Training task generation method, device, electronic apparatus, and storage medium

Abstract

The application relates to the computer technical field, in particular to a training task generation method and device, electronic equipment and storage medium, to improve the training efficiency of a user. The method comprises the following steps: obtaining corresponding training data according to a training rule associated with a target object; constructing an initial training node path based on the training data, each training node representing a kind of key knowledge information in the training data, and the initial training node path representing an initial use sequence of the training nodes; screening each training node contained in the initial training node path and recombining the path based on historical training data associated with the target object, to obtain a corresponding target training node path; and generating a training task for the target object based on the target training node path. Since the training task for the target object in the application is generated based on the target training path, personalized training tasks can be generated for different users, and the training efficiency of the user is effectively improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a training task generation method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of artificial intelligence, a number of training applications, training terminals, and learning applications with training functions have emerged, bringing intelligent training models to trainers and enabling them to conduct training and practice anytime and anywhere.

[0003] Taking dictation exercises as an example, when a user needs to practice dictation, they simply open the dictation terminal and select the content, which the terminal then automatically reads aloud to complete the exercise. However, when users practice dictation, they follow a uniform standard, and the content is predetermined, resulting in poor adaptability. When users engage in independent dictation practice, it is difficult for them to choose content suitable for their individual needs, hindering training efficiency. Therefore, how to generate personalized training tasks for different users and improve training efficiency is an urgent issue to be addressed. Summary of the Invention

[0004] This application provides a training task generation method, apparatus, electronic device, and storage medium to improve user training efficiency.

[0005] This application provides a training task generation method, including:

[0006] Obtain relevant training data based on the training rules associated with the target audience;

[0007] Based on the training data, an initial training node path is constructed, wherein each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node.

[0008] Based on the historical training data associated with the target object, the training nodes included in the initial training node path are filtered and the paths are reorganized to obtain the corresponding target training node path.

[0009] Based on the target training node path, a training task is generated for the target object.

[0010] This application provides a training task generation device, comprising:

[0011] The data acquisition unit is used to obtain the corresponding training data according to the training rules associated with the target object;

[0012] An initial construction unit is used to construct an initial training node path based on the training data, wherein each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node.

[0013] The target construction unit is used to filter and reorganize the training nodes included in the initial training node path based on the historical training data associated with the target object, so as to obtain the corresponding target training node path.

[0014] The task generation unit is used to generate training tasks for the target object based on the target training node path.

[0015] Optionally, the task generation unit is specifically used for:

[0016] Based on the training style corresponding to the target audience, determine the media type corresponding to the training task; and

[0017] Obtain a primary, auxiliary key information database related to current environmental factors;

[0018] Based on the target training node path and the first auxiliary key information database, a training task for the media type is generated.

[0019] Optionally, the device further includes:

[0020] The display unit is used to generate a training activity sequence and training navigation for the target object based on the target training node path, and display them in the task interface; wherein,

[0021] The training activity sequence is used to represent the order of training projects recommended according to the training style of the target object. The training navigation includes at least one of global navigation and local navigation recommended according to the training style of the target object. The global navigation includes a complete training system presented through a knowledge tree structure and the current training status of the target object. The local navigation includes the associated knowledge of the current training node presented through a knowledge concept graph structure.

[0022] Optionally, the device further includes:

[0023] The task update unit is used to obtain a second auxiliary key information database associated with the changed training status if a change in the training status of the target object is detected.

[0024] Based on the second auxiliary key information database, update the target training nodes in the target training node path and the target usage order between the target training nodes;

[0025] Based on the updated target training node path, a new training task is generated for the target object.

[0026] An electronic device provided in this application includes a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor performs the steps of any of the training task generation methods described above.

[0027] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of any of the training task generation methods described above.

[0028] This application provides a computer-readable storage medium including program code. When the program product is run on an electronic device, the program code is used to cause the electronic device to perform the steps of any of the above-described training task generation methods.

[0029] The beneficial effects of this application are as follows:

[0030] This application provides a training task generation method, apparatus, electronic device, and storage medium. Because this application first generates a general initial training path based on training data, and then adjusts the initial training node path by combining it with the target object's historical training data, a target training path is obtained for the target object. The training tasks generated based on the target training path are also targeted at the target object, suitable for the target object, and have high adaptability. That is, this application can generate personalized training tasks for different users, providing different scientific and effective methods and personalized training guidance solutions for users with different training levels and at different times, effectively improving users' training efficiency.

[0031] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0033] Figure 1A This is a schematic diagram of a dictation method in related technologies;

[0034] Figure 1B This is a schematic diagram of another dictation method in related technologies;

[0035] Figure 2 This is an optional schematic diagram of an application scenario in an embodiment of this application;

[0036] Figure 3 This is a flowchart illustrating a training task generation method according to an embodiment of this application;

[0037] Figure 4 This is a schematic diagram of an initial training node path in an embodiment of this application;

[0038] Figure 5 This is a schematic diagram of a target training node path in an embodiment of this application;

[0039] Figure 6 This is a flowchart illustrating a method for generating a target training node path in an embodiment of this application.

[0040] Figure 7 This is a flowchart illustrating a dictation task generation method according to an embodiment of this application;

[0041] Figure 8 This is a schematic diagram of a general model of an adaptive learning system in an embodiment of this application;

[0042] Figure 9 This is a reference model for an adaptive learning system in an embodiment of this application;

[0043] Figure 10 This is a schematic diagram of the first learning activity sequence in the embodiments of this application;

[0044] Figure 11 This is a schematic diagram of the second learning activity sequence in the embodiments of this application;

[0045] Figure 12 This is a schematic diagram illustrating global and local navigation in an embodiment of this application;

[0046] Figure 13 This is a flowchart illustrating a dictation task generation method in an embodiment of this application;

[0047] Figure 14 This is a schematic diagram of the composition of a training task generation device according to an embodiment of this application;

[0048] Figure 15 This is a schematic diagram of the hardware structure of an electronic device using an embodiment of this application;

[0049] Figure 16This is a schematic diagram of the hardware structure of another electronic device using an embodiment of this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this application. Obviously, the described embodiments are only some embodiments of the technical solutions of this application, and not all embodiments. Based on the embodiments recorded in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the technical solutions of this application.

[0051] The following describes some of the concepts involved in the embodiments of this application.

[0052] Dictation is a method of reinforcing memory when learning a human language. Also known as silent writing, it's a teaching method where someone (usually a teacher or parent) reads words or sentences, and the student (or child) writes down the corresponding characters. It's primarily used in learning Chinese and English. For example, when learning Chinese, students listen to the teacher or classmates read aloud while spelling out the words in their notebooks; when learning English, dictation mainly involves the teacher verbally dictating or using multimedia to play the dictation material, and the student listens and writes down what they hear.

[0053] Adaptive learning systems refer to systems that provide learners with personalized learning services. These systems can recommend personalized learning paths and resources based on learners' various characteristics and behavioral tendencies, such as learning goals, preferences, and cognitive levels.

[0054] Training: A method of enabling trainees to master a certain skill through cultivation and training. Specifically, it refers to training that, in order to achieve unified scientific and technological standards and standardized operations, utilizes modern information-based processes such as goal setting, knowledge and information transfer, skill proficiency practice, task achievement evaluation, and result communication and announcement. Through specific educational and training techniques, trainees achieve the expected level of improvement, enhancing their combat effectiveness, personal abilities, and work capabilities. In this embodiment, word dictation training is used as an example for illustration, enabling users to master relevant words and phrases through training.

[0055] Training node path: This represents the order in which training nodes are used, where each training node represents a key piece of knowledge information in the training data. In this application, there are two types of training node paths: the initial training node path and the target training node path. The initial training node path is constructed based on training data associated with training rules, and it is the same for different users, representing the initial order in which each training node is used. The target training node path is obtained by filtering and reorganizing the training nodes in the initial training node path; therefore, the target training node path can be different for different users.

[0056] Key knowledge information refers to the information obtained from the classification of training data. It can be a single character, a word, or a radical, pinyin, stroke, or stroke style (such as left-right structure, top-bottom structure, or top-middle-bottom structure).

[0057] Artificial Intelligence (AI) is the theory, methods, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to have perception, reasoning, and decision-making capabilities. AI technology is a comprehensive discipline involving a wide range of fields, encompassing both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, speech processing, natural language processing, and machine learning / deep learning. In this embodiment, the terminal device or server can implement adaptive recommendations for dictation content based on AI technology.

[0058] The design concept of the embodiments of this application is briefly introduced below:

[0059] Taking dictation as an example of a training task, dictation is an important way for students to assess their learning outcomes. With the development of science and technology, students usually choose to use electronic devices (such as tutoring machines) for dictation practice. Conventional electronic devices require users to add dictation content and then read it aloud based on the added content.

[0060] In intelligent dictation mode, learners can practice dictation anytime, anywhere. However, there are two related technical solutions, both of which rely on teachers, parents, or the students themselves; they are not intelligent and their effectiveness is low. The following sections will introduce these two technical solutions respectively:

[0061] Option 1: User actively selects the option; the specific implementation process is as follows: Figure 1A As shown:

[0062] Step 1: Digitize and store the textbook dictation content digitally, and add tags; Step 2: After the data is processed, present it on a page according to the book's table of contents, allowing users to click and select; Step 3: After seeing the visual table of contents, users can manually select the words they need to dictate; Step 4: Start dictation.

[0063] However, this method lacks scientific guidance regarding which dictation content users need to select, how to dictate, how much to dictate today, and whether dictation is required tomorrow. Users simply follow the teacher's pace, learning and dictating one lesson at a time from beginning to end. Teachers can only adjust the plan and assign homework based on the overall situation of the class, failing to provide individualized teaching guidance and assistance for each student. It cannot customize a scientific and reasonable teaching plan suitable for each student's individual intelligence level, learning ability, academic performance, mastery level, and acceptance level. Therefore, this method is inefficient and ineffective, failing to identify students' weaknesses and conduct targeted dictation training and review.

[0064] Option 2: Task distribution, the specific implementation process is as follows: Figure 1B As shown:

[0065] Step 1: Based on the teacher's teaching experience, assign electronic dictation homework or dictation requirements, such as dictating the vocabulary of Lessons 1-2 today, or dictating all the vocabulary of Units 1-4 of the third grade textbook today; Step 2: Students dictate according to the teacher's requirements.

[0066] However, this method assigns homework to all students in a class. Because students of different learning levels, abilities, and proficiency levels need to complete the same task, it takes a certain amount of time for high-achieving students to complete such homework, and it is not very meaningful, since they have already mastered the words and phrases. For low-achieving students, this approach takes a lot of time, because their proficiency and mastery of the words and phrases are lower, requiring a long time to complete and yielding poor results. Therefore, teachers cannot assign homework in a differentiated manner based on students' abilities, providing different solutions and learning plans for different students.

[0067] In summary, both of these approaches rely heavily on experienced teachers. Guiding students based on their teaching experience requires high-quality human resources. Furthermore, if teachers lack comprehensive data collection, understanding of students' learning progress, or timely updates, the experience they provide may be inappropriate, which can negatively impact the final teaching effectiveness.

[0068] In view of this, embodiments of this application provide a training task generation method, apparatus, electronic device, and storage medium. Since this application first generates a general initial training path based on training data, and then adjusts the initial training node path by combining it with the historical training data of the target object, a target training path is obtained for the target object. The training tasks generated based on the target training path are also targeted at the target object, suitable for the target object, and have high adaptability. That is, this application can generate personalized training tasks for different users, providing different scientific and effective methods and personalized training guidance solutions for users with different training levels and at different times, effectively improving the user's training efficiency.

[0069] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0070] like Figure 2 The diagram shown illustrates an application scenario of an embodiment of this application. The application scenario diagram includes two terminal devices 210 and one server 220. In this embodiment, the terminal device 210 may be equipped with a training client, which allows trainees to conduct training exercises anytime, anywhere.

[0071] Specifically, the training in this application embodiment can refer to Chinese dictation training, English word dictation training, mathematical formula training, etc. In this article, Chinese dictation training is mainly used as an example for illustration. For example, a dictation client can be installed on the terminal device 210, which is used to enable the dictator to practice dictation anytime and anywhere.

[0072] Each terminal device can have a client installed for training, such as an application (APP) for Chinese dictation, an APP for English dictation, or other learning APPs with dictation functions. The client involved in this application embodiment can be a pre-installed client (e.g., software), a client embedded in an application (e.g., a mini-program), or a web-based client; the specific type of client is not limited. The server is the server corresponding to the software, webpage, mini-program, etc.

[0073] In dictation scenarios, dictation assignments are usually given regularly, such as after learning new lessons, during weekend review, during unit reviews, and before mid-term and final exams. Therefore, dictation assignments are a common and frequently occurring form of homework. Dictation assignments are typically initiated by teachers, parents, or students. Teachers may assign dictation as homework, parents may encourage students to study more after class, and children may want to review and prepare before exams.

[0074] The training task generation method in this application embodiment can be executed by the server or the terminal device alone, or by both the server and the terminal device. For example, the server obtains the corresponding training data according to the training rules associated with the target object, and constructs an initial training node path based on the training data; then, based on the historical training data associated with the target object, the server filters and reorganizes the training nodes included in the initial training node path to obtain the corresponding target training node path, and sends the target training node path to the terminal device. The terminal device generates and displays a training task for the target object based on the target training node path, such as a word dictation task.

[0075] In one alternative implementation, the terminal device 210 and the server 220 can communicate via a communication network.

[0076] In one alternative implementation, the communication network is a wired network or a wireless network.

[0077] In this embodiment, the terminal device 210 is an electronic device used by a user. This electronic device can be a personal computer, laptop, learning phone, learning tablet, mobile phone, mobile tablet, learning machine, e-reader, tutoring machine, television, e-book reader, in-vehicle terminal, personal digital assistant, or other electronic device with certain computing capabilities and running instant messaging software and websites or social networking software and websites. It can also be a smart education hardware product with training capabilities, such as a smart speaker, smart learning platform, or smart study lamp. Each terminal device 210 is connected to the server 220 via a wireless network. The server 220 is a single server, a server cluster or cloud computing center composed of several servers, or a virtualization platform.

[0078] It should be noted that, Figure 2 The examples shown are merely illustrative; in reality, the number of terminal devices and servers is unlimited and is not specifically limited in the embodiments of this application.

[0079] The training task generation method provided by the exemplary embodiments of this application will be described below with reference to the accompanying drawings and the application scenarios described above. It should be noted that the application scenarios described above are only shown to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way in this respect.

[0080] See Figure 3 The diagram shown is an implementation flowchart of a training task generation method provided in this application embodiment. The example uses a terminal device as the executing entity. The specific implementation flow of this method is as follows:

[0081] S31: The terminal device obtains the corresponding training data according to the training rules associated with the target object;

[0082] In a dictation scenario, training rules mainly refer to teaching requirements and syllabi related to vocabulary learning, while training data refers to the dictation-related words and phrases specified in the teaching requirements and syllabi. First, based on the training rules, the relevant textbook dictation content needs to be digitized and stored digitally, with labels added. For example, "People's Education Press, Grade 1, Unit 1, Lesson 1: The Primary School Under the Big Green Tree." New words are divided into two different categories: "I can write" and "I can recognize." From a teaching perspective, the requirements for "I can write" are higher than those for "I can recognize," for example, "I can write: sky, earth, person..."; "I can recognize: you, I, he..."; and words like "sky, white clouds...".

[0083] S32: The terminal device constructs an initial training node path based on the training data, where each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node.

[0084] The initial training node path refers to the universal learning path applicable to all objects.

[0085] Optionally, when constructing the initial training node path based on the training data, since each training node in the path represents a key knowledge information, the corresponding training nodes and the initial usage order between the training nodes can be determined by classifying all the key knowledge information in the training data; then, the initial training node path can be constructed based on the training nodes and the initial usage order between the training nodes.

[0086] One type of key knowledge information can be a character, a word, or a radical, pinyin, stroke, or stroke style (such as left-right structure, top-bottom structure, or top-middle-bottom structure), etc., without specific limitations.

[0087] Suppose that the training data consists of dictation words from a first-grade elementary school textbook, and each training node represents a specific word. Then, all the training data can be categorized and divided to determine all the words that need to be mastered, with each word corresponding to a training node. Furthermore, based on the teaching requirements, the initial order of use of each training node, i.e., the learning order, can be determined.

[0088] See Figure 4 The diagram shown illustrates an initial training node path in an embodiment of this application. For example, it first divides the textbook into units, resulting in Unit 1, Unit 2, Unit 3, Unit 4, etc., and then sorts the training nodes within each unit based on teaching requirements, such as... Figure 4 As shown, the order is as follows: Training Node 1, Training Node 2, Training Node 3, Training Node 4, ..., Training Node 13, ...

[0089] S33: Based on the historical training data associated with the target object, the terminal device filters and reorganizes the training nodes included in the initial training node path to obtain the corresponding target training node path.

[0090] S34: The terminal device generates a training task for the target object based on the target training node path.

[0091] See Figure 5 As shown, this is a schematic diagram of a target training node path in an embodiment of this application. Figure 4 Compared to the initial training node path shown, the training nodes that the target audience has not yet mastered, and their order, are: Training Node 8, Training Node 3, Training Node 4, Training Node 9, Training Node 2, Training Node 12, and Training Node 11. Clearly, for the target audience, the training nodes in this target training node path are... Figure 4 The number and order of the training nodes shown are different.

[0092] Specifically, this embodiment of the application takes into account that different objects may have different learning levels and abilities. Therefore, after determining the initial training node path that is universal for all objects based on step S32, it is necessary to further generate a personalized target training node path for the target object based on the historical training data associated with the target object. Then, based on this, a personalized training task for the target object is generated. This method can provide users with scientific and accurate training plans and path guidance, enabling high-quality training, improving training efficiency, and ensuring training effectiveness.

[0093] The following section will take dictation as an example to provide a detailed explanation of the dictation task generation method in the embodiments of this application.

[0094] One alternative implementation is to proceed as follows: Figure 6 The flowchart shown below implements S32, which is a schematic diagram of a method for generating a target training node path in an embodiment of this application, including the following steps:

[0095] S61: The terminal device determines the target key knowledge information that meets the preset conditions in the historical training data, as well as the training standards corresponding to the target key knowledge information.

[0096] Among them, historical training data refers to the data collected on electronic devices such as desk lamps, tablets, and mobile phones when users use learning software, with user authorization. For example, the learning data generated by user A in various Chinese language-related learning apps. After obtaining this data, some preset data information related to words and phrases can be extracted as key knowledge information for the target, in order to construct a knowledge path map for word and phrase learning, i.e., the target training node path.

[0097] Optionally, the target key knowledge information that meets the preset conditions includes at least one of the following:

[0098] During the corresponding historical training process, the key knowledge information whose error rate reaches the first preset threshold;

[0099] During the relevant historical training process, add key knowledge information with designated markers;

[0100] During the corresponding historical training process, key knowledge information that has been searched up to the second preset threshold number of times.

[0101] Based on the aforementioned historical training data, at least one of the following can be obtained over a certain period: key knowledge information where the user's error rate exceeds a first preset threshold, such as words with a certain radical; key knowledge information marked with specific tags such as error markers or emphasis markers added by the user (e.g., words added to a misspelling notebook, misspelling word notebook, or new character notebook); and words whose search frequency reaches a second preset threshold during learning using a certain learning app. These are not specifically limited here. Based on this user data, the user's weak areas can be identified, and corresponding learning paths, learning plans, and content can be matched to the user.

[0102] S62: Based on the target key knowledge information and the corresponding training standards, the terminal device filters and reorganizes the training nodes included in the initial training node path to generate the target training node path.

[0103] The training standards mainly refer to the learning requirements and attributes of words and phrases, such as "I can read" and "I can write". Based on the training standards and key knowledge information that reflects the learning level of the target audience, the training nodes in the initial training node path can be further filtered. Training nodes already mastered by the target audience are removed, and several training nodes not yet mastered are selected. The order of use of these selected training nodes is then rearranged, i.e., path reorganization, to generate the target training node path.

[0104] Optionally, step S62 can be further divided into the following steps:

[0105] S621: The terminal device filters out each training node that is associated with the key knowledge information of the target.

[0106] For example, based on user A's historical training data, the target key knowledge information selected might include words with the "person" radical, words with the "wood" radical, and related pinyin and sentence examples. Based on this target key knowledge information, relevant target training nodes can be selected from the initial training node path. For instance, 10 training nodes could be selected from 100 initial training nodes as target training nodes, numbered 1-10. Alternatively, 20 training nodes could be selected from 100 initial training nodes, and related nodes within these 20 nodes could be merged to generate 10 target training nodes. The merging of training nodes can be based on the target audience's learning level, learning style, etc., and is not specifically limited here.

[0107] S622: The terminal device determines the difficulty label of the associated target training node based on the training standard corresponding to the target key knowledge information;

[0108] In addition to the aforementioned "I can read" and "I can write," the training standards can also include more complex standards, such as "I can create words" and "I can construct sentences." Based on these training standards, the difficulty level of each training objective can be determined; for example, "I can read" is Level 1, "I can write" is Level 2, "I can create words" is Level 3, "I can construct sentences" is Level 4, and so on.

[0109] S623: The terminal device reorganizes the paths of each target training node based on the difficulty labels of each target training node and the initial usage order between each target training node in the general training path, and determines the target usage order between each target training node.

[0110] S624: The terminal device constructs the target training node path based on each target training node and the target usage order between each target training node.

[0111] After determining the difficulty labels of each target training node based on the above process, the target training nodes can be rearranged based on the initial usage order between the target training nodes and the previously determined difficulty labels. Specifically, when rearranging, the order between the target training nodes follows the principle that for the same type of target training nodes, the higher the difficulty label, the more backward the node is, and for different types of target training nodes, the order is determined based on the initial usage order, etc.

[0112] For example, there are 10 target training nodes. These target training nodes can be classified according to radicals, structures, etc. Among them, 5 target training nodes belong to the radical "ren" and can be classified as one type of target training nodes (abbreviated as type A, numbered 1-5 respectively), and the other 5 target training nodes belong to the radical "mu" and can be classified as one type of target training nodes (abbreviated as type B, numbered 1-5 respectively). When sorting the 5 type A target training nodes, the principle that the higher the difficulty label, the more backward the node can be followed. For example, the order is: target training node 1 -> target training node 3 -> target training node 2 -> target training node 4 -> target training node 5; when sorting the 5 type B target training nodes, the same principle that the higher the difficulty label, the more backward the node can be followed. For example, the order is: target training node 10 -> target training node 8 -> target training node 7 -> target training node 9 -> target training node 6; for type A and type B, among which the initial usage order of type A is mostly forward and the initial usage order of type B is mostly backward. Therefore, based on this, the final target usage order is determined, and the target training node path is generated as: target training node 1 -> target training node 3 -> target training node 2 -> target training node 4 -> target training node 5 -> target training node 10 -> target training node 8 -> target training node 7 -> target training node 9 -> target training node 6.

[0113] Of course, it is also possible to calculate the average value of the initial usage order of each target training node in one type of target training nodes and perform inter-class sorting based on the average value. It should be noted that the above method for determining the target usage order is only an example. In fact, any method for determining the target usage order based on the difficulty labels of each target training node and the initial usage order between the target training nodes in the general training path is applicable in this application and will not be specifically limited here.

[0114] Based on the above implementation method, the order of textbook compilation can be broken. Students do not need to strictly perform dictation according to the requirements of teachers, parents, etc., and do not need to blindly follow the order of the book catalog, such as dictating the first lesson first, or dictating lessons 1-5 in the first unit first, etc. In this way, all the words and expressions that students should master within the learning stage can be scattered according to the students' personal learning abilities, and the order of words and expressions can be reorganized according to the students' learning situations, so as to achieve better teaching purposes.

[0115] In one alternative implementation, when generating a training task for the target object based on the target training node path, the specific process is as follows:

[0116] Based on the training style corresponding to the target audience, determine the media type corresponding to the training task; and obtain the first auxiliary key information database associated with the current environmental factors; then, based on the target training node path and the first auxiliary key information database, generate the training task of that media type.

[0117] Training style primarily refers to learning style, which can generally be categorized as: information processing (active, reflective), perception (perception, intuition), information input (visual, verbal), and content comprehension (sequential, comprehensive). Media type describes a user's preference for specific media formats, including: images, videos, and text. For example, an active training style is best suited to video; a reflective style to images and text; a visual style to videos and images; and a verbal style to text.

[0118] In this embodiment, current environmental factors include social hotspots and weather factors. For example, if the current weather is the plum rain season, information related to the plum rain season can be obtained as a first auxiliary key information database. When generating a training task for a certain media type based on the first auxiliary key information database and the previously obtained target training node path,

[0119] The media type can be at least one of video, image, and text. For example, it can be in video format, or it can be in image + text format, etc. The specific choice depends on the actual situation and is not specifically limited here.

[0120] In the above implementation, different target training node paths can be provided according to factors such as period and learning environment. During the user's entire learning cycle, there will be special periods, such as during winter and summer vacations, there will be review and preview; during the semester, there will be new course learning, weekly summaries, monthly reviews, mid-term exams, and final exams; and throughout the entire academic stage, there will be special periods such as entrance exams. Based on the above implementation, different training programs can be provided to students according to different timings.

[0121] Optionally, considering that users' learning performance changes dynamically, when the status of word browsing or dictation testing changes, it is necessary to adjust and update in a timely manner, dynamically update the position in the word learning knowledge path, regenerate appropriate learning positions and tasks, fully supplement school education, solve the problem of teachers' inability to provide precise teaching for individual students, thereby reducing the burden on teachers, parents and students, and ensuring the final teaching effect and efficiency.

[0122] An alternative implementation involves updating the target training node path based on the following process:

[0123] If a change in the training status of the target object is detected, the second auxiliary key information database associated with the changed training status is obtained; based on the second auxiliary key information database, the target training nodes in the target training node path and the target usage order between the target training nodes are updated; based on the updated target training node path, the training task for the target object is regenerated.

[0124] The training status primarily refers to the user's learning state, which can be determined based on the user's learning comprehension ability and level. Generally, a user's training status changes as the number of knowledge points learned increases. The second auxiliary key information database refers to the information database associated with the changed training status. For example, if a user sets a goal of obtaining a relevant award, the information database related to that award can be used as the second auxiliary key information database; or, if a user obtains a word-related award, a more complex new word database outside of that award can be used as the second auxiliary key information database, and so on. The specific approach depends on the actual situation and is not specifically limited here.

[0125] When updating the target training node path based on the second auxiliary key information database and the training status of the target object, in addition to updating the target usage order of the target training nodes, it also includes updating the target training nodes, that is, deleting the target training nodes that the user has mastered and then selecting some new target training nodes.

[0126] Based on the above implementation method, the words and phrases that students need to master can be broken down and reorganized according to different students, different periods, and different levels of mastery; a customized dictation plan can be provided for each student; different content can be provided for each student; making dictation more intelligent, more efficient, and more effective, guiding users to dictate with the best solution and the best plan to ensure the final learning effect.

[0127] The following section will take dictation task generation as an example to describe in detail the above-mentioned method in the embodiments of this application:

[0128] Because related technologies often fail to consider the varying dictation abilities of different students, a mismatch may arise between the difficulty of the dictation content and the students' dictation skills. This application proposes a method for generating dictation tasks. (See reference...) Figure 7 The diagram shown is a flowchart illustrating a dictation task generation method proposed in this application. It specifically includes the following steps:

[0129] 1. Data processing refers to the electronic processing of the vocabulary that students should master.

[0130] A specific implementation method can be as follows: use the camera module of an electronic device to take a picture of the paper book in the shooting area of ​​the camera module to obtain a book image; analyze the book image to obtain the book content, and then record the words contained in the book content as dictation words.

[0131] For example, based on the requirements of the curriculum standards, student textbooks, teaching syllabus, and examination syllabus, extract the words and phrases that students need to master in this stage (primary, junior high, and senior high school) and store them in data form. When storing, the words and phrases should be accompanied by detailed tag attributes, such as publisher, grade, volume, unit, text title, words I can recognize, words I can write, etc.

[0132] 2. Construct a general knowledge path for word and phrase learning, namely the initial training node path in this article.

[0133] Specifically, a general knowledge path for vocabulary learning can be constructed according to grade level, textbook order, text sequence, difficulty, etymological relationships, and writing style relationships. This path presents content that students need to master in accordance with the characteristics of their grade level.

[0134] Among them, etymological relationship refers to the connection between the evolutionary processes of characters, while brushwork relationship refers to the connection between the writing brushwork of characters, such as general brushwork such as left-right structure, top-bottom structure, and top-middle-bottom structure.

[0135] 3. Data collection refers to collecting user data generated from various learning apps with user authorization. This includes collecting incorrectly written words and marking them with attributes. Examples include words the user has looked up, words added to their vocabulary notebooks, words the user has dictated, and words the user has photographed and corrected. These data are used for subsequent location tracking. Attributes refer to the word's characteristics, such as whether it can be written, recognized, or memorized.

[0136] 4. Generate a customized knowledge path for the user, i.e., a target training node path.

[0137] Specifically, firstly, a knowledge path map suitable for the user's word learning is generated, including the learning order and difficulty labels of the knowledge; then, by collecting Chinese character information and combining it with the user's current state, the weakest word learning area of ​​the user is located, and the corresponding learning path is matched.

[0138] 5. Generate dictation tasks.

[0139] Specifically, the system prioritizes providing dictation content for the current area and plans subsequent learning and dictation activities based on the learning path, generating daily tasks for dictation content and vocabulary mastery. When the vocabulary browsing or dictation test status changes, the system dynamically updates the position of the vocabulary in the learning knowledge path and regenerates appropriate learning positions and tasks.

[0140] In this embodiment of the application, an adaptive learning system can be constructed to plan a knowledge path for users to learn words and phrases.

[0141] See Figure 8 As shown, this is a schematic diagram of a general model of an adaptive learning system proposed in this application embodiment. The model may specifically include the following parts:

[0142] I. Domain Model: Describes the knowledge structure of the domain, including concepts and the relationships between them. II. Student Model (also known as User Model, UM): Represents student characteristics, describing each user's knowledge, tendencies, and interests. III. Pedagogical Model: Defines the rules for accessing various parts of the domain model based on information from the student model. IV. Adaptive Engine: The entire software environment for creating and updating domain concepts and links, using information from other models to personalize the selection, annotation, and presentation of learning content for learners. V. Interface Module: Represents and defines the interaction between the user and the adaptive learning system.

[0143] In this embodiment, the system can semantically describe learning resources and semantically diagnose learning styles and cognitive levels, enabling learning resources and learning paths to be dynamically presented based on learner models. This achieves resource sharing, reuse, and personalized recommendations, realizing bidirectional adaptation between learners and the system.

[0144] The following is combined Figure 8 The general learning model of the adaptive system shown is presented, and an adaptive learning system reference model is proposed for the dictation task generation method in the embodiments of this application.

[0145] See Figure 9As shown, this is a reference model for an adaptive learning system in an embodiment of this application. The model specifically includes the following parts:

[0146] I. User Model (i.e., student model) and Learning Behaviors:

[0147] The user model describes the individual characteristics of users, such as basic information about learners (students) (name, gender, date of birth, phone number, email address, education level, etc.), learning style, cognitive level, and interest preferences.

[0148] Learning behavior records the learner's learning history (such as the type of media accessed, learning time, and number of accesses to learning resources), and the system can continuously update the user model based on the user's learning history.

[0149] II. Domain Model:

[0150] Describe the structure of domain knowledge, including concepts and relationships between them. Each concept can have different attributes, and concepts with the same attributes can be of different data types. A relationship between concepts is an object that connects two or more concepts, possessing a unique identifier and attributes.

[0151] III. Adaptive Model (i.e., Educational Model):

[0152] This model defines a set of rules for how to access different parts of the domain model based on information in the user model, generate adaptive actions, and modify the user model. These rules reflect the ideas behind the instructional design of the course.

[0153] IV. Adaptive Engine:

[0154] This part corresponds to the system implementation, executing adaptive rules, selecting, assembling, and presenting pages based on the user model, and modifying and maintaining the user model based on the user's learning behavior history.

[0155] V. Presentation Model:

[0156] The system uses an adaptive engine to achieve adaptive display of at least one of the three aspects: content, presentation, and sequence, based on the user model, domain model, and adaptive model.

[0157] When displaying content, the system can present different media types (such as videos, images, text, etc.) according to the user's learning style; the system can also present learning content with different characteristics such as facts or abstractions according to the user's learning style.

[0158] When displaying navigation, the system can divide it into global navigation and local navigation based on learning style and cognitive level, which will be described in detail below.

[0159] The estimation of cognitive level is mainly achieved by estimating students' mastery of a certain knowledge point through practice test records. Then, the system recommends knowledge resources at the corresponding level according to the user's different cognitive levels, thereby creating a more personalized learning process and learning goals.

[0160] When displaying the learning activity sequence, the system can adapt and recommend learning sequences based on the learner's learning style. Specifically, to achieve the learning objectives, the system can present a practical learning plan based on the user's individual differences. This learning plan integrates learning objectives, training tasks, operation steps, interaction methods, evaluation mechanisms, etc., which will be described in detail below.

[0161] Based on the aforementioned adaptive learning system, this application proposes a method for providing users with vocabulary learning path planning and content planning using an adaptive learning system. This addresses the problem that users often simply follow a sequential order when dictating words, resulting in a time-consuming and ineffective process. Therefore, it can provide different scientific and effective methods and personalized teaching and tutoring solutions for students at different learning levels and stages. Furthermore, this application solves the problem that school teachers can only provide general education and cannot offer personalized and targeted learning plans. It allows students to focus on dictating words that are less familiar, more difficult, or less firmly grasped. By following this method and the provided path for learning and dictation, students can achieve more efficient learning.

[0162] In one alternative implementation, the task interface can be displayed in the following manner:

[0163] Based on the target training node path, a training activity sequence and training navigation for the target audience are generated and displayed in the task interface.

[0164] Among them, the training activity sequence is used to represent the order of training programs recommended according to the training style of the target audience. It is also called the learning activity sequence. The system can adapt and recommend learning sequences according to the learner's learning style.

[0165] See Figure 10The diagram illustrates the first learning activity sequence in this embodiment. The left side represents the learning activity sequence for active users, and the right side represents the learning activity sequence for contemplative users. For active learners, the system recommends the following learning activity sequence: Outline → Resources → Summary → Practice → Forum → Examples → Test; for contemplative learners, the system recommends the following learning activity sequence: Outline → Resources → Summary → Examples → Forum → Practice → Test.

[0166] See Figure 11 As shown, this is a schematic diagram of the second learning activity sequence in an embodiment of this application. Figure 10 resemblance, Figure 11 The left side of the middle section shows the learning activity sequence corresponding to verbal learners. Figure 10 The left-hand sequence is the same, while the right-hand sequence represents the learning activity sequence for visual learners. Figure 10 The left-hand sequences are the same. Figure 11 It further demonstrates the different media types for users with different learning styles. For verbal learners, learning resources can be displayed through text; for visual learners, learning resources can be displayed through at least one of video and images.

[0167] remove Figure 10 and Figure 11 In addition to the examples listed, the system can also recommend the following learning activity sequence for active learners: participate in discussions (required) → read learning materials (recommended) → conduct case studies (recommended) → do exercises (required) → complete tests (required); for reflective learners, the system can also recommend the following learning activity sequence: read learning materials (required) → conduct case studies (required) → participate in discussions (recommended) → do exercises (required) → complete tests (required).

[0168] It should be noted that the learning activity sequences listed above are just examples, and specific implementations can be made according to actual circumstances. No specific limitations are made here.

[0169] The training navigation in the embodiments of this application will be described in detail below.

[0170] The training navigation includes at least one of global navigation and local navigation recommended based on the training style of the target audience.

[0171] See Figure 12 As shown, it is a schematic diagram of global navigation and local navigation in an embodiment of this application. Figure 12 The knowledge tree shown on the left is the global navigation, which can include a complete training system presented through a (domain) knowledge tree structure. For example... Figure 12As shown, there are multiple nodes. The current illustration only displays the sixth node (the training node). You can scroll up and down to view the other nodes that are not yet displayed. In addition, a node can also include multiple child nodes, such as sub-nodes for word creation and sentence creation, or further subdivided into sub-nodes according to stroke count, etymology, etc. There are no specific limitations here.

[0172] In addition, the current training status of the target can be displayed through a tree structure. For example, by using different colors, different patterns and other learning status markers, the current mastery status of the learner can be displayed. No specific limitations are made here.

[0173] Figure 12 The knowledge point structure shown on the right is the local navigation, which includes the related knowledge of the current training node (i.e., xx under the fourth sub-node) presented through a knowledge concept map structure. Specifically, the knowledge concept map provided to learners clearly shows the related knowledge, preceding knowledge, and subsequent knowledge of the current knowledge point. Among them, related knowledge includes, for example, pinyin, word formation, and sentence construction; preceding knowledge includes, for example, knowledge that needs to be reviewed; and subsequent knowledge includes, for example, knowledge that needs to be previewed.

[0174] In the above implementation, when students are about to complete a dictation task, they will see a vocabulary learning map tailored to them, marked with a clear learning path and current progress, and provided with a detailed plan, such as which words to dictate and the frequency of dictation; once students have used it, if their learning performance and progress change or are updated, the path will be planned, and the task will be dynamically adjusted to be the most suitable according to the student's learning situation and mastery.

[0175] In summary, this application leverages AI's adaptive capabilities to provide users with targeted and scientific dictation plans, solutions, and content, significantly improving training efficiency and effectiveness while avoiding the pitfalls of rote memorization. It can accurately reflect students' true dictation levels, helping them clearly understand whether their dictation skills have improved, enabling them to make rapid and significant progress in dictation training and enhancing their learning outcomes.

[0176] See Figure 13 The diagram shown is a flowchart of another dictation task generation method according to an embodiment of this application. The specific implementation process of this method is as follows:

[0177] Step S1301: The terminal device obtains the corresponding words and phrases according to the course dictation rules associated with student A;

[0178] Step S1302: The terminal device constructs the initial dictation node path for word learning based on the obtained words;

[0179] Step S1303: With student A's authorization, the terminal device collects user data of student A generated in various learning apps;

[0180] Step S1304: Based on the collected user data, the terminal device determines the target key knowledge information that meets the preset conditions, as well as the dictation standard corresponding to the target key knowledge information.

[0181] Step S1305: The terminal device filters out each target dictation node that is associated with the target key knowledge information in each dictation node;

[0182] Step S1306: The terminal device determines the difficulty label of the associated target dictation node based on the dictation standard corresponding to the target key knowledge information;

[0183] Step S1307: Based on the difficulty tags of each target dictation node and the initial usage order between each target dictation node in the general dictation path, the terminal device reorganizes the paths of each target dictation node to determine the target usage order between each target dictation node.

[0184] Step S1308: The terminal device constructs the target dictation node path based on each target dictation node and the target usage order between each target dictation node;

[0185] Step S1309: The terminal device determines the media type corresponding to the dictation task based on the dictation style of student A;

[0186] Step S1310: The terminal device generates a dictation task for this media type based on the target dictation node path;

[0187] Step S1311: If the terminal device detects a change in student A's dictation status, it acquires the auxiliary key information database associated with the changed dictation status.

[0188] Step S1312: The terminal device updates the target dictation nodes in the target dictation node path and the target usage order between the target dictation nodes according to the auxiliary key information database;

[0189] Step S1313: The terminal device regenerates the dictation task for student A based on the updated target dictation node path.

[0190] Based on the above implementation method, when students are about to complete a dictation task, they will see a vocabulary learning map tailored to them, with a clear learning path and current progress marked, and a detailed plan provided, such as which words to dictate and the frequency of dictation. Once students have used it, if their learning performance and progress change or are updated, the path will be replanned, and the task will be dynamically adjusted to be the most suitable according to the student's learning situation and mastery.

[0191] Based on the same inventive concept, embodiments of this application also provide a training task generation device. For example... Figure 14 As shown, this is a schematic diagram of the training task generation device 1400, which may include:

[0192] The data acquisition unit 1401 is used to obtain the corresponding training data according to the training rules associated with the target object;

[0193] The initial building unit 1402 is used to build an initial training node path based on the training data, wherein each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node.

[0194] The target construction unit 1403 is used to filter and reorganize the training nodes included in the initial training node path based on the historical training data associated with the target object, so as to obtain the corresponding target training node path.

[0195] The task generation unit 1404 is used to generate training tasks for the target object based on the target training node path.

[0196] Optionally, the initial building unit 1402 is specifically used for:

[0197] By classifying all the key knowledge information in the training data, we can determine the corresponding training nodes and the initial usage order between the training nodes.

[0198] The initial training node path is constructed based on each training node and the initial usage order between them.

[0199] Optionally, target building unit 1403 is specifically used for:

[0200] Identify the key knowledge information of the target that meets the preset conditions in the historical training data, and the training standards corresponding to the key knowledge information of the target;

[0201] Based on the key knowledge information of the target and the corresponding training standards, the training nodes included in the initial training node path are screened and the paths are reorganized to generate the target training node path.

[0202] Optionally, the target key knowledge information that meets the preset conditions includes at least one of the following:

[0203] During the corresponding historical training process, the key knowledge information whose error rate reaches the first preset threshold;

[0204] During the relevant historical training process, add key knowledge information with designated markers;

[0205] During the corresponding historical training process, key knowledge information that has been searched up to the second preset threshold number of times.

[0206] Optionally, target building unit 1403 is specifically used for:

[0207] Filter out the training nodes that are associated with the key knowledge information of the target from each training node;

[0208] Based on the training standards corresponding to the key knowledge information of the target, the difficulty labels of the associated target training nodes are determined.

[0209] Based on the difficulty labels of each target training node and the initial usage order of each target training node in the general training path, the path of each target training node is reorganized to determine the target usage order of each target training node.

[0210] Based on each target training node and the order in which the target is used between them, a target training node path is constructed.

[0211] Optionally, the task generation unit 1404 is specifically used for:

[0212] Determine the media type appropriate for the training task based on the training style of the target audience; and

[0213] Obtain a primary, auxiliary key information database related to current environmental factors;

[0214] Based on the target training node path and the first auxiliary key information database, generate training tasks for media types.

[0215] Optionally, the device also includes:

[0216] Display unit 1405 is used to generate a training activity sequence and training navigation for the target audience based on the target training node path, and display them in the task interface; wherein,

[0217] The training activity sequence is used to represent the order of training projects recommended based on the training style of the target audience. The training navigation includes at least one of global navigation and local navigation recommended based on the training style of the target audience. The global navigation includes the complete training system presented through a knowledge tree structure and the current training status of the target audience. The local navigation includes the associated knowledge of the current training node presented through a knowledge concept graph structure.

[0218] Optionally, the device also includes:

[0219] The task update unit 1406 is used to obtain a second auxiliary key information database associated with the changed training status if a change in the training status of the target object is detected.

[0220] Based on the second auxiliary key information database, update the target training nodes in the target training node path, as well as the target usage order between the target training nodes;

[0221] Based on the updated target training node path, a new training task is generated for the target audience.

[0222] For ease of description, the above sections are divided into modules (or units) according to their functions and described separately. Of course, in implementing this application, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0223] Having introduced the training task generation method and apparatus according to exemplary embodiments of this application, we will now introduce an electronic device for training task generation according to another exemplary embodiment of this application.

[0224] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0225] Based on the same inventive concept as the above-described method embodiments, this application also provides an electronic device. In one embodiment, the electronic device may be a server, such as... Figure 2 The server 220 is shown. In this embodiment, the structure of the electronic device can be as follows: Figure 15 As shown, it includes a memory 1501, a communication module 1503, and one or more processors 1502.

[0226] The memory 1501 is used to store computer programs executed by the processor 1502. The memory 1501 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0227] Memory 1501 may be volatile memory, such as random-access memory (RAM); memory 1501 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 1501 may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 1501 may be a combination of the above-described memories.

[0228] Processor 1502 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 1502 is used to implement the above-described training task generation method when it calls the computer program stored in memory 1501.

[0229] The communication module 1503 is used to communicate with terminal devices and other servers.

[0230] This application embodiment does not limit the specific connection medium between the memory 1501, communication module 1503, and processor 1502. This application embodiment... Figure 15 The memory 1501 and the processor 1502 are connected via a bus 1504, and the bus 1504 is in Figure 15 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. The 1504 bus can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 15 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.

[0231] The memory 1501 stores a computer storage medium, which stores computer-executable instructions for implementing the training task generation method of this application embodiment. The processor 1502 is used to execute the above-described training task generation method, such as... Figure 3 As shown.

[0232] In another embodiment, the electronic device can also be other electronic devices, such as... Figure 2 The terminal device 210 is shown. In this embodiment, the electronic device can be structured as follows: Figure 16As shown, it includes components such as: communication component 1610, memory 1620, display unit 1630, camera 1640, sensor 1650, audio circuit 1660, Bluetooth module 1670, processor 1680, etc.

[0233] The communication component 1610 is used to communicate with the server. In some embodiments, it may include a Wireless Fidelity (WiFi) module, which is a short-range wireless transmission technology, and the electronic device can help the user send and receive information through the WiFi module.

[0234] The memory 1620 can be used to store software programs and data. The processor 1680 executes various functions of the terminal device 210 and performs data processing by running the software programs or data stored in the memory 1620. The memory 1620 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 1620 stores an operating system that enables the terminal device 210 to run. In this application, the memory 1620 may store the operating system and various applications, and may also store code that executes the training task generation method of the embodiments of this application.

[0235] The display unit 1630 can also be used to display information input by the user or information provided to the user, as well as various menus of the terminal device 210, forming a graphical user interface (GUI). Specifically, the display unit 1630 may include a display screen 1632 disposed on the front of the terminal device 210. The display screen 1632 may be configured as a liquid crystal display, a light-emitting diode, or the like. The display unit 1630 can be used to display the task interface, etc., as described in the embodiments of this application.

[0236] The display unit 1630 can also be used to receive input digital or character information and generate signal inputs related to user settings and function control of the terminal device 210. Specifically, the display unit 1630 may include a touch screen 1631 disposed on the front of the terminal device 210, which can collect touch operations of the user on or near it, such as clicking buttons, dragging scroll boxes, etc.

[0237] The touchscreen 1631 can be placed over the display screen 1632, or the touchscreen 1631 and the display screen 1632 can be integrated to realize the input and output functions of the terminal device 210. After integration, it can be referred to as a touch display screen. In this application, the display unit 1630 can display the application program and the corresponding operation steps.

[0238] Camera 1640 can be used to capture still images, which users can then post comments on via the application. There can be one or multiple cameras 1640. An object is projected onto a photosensitive element through a lens, generating an optical image. This photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to the processor 1680 to be converted into a digital image signal.

[0239] The terminal device may also include at least one sensor 1650, such as an accelerometer 1651, a proximity sensor 1652, a fingerprint sensor 1653, and a temperature sensor 1654. The terminal device may also be equipped with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, and motion sensor.

[0240] Audio circuitry 1660, speaker 1661, and microphone 1662 provide an audio interface between the user and terminal device 210. Audio circuitry 1660 converts received audio data into electrical signals, which are then transmitted to speaker 1661, where they are converted into sound signals for output. Terminal device 210 may also be equipped with volume buttons for adjusting the volume of the sound signal. On the other hand, microphone 1662 converts collected sound signals into electrical signals, which are received by audio circuitry 1660, converted into audio data, and then output to communication component 1610 for transmission to, for example, another terminal device 210, or to memory 1620 for further processing.

[0241] The Bluetooth module 1670 is used to interact with other Bluetooth devices that also have a Bluetooth module via the Bluetooth protocol. For example, a terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smartwatch) that also has a Bluetooth module through the Bluetooth module 1670, thereby exchanging data.

[0242] The processor 1680 is the control center of the terminal device, connecting various parts of the terminal through various interfaces and lines. It executes various functions and processes data by running or executing software programs stored in the memory 1620 and calling data stored in the memory 1620. In some embodiments, the processor 1680 may include one or more processing units; the processor 1680 may also integrate an application processor and a baseband processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the baseband processor mainly handles wireless communication. It is understood that the baseband processor may not be integrated into the processor 1680. In this application, the processor 1680 can run the operating system, applications, user interface display and touch response, as well as the training task generation method of this embodiment. Furthermore, the processor 1680 is coupled to the display unit 1630.

[0243] In some possible implementations, various aspects of the training task generation method provided in this application can also be implemented as a program product, which includes program code. When the program product is run on an electronic device, the program code causes the electronic device to perform the steps in the training task generation method according to the various exemplary embodiments of this application described above. For example, the electronic device can perform actions such as... Figure 3 The steps are shown in the figure.

[0244] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0245] The program product of the embodiments of this application may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a computing device. However, the program product of this application is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with a command execution system, apparatus, or device.

[0246] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with a command execution system, apparatus, or device.

[0247] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0248] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0249] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0250] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0251] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0252] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for generating training tasks, characterized in that, The method includes: Based on the training rules associated with the target object, obtain training data that is appropriate for the learning stage of the target object; Based on the training data, an initial training node path is constructed that is applicable to any object within the learning stage, wherein each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node. Based on the historical training data associated with the target object, the training nodes included in the initial training node path are filtered and the paths are reorganized to obtain the corresponding target training node path. Based on the target training node path and the first auxiliary key information database associated with the current environmental factors, a training task for the target object is generated; and if a change in the training status of the target object is detected, the target training node path is updated in conjunction with the second auxiliary key information database associated with the changed status, and the training task is regenerated.

2. The method as described in claim 1, characterized in that, The step of constructing an initial training node path that is universal for any object within the learning phase based on the training data includes: By classifying all the key knowledge information in the training data, the corresponding training nodes and the initial usage order between the training nodes are determined. The initial training node path is constructed based on each training node and the initial usage order among them.

3. The method as described in claim 1, characterized in that, The historical training data associated with the target object is used to filter and reorganize the training nodes included in the initial training node path to obtain the corresponding target training node path, including: Identify the target key knowledge information in the historical training data that meets preset conditions, and the training standards corresponding to the target key knowledge information; Based on the target key knowledge information and the corresponding training standards, the training nodes included in the initial training node path are screened and the paths are reorganized to generate the target training node path.

4. The method as described in claim 3, characterized in that, The target key knowledge information that meets the preset conditions includes at least one of the following: During the corresponding historical training process, the key knowledge information whose error rate reaches the first preset threshold; During the relevant historical training process, add key knowledge information with designated markers; During the corresponding historical training process, key knowledge information that has been searched up to the second preset threshold number of times.

5. The method as described in claim 3, characterized in that, The step of filtering and reorganizing the training nodes included in the initial training node path based on the target key knowledge information and the corresponding training standards to obtain the target training node path includes: Filter out the target training nodes that are associated with the target key knowledge information from among the various training nodes; Based on the training standards corresponding to the key knowledge information of the target, the difficulty labels of the associated target training nodes are determined. Based on the difficulty labels of each target training node and the initial usage order of each target training node in the general training path, the paths of each target training node are reorganized to determine the target usage order of each target training node. The target training node path is constructed based on each target training node and the target usage order among the target training nodes.

6. The method as described in claim 1, characterized in that, The step of generating a training task for the target object based on the target training node path and a first auxiliary key information database associated with current environmental factors includes: Based on the training style corresponding to the target audience, determine the media type corresponding to the training task; and Obtain a primary, auxiliary key information database related to current environmental factors; Based on the target training node path and the first auxiliary key information database, a training task for the media type is generated.

7. The method as described in claim 1, characterized in that, The method further includes: Based on the target training node path, a training activity sequence and training navigation for the target object are generated and displayed in the task interface; wherein... The training activity sequence is used to represent the order of training projects recommended according to the training style of the target object. The training navigation includes at least one of global navigation and local navigation recommended according to the training style of the target object. The global navigation includes a complete training system presented through a knowledge tree structure and the current training status of the target object. The local navigation includes the associated knowledge of the current training node presented through a knowledge concept graph structure.

8. The method according to any one of claims 1 to 7, characterized in that, If a change in the training status of the target object is detected, the target training node path is updated based on the second auxiliary key information database associated with the changed status, and the training task is regenerated, including: If a change in the training status of the target object is detected, a second auxiliary key information database associated with the changed training status is obtained; Based on the second auxiliary key information database, update the target training nodes in the target training node path and the target usage order between the target training nodes; Based on the updated target training node path, a new training task is generated for the target object.

9. A training task generation device, characterized in that, include: The data acquisition unit is used to obtain training data that is adapted to the learning stage of the target object according to the training rules associated with the target object. An initial construction unit is used to construct an initial training node path that is universal for any object in the learning stage based on the training data, wherein each training node represents a key knowledge information in the training data, and the initial training node path represents the initial usage order of each training node. The target construction unit is used to filter and reorganize the training nodes included in the initial training node path based on the historical training data associated with the target object, so as to obtain the corresponding target training node path. The task generation unit is configured to generate a training task for the target object based on the target training node path and a first auxiliary key information database associated with the current environmental factors; and if a change in the training status of the target object is detected, update the target training node path in conjunction with the second auxiliary key information database associated with the changed status, and regenerate the training task.

10. The apparatus as claimed in claim 9, characterized in that, The initial construction unit is specifically used for: By classifying all the key knowledge information in the training data, the corresponding training nodes and the initial usage order between the training nodes are determined. The initial training node path is constructed based on each training node and the initial usage order among them.

11. The apparatus as claimed in claim 9, characterized in that, The target construction unit is specifically used for: Identify the target key knowledge information in the historical training data that meets preset conditions, and the training standards corresponding to the target key knowledge information; Based on the target key knowledge information and the corresponding training standards, the training nodes included in the initial training node path are screened and the paths are reorganized to generate the target training node path.

12. The apparatus as claimed in claim 11, characterized in that, The target key knowledge information that meets the preset conditions includes at least one of the following: During the corresponding historical training process, the key knowledge information whose error rate reaches the first preset threshold; During the relevant historical training process, add key knowledge information with designated markers; During the corresponding historical training process, key knowledge information that has been searched up to the second preset threshold number of times.

13. The apparatus as claimed in claim 11, characterized in that, The target construction unit is specifically used for: Filter out the target training nodes that are associated with the target key knowledge information from among the various training nodes; Based on the training standards corresponding to the key knowledge information of the target, the difficulty labels of the associated target training nodes are determined. Based on the difficulty labels of each target training node and the initial usage order of each target training node in the general training path, the paths of each target training node are reorganized to determine the target usage order of each target training node. The target training node path is constructed based on each target training node and the target usage order among the target training nodes.

14. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of any of the methods described in claims 1 to 8.

15. A computer-readable storage medium, characterized in that, It includes program code that, when the storage medium is running on an electronic device, causes the electronic device to perform the steps of any of the methods described in claims 1 to 8.

Images