Intelligent note arrangement and review optimization method, system and device and storage medium

Abstract

The invention relates to an intelligent note arrangement and review optimization method, system and device and a storage medium. The method comprises the steps of receiving handwritten text data, performing real-time handwritten recognition on the handwritten text data, and converting the handwritten text data into standard text data; based on a natural language processing technology, performing text analysis on the standard text data to obtain text key features; classifying and extracting the text key features through a deep learning model, performing correlation analysis on the processed text key features by using a graph neural network, and constructing a logic relation graph of the text key features; performing visual layout according to the logic relation graph to obtain a corresponding mind map, and generating review data according to the text key features and the logic relation graph; and according to a preset time period, obtaining a user learning history, and based on the user learning history, adopting a reinforcement learning algorithm to adjust a learning path. The method has the effect of enhancing the pertinence and individuation of user learning.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent education, and in particular to an intelligent note organization and review optimization method, system, device and storage medium. Background Art

[0002] At present, with the popularity of electronic devices, more and more students and professionals use mobile devices such as tablets to take notes. Existing note-taking applications can provide basic text input and storage functions, but they usually lack the ability to deeply analyze and intelligently organize the content of notes, making it difficult to effectively extract key knowledge points from notes, and unable to automatically generate structured review materials or review suggestions based on learners' needs. As a result, students still need to manually organize their notes during review, wasting a lot of time and easily missing key content.

[0003] The above-mentioned existing technical solutions have the following defects: the existing note-organizing tools are difficult to provide intelligent content analysis and personalized review functions, so there is room for improvement. Summary of the invention

[0004] In order to enhance the pertinence and personalization of learning, the present application provides an intelligent note organization and review optimization method, system, device and storage medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: An intelligent note arrangement and review optimization method, the intelligent note arrangement and review optimization method comprising: Receiving handwritten text data, performing real-time handwriting recognition on the handwritten text data, and converting the handwritten text data into standard text data; Based on natural language processing technology, the standard text data is parsed to obtain key features of the text; The key features of the text are classified and extracted through a deep learning model, and a graph neural network is used to perform a correlation analysis on the processed key features of the text to construct a logical relationship graph of the key features of the text; Performing visual layout according to the logical relationship map to obtain a corresponding mind map, and generating review material data according to the key features of the text and the logical relationship map; The user learning history is obtained according to a preset time period, and based on the user learning history, a reinforcement learning algorithm is used to adjust the learning path.

[0006] By adopting the above technical solution, by receiving handwritten text data and converting it into standard text data, it is possible to quickly digitize handwritten notes, thereby improving the storage and subsequent processing efficiency of notes; by performing text analysis on standard text data based on natural language processing technology, it is possible to extract key features in the text, ensuring in-depth understanding and accurate processing of the text content; by classifying and extracting key features of the text through a deep learning model, and combining it with a graph neural network for correlation analysis, it is possible to automatically identify and process key knowledge points and their relationships in the notes, thereby constructing a more accurate and complete knowledge graph; by visually laying out and generating a mind map based on the logical relationship graph, it is possible to help users more intuitively understand and grasp the intrinsic relationship between knowledge points, thereby improving the efficiency of review and learning; by using a reinforcement learning algorithm to adjust the learning path based on the user's learning history, it is possible to dynamically optimize the learning content according to the user's learning progress and weak links, thereby achieving personalized learning support and improving review results.

[0007] In one example, the present application may be further configured as follows: based on the natural language processing technology, the standard text data is parsed to obtain key text features, specifically including: Performing syntactic analysis on the standard text data, identifying sentence structure and basic components, and generating a grammatical tree of the text; The standard text data is semantically understood based on the syntax tree, and special keywords such as concepts, terms, key phrases, etc. in the standard text data are extracted to obtain the key features of the text.

[0008] By adopting the above technical solution and performing syntactic analysis and semantic understanding on standard text data, we can deeply understand the structure and semantic information in the text, thereby providing more accurate and efficient data support for subsequent knowledge extraction and relationship analysis, and improving the level of intelligent text processing.

[0009] In one example, the present application may be further configured as follows: the classification and extraction of the key features of the text by the deep learning model specifically includes: Using a pre-trained deep learning model to extract key features of the text, obtain key information of the text, and classify the key information of the text; The classified key information of the text is analyzed and abstracted through a multi-level neural network to determine the learning priority of the key information of the text.

[0010] By adopting the above technical solution, the key features of the text are classified and extracted through a deep learning model, which can efficiently transform complex text data into structured knowledge information, thereby improving the accuracy and effectiveness of subsequent steps such as knowledge graph construction and review material generation. By analyzing and abstracting the classified key information through a multi-level neural network, it can ensure that the learning priority of knowledge points is reasonably arranged, thereby helping users to review and learn more efficiently.

[0011] In one example, the present application may be further configured as follows: the use of a graph neural network to perform a correlation analysis on the processed key features of the text and construct a logical relationship graph of the key features of the text, specifically including: The key information of the text is represented as a node, and the association relationship between different key information of the text is represented as an edge, so as to construct a basic knowledge graph; The basic knowledge graph is analyzed using a graph neural network to learn the interactions and relationships between the nodes and generate the logical relationship graph of the key features of the text.

[0012] By adopting the above technical solution and using graph neural networks to perform correlation analysis on key features of the text, the complex relationship between knowledge points can be accurately revealed, thereby constructing a knowledge graph that reflects the internal logic of the text; by representing key text information as nodes and their relationships as edges, the correlation between knowledge points can be intuitively displayed, providing a structured knowledge framework for subsequent review material generation and mind map presentation.

[0013] In one example, the present application may be further configured as follows: performing a visual layout according to the logical relationship map to obtain a corresponding mind map, and generating review material data according to the key features of the text and the logical relationship map, specifically including: Applying a graphical layout algorithm to visually arrange the nodes and edges in the logical relationship graph, and adaptively generating the mind map according to the size of the display area; Review summary information is generated according to the key features of the text, and related practice questions are generated based on the logical relationship map.

[0014] By adopting the above technical solution and applying a graphical layout algorithm to visualize the logical relationship map, the hierarchy and relationship between knowledge points can be intuitively displayed, thereby helping users to clearly understand the knowledge structure; by generating review summaries and practice questions based on the logical relationship map, users can be provided with targeted review materials, thereby improving review efficiency and helping students consolidate and deepen their understanding of knowledge points.

[0015] In one example, the present application may be further configured as follows: adjusting the learning path based on the user learning history using a reinforcement learning algorithm specifically includes: Analyzing the user's learning history using a reinforcement learning algorithm, calculating the degree of completion of different links in the user's learning history, and identifying weak links in the learning history; According to the weak links, corresponding review content is generated, and the priority and difficulty of the review content are adjusted.

[0016] By adopting the above technical solution and using reinforcement learning algorithms to analyze user learning histories, users' weak links can be accurately identified, thereby providing them with personalized learning paths; by adjusting the priority and difficulty of review content based on users' weak links, users can be ensured to focus on knowledge points that have not yet been mastered during review, thereby improving review effectiveness and learning efficiency.

[0017] The second object of the invention is achieved by the following technical solutions: An intelligent note arrangement and review optimization system, the intelligent note arrangement and review optimization system comprising: A handwriting data collection module, used to receive handwritten text data, perform real-time handwriting recognition on the handwritten text data, and convert the handwritten text data into standard text data; A text parsing module, used to parse the standard text data based on natural language processing technology to obtain key features of the text; A feature classification and extraction module is used to classify and extract the key features of the text through a deep learning model, and use a graph neural network to perform correlation analysis on the processed key features of the text to construct a logical relationship map of the key features of the text; A visual layout module, used to perform visual layout according to the logical relationship map, obtain a corresponding mind map, and generate review material data according to the key features of the text and the logical relationship map; The learning history analysis module is used to obtain the user's learning history according to a preset time period, and based on the user's learning history, use a reinforcement learning algorithm to adjust the learning path.

[0018] By adopting the above technical solution, by receiving handwritten text data and converting it into standard text data, it is possible to quickly digitize handwritten notes, thereby improving the storage and subsequent processing efficiency of notes; by performing text analysis on standard text data based on natural language processing technology, it is possible to extract key features in the text, ensuring in-depth understanding and accurate processing of the text content; by classifying and extracting key features of the text through a deep learning model, and combining it with a graph neural network for correlation analysis, it is possible to automatically identify and process key knowledge points and their relationships in the notes, thereby constructing a more accurate and complete knowledge graph; by visually laying out and generating a mind map based on the logical relationship graph, it is possible to help users more intuitively understand and grasp the intrinsic relationship between knowledge points, thereby improving the efficiency of review and learning; by using a reinforcement learning algorithm to adjust the learning path based on the user's learning history, it is possible to dynamically optimize the learning content according to the user's learning progress and weak links, thereby achieving personalized learning support and improving review results.

[0019] The third objective of the present application is achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned intelligent note organization and review optimization method when executing the computer program.

[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent note organization and review optimization method.

[0021] In summary, this application includes the following beneficial technical effects: 1. By receiving handwritten text data and converting it into standard text data, it is possible to quickly digitize handwritten notes, thereby improving the storage and subsequent processing efficiency of notes; by performing text analysis on standard text data based on natural language processing technology, it is possible to extract key features in the text, ensuring in-depth understanding and accurate processing of the text content; by classifying and extracting key features of the text through a deep learning model, and combining it with a graph neural network for correlation analysis, it is possible to automatically identify and process key knowledge points and their relationships in the notes, thereby building a more accurate and complete knowledge graph; by visually laying out and generating a mind map based on the logical relationship graph, it is possible to help users more intuitively understand and grasp the intrinsic relationship between knowledge points, thereby improving the efficiency of review and learning; by using a reinforcement learning algorithm to adjust the learning path based on the user's learning history, it is possible to dynamically optimize the learning content according to the user's learning progress and weak links, thereby achieving personalized learning support and improving the review effect; 2. Classify and extract key features of text through deep learning models, which can efficiently transform complex text data into structured knowledge information, thereby improving the accuracy and effectiveness of subsequent steps such as knowledge graph construction and review material generation; analyze and abstract the classified key information through multi-level neural networks, which can ensure that the learning priority of knowledge points is reasonably arranged, thereby helping users to review and learn more efficiently; 3. By using graph neural networks to perform correlation analysis on key features of the text, the complex relationship between knowledge points can be accurately revealed, thereby constructing a knowledge graph that reflects the internal logic of the text; by representing key text information as nodes and their relationships as edges, the correlation between knowledge points can be intuitively displayed, providing a structured knowledge framework for subsequent review material generation and mind map presentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a smart note arrangement and review optimization method in one embodiment of the present application; Figure 2 It is a flowchart for implementing step S20 in the intelligent note arrangement and review optimization method in one embodiment of the present application; Figure 3 It is a flowchart for implementing step S30 in the intelligent note arrangement and review optimization method in one embodiment of the present application; Figure 4 This is another implementation flow chart of step S30 in the intelligent note arrangement and review optimization method in one embodiment of the present application; Figure 5 It is a flowchart for implementing step S40 in the intelligent note arrangement and review optimization method in one embodiment of the present application; Figure 6It is a flowchart for implementing step S50 in the intelligent note arrangement and review optimization method in one embodiment of the present application; Figure 7 This is a principle block diagram of an intelligent note arrangement and review optimization system in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses an intelligent note arrangement and review optimization method, which specifically includes the following steps: S10: receiving handwritten text data, performing real-time handwriting recognition on the handwritten text data, and converting the handwritten text data into standard text data.

[0025] Specifically, when receiving handwritten text data, the user's handwritten content, including handwritten text, symbols, formulas, etc., is recorded through the touch screen of the tablet computer. When the user completes the handwriting input, the handwritten text is recognized in real time through the built-in high-precision handwriting recognition engine, and the handwriting input is converted into standard digital text data. The recognition process not only covers regular characters, but also includes complex mathematical symbols or special symbols, etc. The recognized text data can be subsequently edited, analyzed and processed.

[0026] S20: Based on natural language processing technology, standard text data is parsed to obtain key features of the text.

[0027] Specifically, when parsing standard text data, we first perform syntactic analysis to identify the main components of a sentence, such as subject, predicate, object, etc., and build a sentence structure based on these components. Then, by analyzing the vocabulary in the sentence, we identify key terms, concepts, and their contextual information in the text, and extract the core features of the text to provide structured input for subsequent processing.

[0028] S30: Classify and extract key features of the text through a deep learning model, and use a graph neural network to perform correlation analysis on the processed key features of the text to construct a logical relationship map of the key features of the text.

[0029] Specifically, a deep learning model is used to classify the key features of the text and extract valuable information from them, ensuring that each information unit is clearly classified. The relationship between these key features is then analyzed through a graph neural network, and the concepts and terms in the text are represented as nodes in the graph. The edges between the nodes represent the semantic connection between them. Through the propagation mechanism of the graph neural network, a logical relationship map of the key features of the text is generated, thereby establishing the intrinsic connection between various knowledge points.

[0030] S40: Perform visual layout according to the logical relationship map to obtain the corresponding mind map, and generate review material data according to the key features of the text and the logical relationship map.

[0031] Specifically, based on the logical relationship graph, a graphical layout algorithm is applied to arrange the nodes and edges in the graph to ensure that the generated graph can clearly display the hierarchical relationship and connection between knowledge points, thereby obtaining a mind map. At the same time, based on the knowledge points and their relationships extracted from the graph, review material data is generated, including summaries of relevant knowledge points and exercise questions, to help users concentrate on reviewing and consolidating knowledge.

[0032] S50: Obtain the user's learning history according to a preset time period, and adjust the learning path using a reinforcement learning algorithm based on the user's learning history.

[0033] Specifically, the user's learning history data is obtained through a preset cycle, including learning progress, reviewed knowledge points, completed exercises, etc. Subsequently, a reinforcement learning algorithm is used to evaluate the user's learning situation based on these learning history data, identify the knowledge points that have not been mastered, and adjust the learning path, giving priority to reviewing these weak links to ensure that the user can learn and review efficiently and systematically.

[0034] In one embodiment, if Figure 2 As shown, in step S20, based on natural language processing technology, the standard text data is parsed to obtain key features of the text, including: S21: Perform syntactic analysis on standard text data, identify sentence structure and basic components, and generate a grammatical tree for the text.

[0035] Specifically, through syntactic analysis algorithms such as dependency syntactic analysis, the standard text data is analyzed sentence by sentence, the subject, predicate, object and other sentence components of each sentence are identified, and the dependency relationship between these components is determined. The various elements in the sentence and the grammatical relationship between them are represented by a tree structure to generate a syntax tree. The syntax tree can help the system understand the deep structure of the text and then accurately analyze the meaning of the text.

[0036] S22: Perform semantic understanding on standard text data based on syntax trees, extract special keywords such as concepts, terms, and key phrases in the standard text data, and obtain key features of the text.

[0037] Specifically, the text is semantically understood through the syntax tree. First, the system identifies the key terms and concepts in the text, and classifies and annotates them. Then, it uses word vector models such as Word2Vec and GloVe to vectorize these concepts, and uses context analysis technology to identify other related keywords and phrases, generate a set containing the key features of the text, and further extract important information from the text as input for subsequent processing.

[0038] In one embodiment, if Figure 3 As shown, in step S30, the key features of the text are classified and extracted through the deep learning model, which specifically includes: S31: Use the pre-trained deep learning model to extract key features of the text, obtain key information of the text, and classify the key information of the text.

[0039] Specifically, using pre-trained deep learning models such as BERT or Transformer, we first extract key features from the text and convert the key information of the text into a vector representation. Then, we classify the key information according to preset classification criteria such as knowledge point categories, subject areas, etc., to ensure that the key information can be organized by category for subsequent review and learning tasks.

[0040] S32: The classified key information of the text is analyzed and abstracted through a multi-level neural network to determine the learning priority of the key information of the text.

[0041] Specifically, the key information of the classified text is processed through a multi-level neural network such as a deep neural network or a multi-layer LSTM. The information is abstracted through multi-level structures such as convolutional layers, pooling layers, and fully connected layers to extract more concise feature representations. The learning priority of each key information is determined based on the learning history and progress, and the corresponding learning path is generated according to the priority.

[0042] In one embodiment, if Figure 4 As shown, in step S30, the graph neural network is used to perform correlation analysis on the processed key features of the text, and a logical relationship graph of the key features of the text is constructed, which specifically includes: S33: Represent text key information as nodes, and represent the association between different text key information as edges to construct a basic knowledge graph.

[0043] Specifically, each key information in the text, such as concepts and terms, is used as a node in the graph. The relationships between each pair of knowledge points, such as contextual relationships, grammatical relationships, and dependency relationships, are connected through edges to construct a preliminary knowledge graph. The structure of the knowledge graph can effectively reflect the knowledge points in the text content and their relationships, providing a basis for subsequent analysis and learning paths.

[0044] S34: Use graph neural networks to analyze basic knowledge graphs, learn the interactions and relationships between nodes, and generate logical relationship graphs of key features of texts.

[0045] Specifically, the graph neural network analyzes the basic knowledge graph through an iterative propagation mechanism, and the feature information of the nodes is propagated through edge connections. The network adjusts the representation of the nodes according to factors such as the similarity between nodes and the connection density. Through the propagation of the graph neural network, the deep relationship between the nodes is learned, and a logical relationship graph containing the node relationships is generated, ultimately constructing a more accurate and effective knowledge graph.

[0046] In one embodiment, if Figure 5 As shown, in step S40, a visual layout is performed according to the logical relationship map to obtain a corresponding mind map, and review material data is generated according to the key features of the text and the logical relationship map, specifically including: S41: Apply a graphical layout algorithm to visually arrange the nodes and edges in the logical relationship graph, and adaptively generate a mind map based on the display area size.

[0047] Specifically, the nodes and edges in the logical relationship graph are arranged through a graphical layout algorithm. Layout algorithms such as force-directed algorithm, hierarchical layout algorithm or tree layout are used to ensure that the relationship between knowledge points can be clearly displayed. The nodes in the graph represent knowledge points, and the edges represent the connections between knowledge points. During layout, the algorithm will adaptively adjust the arrangement of the graphics according to the size of the display area to ensure the clarity and readability of the mind map, while avoiding node overlap and ensuring the optimization of the display effect.

[0048] S42: Generate review summary information based on key features of the text, and generate relevant practice questions based on the logical relationship graph.

[0049] Specifically, review summary information is generated based on the key features in the text. The review summary will extract the essence of each knowledge point and succinctly summarize its core content to help users quickly grasp the key points when reviewing. At the same time, based on the relationship between knowledge points in the logical relationship map, relevant practice questions are automatically generated. These questions are closely related to the user's weak links and knowledge points that need to be reviewed, aiming to help users consolidate what they have learned and deepen their understanding. The practice questions can be in different forms such as multiple-choice questions, fill-in-the-blank questions, short-answer questions, etc., and are highly targeted.

[0050] In one embodiment, if Figure 6 As shown, in step S50, based on the user's learning history, a reinforcement learning algorithm is used to adjust the learning path, specifically including: S51: Use reinforcement learning algorithm to analyze user learning history, calculate the completion degree of different links in the user learning history, and identify weak links in the learning history.

[0051] Specifically, the reinforcement learning algorithm analyzes the user's learning history data such as learned knowledge points, review progress, test scores, etc., evaluates the completion of each link in the learning process, calculates the mastery level of each knowledge point or learning module, and identifies weak links in the learning history by comparing the user's performance in different learning links. For example, if a certain knowledge point has been studied fewer times, or the accuracy rate in exercises is low, the system will mark these weak links as parts that need to be reviewed.

[0052] S52: Generate corresponding review content according to the weak links, and adjust the priority and difficulty of the review content.

[0053] Specifically, based on the identified weak links, review content related to these knowledge points is automatically generated, including detailed knowledge point analysis, review materials and related examples. The difficulty and priority of the review content will be dynamically adjusted according to the user's learning progress and historical feedback. For example, if a certain knowledge point is poorly mastered, the review frequency will be automatically increased and the difficulty of the review content will be increased to ensure that users can concentrate on intensive training on their weak links, thereby improving learning outcomes.

[0054] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] In one embodiment, a smart note organization and review optimization system is provided, and the smart note organization and review optimization system corresponds one-to-one to the smart note organization and review optimization method in the above embodiment. Figure 7 As shown, the intelligent note arrangement and review optimization system includes a handwriting data collection module, a text analysis module, a feature classification and extraction module, a visual layout module, and a learning history analysis module. The detailed description of each functional module is as follows: A handwriting data collection module is used to receive handwritten text data, perform real-time handwriting recognition on the handwritten text data, and convert the handwritten text data into standard text data; The text parsing module is used to parse standard text data based on natural language processing technology to obtain key features of the text; The feature classification and extraction module is used to classify and extract key features of texts through a deep learning model, and use a graph neural network to perform correlation analysis on the processed key features of texts to construct a logical relationship map of key features of texts; The visual layout module is used to perform visual layout according to the logical relationship map, obtain the corresponding mind map, and generate review material data according to the key features of the text and the logical relationship map; The learning history analysis module is used to obtain the user's learning history according to a preset time period, and based on the user's learning history, use the reinforcement learning algorithm to adjust the learning path.

[0056] Optionally, the text parsing module specifically includes: The syntax analysis submodule is used to perform syntax analysis on standard text data, identify sentence structures and basic components, and generate a syntax tree for the text; The semantic understanding submodule is used to perform semantic understanding on standard text data based on syntax trees, extract special keywords such as concepts, terms, and key phrases in standard text data, and obtain key features of the text.

[0057] Optionally, the feature classification and extraction module specifically includes: The feature extraction submodule is used to extract key features of the text using a pre-trained deep learning model to obtain key information of the text and classify the key information of the text; The feature analysis submodule is used to analyze and abstract the key information of the classified text through a multi-level neural network to determine the learning priority of the key information of the text.

[0058] The node construction submodule is used to represent the key information of the text as nodes, and the association between different key information of the text as edges to construct the basic knowledge graph; The graph analysis submodule is used to analyze the basic knowledge graph using a graph neural network, learn the interactions and relationships between nodes, and generate a logical relationship graph of key features of the text.

[0059] Optionally, the visual layout module specifically includes: The graphical layout submodule is used to apply the graphical layout algorithm to visually arrange the nodes and edges in the logical relationship graph, and to adaptively generate a mind map according to the display area size; The review material generation submodule is used to generate review summary information based on the key features of the text and to generate relevant practice questions based on the logical relationship graph.

[0060] Optional, learning history analysis module specifically includes: The completion calculation submodule is used to analyze the user's learning history using the reinforcement learning algorithm, calculate the completion of different links in the user's learning history, and identify the weak links in the learning history; The review path adjustment submodule is used to generate corresponding review content according to the weak links and adjust the priority and difficulty of the review content.

[0061] For the specific limitations of the intelligent note organization and review optimization system, please refer to the limitations of the intelligent note organization and review optimization method above, which will not be repeated here. Each module in the above-mentioned intelligent note organization and review optimization system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0062] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent note arrangement and review optimization method is implemented.

[0063] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Receiving handwritten text data, performing real-time handwriting recognition on the handwritten text data, and converting the handwritten text data into standard text data; Based on natural language processing technology, standard text data is parsed to obtain key features of the text; The key features of the text are classified and extracted through the deep learning model, and the graph neural network is used to analyze the correlation of the processed key features of the text to build a logical relationship map of the key features of the text; Perform visual layout according to the logical relationship map to obtain the corresponding mind map, and generate review material data based on the key features of the text and the logical relationship map; The user's learning history is obtained according to a preset time period, and based on the user's learning history, a reinforcement learning algorithm is used to adjust the learning path.

[0064] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Receiving handwritten text data, performing real-time handwriting recognition on the handwritten text data, and converting the handwritten text data into standard text data; Based on natural language processing technology, standard text data is parsed to obtain key features of the text; The key features of the text are classified and extracted through the deep learning model, and the graph neural network is used to analyze the correlation of the processed key features of the text to build a logical relationship map of the key features of the text; Perform visual layout according to the logical relationship map to obtain the corresponding mind map, and generate review material data based on the key features of the text and the logical relationship map; The user's learning history is obtained according to a preset time period, and based on the user's learning history, a reinforcement learning algorithm is used to adjust the learning path.

[0065] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0066] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0067] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent note arrangement and review optimization method, characterized in that: The intelligent note arrangement and review optimization method comprises: Receiving handwritten text data, performing real-time handwriting recognition on the handwritten text data, and converting the handwritten text data into standard text data; Based on natural language processing technology, the standard text data is parsed to obtain key features of the text; The key features of the text are classified and extracted through a deep learning model, and a graph neural network is used to perform a correlation analysis on the processed key features of the text to construct a logical relationship graph of the key features of the text; Performing visual layout according to the logical relationship map to obtain a corresponding mind map, and generating review material data according to the key features of the text and the logical relationship map; The user learning history is obtained according to a preset time period, and based on the user learning history, a reinforcement learning algorithm is used to adjust the learning path.

2. The intelligent note arrangement and review optimization method according to claim 1, characterized in that: Based on the natural language processing technology, the standard text data is parsed to obtain key text features, which specifically include: Performing syntactic analysis on the standard text data, identifying sentence structure and basic components, and generating a grammatical tree of the text; The standard text data is semantically understood based on the syntax tree, and special keywords such as concepts, terms, key phrases, etc. in the standard text data are extracted to obtain the key features of the text.

3. The intelligent note arrangement and review optimization method according to claim 1, characterized in that: The classification and extraction of the key features of the text by the deep learning model specifically includes: Using a pre-trained deep learning model to extract key features of the text, obtain key information of the text, and classify the key information of the text; The classified key information of the text is analyzed and abstracted through a multi-level neural network to determine the learning priority of the key information of the text.

4. The intelligent note arrangement and review optimization method according to claim 1, characterized in that: The method of using a graph neural network to perform a correlation analysis on the processed key features of the text and constructing a logical relationship graph of the key features of the text specifically includes: The key information of the text is represented as a node, and the association relationship between different key information of the text is represented as an edge, so as to construct a basic knowledge graph; The basic knowledge graph is analyzed using a graph neural network to learn the interactions and relationships between the nodes and generate the logical relationship graph of the key features of the text.

5. The intelligent note arrangement and review optimization method according to claim 4, characterized in that: The visual layout is performed according to the logical relationship map to obtain a corresponding mind map, and the review material data is generated according to the key features of the text and the logical relationship map, specifically including: Applying a graphical layout algorithm to visually arrange the nodes and edges in the logical relationship graph, and adaptively generating the mind map according to the size of the display area; Review summary information is generated according to the key features of the text, and related practice questions are generated based on the logical relationship map.

6. The intelligent note arrangement and review optimization method according to claim 1, characterized in that: The method of adjusting the learning path based on the user's learning history by using a reinforcement learning algorithm specifically includes: Analyzing the user's learning history using a reinforcement learning algorithm, calculating the degree of completion of different links in the user's learning history, and identifying weak links in the learning history; According to the weak links, corresponding review content is generated, and the priority and difficulty of the review content are adjusted.

7. An intelligent note arrangement and review optimization system, characterized in that: The intelligent note arrangement and review optimization system includes: A handwriting data collection module, used to receive handwritten text data, perform real-time handwriting recognition on the handwritten text data, and convert the handwritten text data into standard text data; A text parsing module, used to parse the standard text data based on natural language processing technology to obtain key features of the text; A feature classification and extraction module is used to classify and extract the key features of the text through a deep learning model, and use a graph neural network to perform correlation analysis on the processed key features of the text to construct a logical relationship map of the key features of the text; A visual layout module, used to perform visual layout according to the logical relationship map, obtain a corresponding mind map, and generate review material data according to the key features of the text and the logical relationship map; The learning history analysis module is used to obtain the user's learning history according to a preset time period, and based on the user's learning history, use a reinforcement learning algorithm to adjust the learning path.

8. The intelligent note arrangement and review optimization system according to claim 7, characterized in that: The text parsing module specifically includes: A syntax analysis submodule, used to perform syntax analysis on the standard text data, identify sentence structures and basic components, and generate a syntax tree of the text; The semantic understanding submodule is used to perform semantic understanding on the standard text data based on the syntax tree, extract special keywords such as concepts, terms and key phrases in the standard text data, and obtain the key features of the text.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent note organization and review optimization method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent note organization and review optimization method as described in any one of claims 1 to 6 are implemented.

Images