements to avoid excessive fatigue or excessive stress of the target user. Select learning content through control operations: From the applicable knowledge content learning resources in the knowledge base, select suitable learning resources for target users based on their actual level and needs, and participate in the formulation of recommendation algorithms and rules.

[0151] The guided learning assistance method provided in the embodiment of the present invention, by combining artificial intelligence technology, provides users with personalized learning resources, and guides users to express, display and share the knowledge and skills they have learned, thereby building a loop for users to provide resource input and guide and urge users to effectively output data, thereby achieving the purpose of improving learning efficiency.

[0152] The guided learning assistance method provided by the embodiment of the present invention splits the knowledge points into several small multimodal guided knowledge elements, and presents them to users in the form of dialogue, games, role-playing, etc., and uses reasoning topologies such as thinking chains and thinking trees to generate guidance information suitable for users, so as to guide users to express and share the knowledge they have learned in the form of language, text, drawings, expressions, and actions, so as to help users gradually understand and solve complex problems; at the same time, guide users to recombine and organize the disassembled knowledge elements, and use deductive reasoning, inductive summary and analogical reasoning methods to show their process and results, so that users can think deeply about the internal connections, attributes and laws of knowledge, and form their own knowledge system and thinking framework, so as to learn more efficiently; when users are ready to share, a safe and familiar scene is built for them, and virtual objects for sharing and interaction are generated using technologies such as artificial intelligence digital humans, so that users can more conveniently express and display the knowledge and skills they have learned through community discussions and sharing.

[0153] Please refer to Figure 5 , is a schematic diagram of the hardware structure of the guided learning assistance system 400 provided in the embodiment of the present application. Figure 5 As shown, the guided learning assistance system 400 may include: The first acquisition module 4001 is used to acquire the knowledge content to be learned corresponding to the target user; A splitting module 4002 is used to split the knowledge content to be learned to obtain multiple knowledge elements; The display module 4003 is used to display multiple knowledge elements to the target user in multiple rounds, and guide the target user to learn the multiple knowledge elements through pre-generated guidance information; wherein the guidance information includes multiple first guidance information; each of the first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element; the display process of each of the multiple knowledge elements includes: displaying the knowledge element and the first guidance information corresponding to the knowledge element; The second acquisition module 4004 is used to acquire the user behavior data of the target user on the currently displayed knowledge element; The first analysis module 4005 is used to analyze the user behavior data according to the preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user on the currently displayed knowledge element; The adjustment module 4006 is used to adjust the knowledge elements and the first guidance information to be displayed in the next round according to the evaluation result.

[0154] In another embodiment, the guidance information further includes second guidance information; the second guidance information is used to guide the target user to display the overall learning results of the multiple knowledge elements after the multiple rounds of display are completed. The guided learning assistance system 400 may also include: a response module, configured to guide the target user through the second guidance information in response to the event that the display of the plurality of knowledge elements is completed; A third acquisition module is used to acquire the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements; A second analysis module is used to analyze the overall learning results and / or learning status to obtain the overall evaluation information of the target user on the knowledge content to be learned; An updating module is used to update the knowledge base corresponding to the target user according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

[0155] Please refer to Figure 6 , is a schematic diagram of the hardware structure of the guided learning auxiliary device 500 provided in the embodiment of the present application. Figure 6 As shown, the guided learning assistance device 500 may include a processor 5001 and a memory 5002. The memory 5002 is used to store one or more computer programs 5003. The one or more computer programs 5003 are configured to be executed by the processor 5001. The one or more computer programs 5003 include instructions, and the above instructions can be used to implement the above-mentioned guided learning assistance method in the guided learning assistance device 500.

[0156] It is understandable that the structure shown in this embodiment does not constitute a specific limitation on the guided learning auxiliary device 500. In other embodiments, the guided learning auxiliary device 500 may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently.

[0157] The processor 5001 may include one or more processing units, for example, the processor 5001 may include an application processor (AP), a modem, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0158] The processor 5001 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 5001 is a cache memory. The memory may store instructions or data that the processor 5001 has just used or circulated. If the processor 5001 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 5001, and thus improves the efficiency of the system.

[0159] In some embodiments, the processor 5001 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.

[0160] In some embodiments, the processor 5001 is used to execute acceleration schemes such as single instruction multiple data (SIMD) and very long instruction word (VLIW).

[0161] In some embodiments, memory 5002 may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0162] This embodiment also provides a computer-readable storage medium, which stores computer instructions. When the instructions are executed on a processor, the flight equipment executes the above-mentioned related method steps to implement the guided learning assistance method in the above-mentioned embodiment.

[0163] Among them, the guided learning auxiliary device and computer-readable storage medium provided in this embodiment are used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0164] In practical applications, the above functions can be distributed to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0165] In several embodiments provided in the present application, the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are schematic. For example, the division of the modules or units is a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0166] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0167] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0168] If the 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 readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially 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, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0169] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A guided learning assistance method, characterized in that: The guided learning assistance method comprises: Acquire knowledge content to be learned corresponding to the target user, wherein the knowledge content to be learned includes multiple knowledge elements; Multiple knowledge elements are sequentially displayed to the target user in multiple rounds, and the target user is guided to learn the multiple knowledge elements through pre-generated guidance information; wherein the guidance information includes multiple first guidance information; each of the first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element; the display process of each of the multiple knowledge elements includes: displaying the knowledge element and the first guidance information corresponding to the knowledge element; obtaining the user behavior data of the target user for the currently displayed knowledge element; analyzing the user behavior data according to the preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user for the currently displayed knowledge element; adjusting the knowledge elements and the first guidance information for the next round of display according to the evaluation result.

2. The method according to claim 1, characterized in that The guidance information further includes second guidance information; the second guidance information is used to guide the target user to display the overall learning results of the multiple knowledge elements after the multiple rounds of display are completed; After presenting the plurality of knowledge elements to the target user in multiple rounds so that the target user can learn the plurality of knowledge elements, the method further includes: In response to an event that the display of the plurality of knowledge elements is completed, guiding the target user through the second guidance information; Acquire the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements; Analyze the overall learning results and / or learning status to obtain the target user's overall evaluation information on the knowledge content to be learned; The knowledge base corresponding to the target user is updated according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

3. The method according to claim 1, characterized in that The step of obtaining the knowledge content to be learned corresponding to the target user includes: Collecting the current behavior and scene information of the target user; Acquire user portrait information and a knowledge base of the target user; the knowledge base includes the target user's historical learning situation, applicable knowledge content, and at least one of the evaluation indicators; The knowledge content to be learned is determined according to the current behavior, the scene information, the user portrait information and at least one item in the knowledge base.

4. The method according to claim 1, characterized in that: The method further comprises: Acquiring the learning goal of the target user for the knowledge content to be learned; Performing semantic analysis on the knowledge content to be learned to obtain knowledge structure features corresponding to the knowledge content to be learned; Collecting user portrait information of the target user and current learning scenario information of the target user; The knowledge content to be learned is split and processed according to at least one of the learning objectives, the knowledge structure characteristics, and the learning scenario information to obtain the multiple knowledge elements.

5. The method according to claim 1, characterized in that The process of determining the preset evaluation index corresponding to the currently displayed knowledge element includes: Performing association analysis on the currently displayed knowledge element and other knowledge elements to obtain associated knowledge elements corresponding to the currently displayed knowledge element; Acquire historical learning data of the target user for the associated knowledge element; Obtaining a mastery level reference value corresponding to the currently displayed knowledge element; The historical learning data and the mastery level reference value are aggregated and analyzed to determine the evaluation index corresponding to the currently displayed knowledge element.

6. The method according to claim 1, characterized in that The adjusting the knowledge elements to be displayed in the next round according to the evaluation result includes: If the evaluation result does not meet the preset standard condition, generating learning guidance information corresponding to the currently displayed knowledge element; Analyze the evaluation results based on big data technology to obtain the user community to which the target user belongs; The knowledge elements to be displayed in the next round are adjusted according to the applicable knowledge content corresponding to the user community and at least one of the learning guidance information.

7. The method according to claim 1, characterized in that After obtaining the user behavior data of the target user on the currently displayed knowledge element, the method further includes: Generate a digital work according to the user behavior data, and import the digital work into a preset virtual reality scene for display; Creating a non-fungible token for the digital work and publishing the non-fungible token to a blockchain; configuring a digital model corresponding to the physical work corresponding to the target user in the virtual reality scene; Detecting interactive operations input by the target user in the virtual reality scene and the real scene; The knowledge elements to be displayed in the next round and the evaluation indicators corresponding to the knowledge elements to be displayed in the next round are adjusted according to the interactive operation.

8. The method according to claim 1, characterized in that The presenting the plurality of knowledge elements to the target user in sequence in a plurality of rounds so that the target user can learn the plurality of knowledge elements includes: Collecting the physiological state and current scene of the target user; Selecting a target virtual role from a plurality of preset optional virtual roles according to the physiological state and the current scene; the preset virtual role includes at least one of an educator role, a caregiver role, and a partner role; The target virtual character interacts with the target user; the interaction process between the target virtual character and the target user includes presenting the knowledge element to the target user.

9. The method according to claim 8, characterized in that The interacting with the target user through the target virtual character includes: Detecting a first interaction operation sent by the target user and a second interaction operation sent by an associated device and / or associated user corresponding to the target user; The target virtual character is controlled based on the first interaction operation and the second interaction operation.

10. The method according to claim 8, characterized in that The optional virtual characters are stored in a preset digital image database; The digital image database also stores the usage scenario information of the target user for each of the optional virtual characters. The method further comprises: Matching the target user's current scene in the digital image database to obtain a recommended virtual character; The recommended virtual character is displayed to the target user.

11. The method according to claim 10, characterized in that The usage scenario information includes at least one historical login device corresponding to the selectable virtual character; The method further comprises: Detecting historical interaction data of the target user with respect to each of the selectable virtual characters; The digital image database is updated according to the historical interaction data.

12. The method according to claim 1, characterized in that The method further comprises: Collecting physiological data of the target user; determining a learning status of the target user according to the physiological data; The knowledge elements to be presented in the next round are adjusted according to the learning status and the evaluation result.

13. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Obtaining a control operation sent by a supervisor corresponding to the target user; The display process of the knowledge content to be learned is adjusted according to the control operation.

14. A guided learning assistance system, characterized in that: The guided learning assistance system comprises: The first acquisition module is used to acquire the knowledge content to be learned corresponding to the target user; A splitting module is used to split the knowledge content to be learned to obtain multiple knowledge elements; A display module, used to display multiple knowledge elements to the target user in multiple rounds, and guide the target user to learn the multiple knowledge elements through pre-generated guidance information; wherein the guidance information includes multiple first guidance information; each of the first guidance information corresponds to each of the knowledge elements; the first guidance information includes information for guiding the target user to output user behavior data for the knowledge element; the display process of each of the multiple knowledge elements includes: displaying the knowledge element and the first guidance information corresponding to the knowledge element; A second acquisition module is used to acquire user behavior data of the target user on the currently displayed knowledge element; A first analysis module is used to analyze the user behavior data according to a preset evaluation index corresponding to the currently displayed knowledge element to obtain the evaluation result of the target user on the currently displayed knowledge element; An adjustment module is used to adjust the knowledge elements and the first guidance information to be displayed in the next round according to the evaluation result.

15. The guided learning assistance system according to claim 14, characterized in that: The guidance information further includes second guidance information; the second guidance information is used to guide the target user to display the overall learning results of the multiple knowledge elements after the multiple rounds of display are completed; The guided learning assistance system also includes: a response module, configured to guide the target user through the second guidance information in response to the event that the display of the plurality of knowledge elements is completed; A third acquisition module is used to acquire the overall learning achievements displayed by the target user for the multiple knowledge elements and / or the learning status of the target user for each of the knowledge elements; A second analysis module is used to analyze the overall learning results and / or learning status to obtain the overall evaluation information of the target user on the knowledge content to be learned; An updating module is used to update the knowledge base corresponding to the target user according to the overall evaluation information; the knowledge base includes the historical learning situation of the target user, applicable knowledge content and at least one of the evaluation indicators.

16. A guided learning auxiliary device, comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the guided learning assistance device performs the guided learning assistance method according to any one of claims 1 to 13.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a processor, the processor is caused to perform the guided learning assistance method according to any one of claims 1 to 13.

Images