Blackboard intelligent display control method, device, equipment and storage medium

Abstract

This application relates to a blackboard intelligent display control method, device, equipment, and storage medium, belonging to the technical field of intelligent interactive display. The method includes: acquiring the current display content information and real-time input handwriting information of the blackboard display area; determining whether there is an overlapping area between the handwriting information and the current display content information; if there is no overlapping area, directly displaying the handwriting on the blackboard display area; if there is an overlapping area and it is not new content, merging the handwriting information with the current display content information; if it is new content, executing a space organization strategy to display the handwriting information in the released display area; generating and storing association mapping information, which is the correspondence between the handwriting information and compressed or migrated historical writing content blocks. This application improves the continuity of teaching and learning.

Description

Technical Field

[0001] This application relates to the technical field of intelligent interactive display, and in particular to a blackboard intelligent display control method, device, equipment and storage medium. Background Technology

[0002] With the widespread adoption of interactive whiteboards and smart blackboards in education, traditional chalk writing is gradually being replaced by electronic writing. Existing smart blackboards typically feature touch writing, content storage, and multimedia playback capabilities, providing convenience for teaching.

[0003] During the teaching process, especially when deriving scientific derivations or summarizing humanities knowledge points, teachers often need to write extensively and continuously on the blackboard. Limited by the physical size of the blackboard display, once the writing fills the screen, teachers have to interrupt their teaching flow and manually clear the screen, turn pages, or zoom to create new writing space. This frequent manual intervention not only disrupts the continuity of the lesson but also distracts students.

[0004] Therefore, there are already methods to solve the problem of insufficient space by automatic page turning or global scaling. However, simple automatic page turning will cause the historical blackboard content to disappear, making it difficult for students to compare the knowledge before and after. While global scaling can provide new display space, the font size will also shrink, making it difficult for students in the back row to read and affecting the teaching effect.

[0005] Therefore, there is an urgent need for a blackboard intelligent display control method that can achieve intelligent management of blackboard display space without interrupting the continuity of teaching, while ensuring the clear readability of the blackboard content and convenient recall. Summary of the Invention

[0006] To improve the continuity of teaching and learning, this application provides a blackboard intelligent display control method, device, equipment, and storage medium.

[0007] Firstly, this application provides a blackboard intelligent display control method, which adopts the following technical solution: Obtain information on the current displayed content and real-time handwriting input in the blackboard display area; Determine whether there is an overlapping area between the handwriting information and the currently displayed content information; If there is no overlapping area, the handwriting will be displayed directly on the blackboard display area; If there are overlapping areas, the writing characteristics of the handwriting information are analyzed to determine whether the handwriting information belongs to newly added content; If it is not new content, then the handwriting information is determined to be a correction or supplement to the currently displayed content information in the overlapping area, and the handwriting information is merged with the currently displayed content information for display. If it is newly added content, then the space organization strategy will be executed to display the handwriting information in the released display area; The space organization strategy includes: Identify at least one target written content block associated with the overlapping region; Determine the display priority of each target written content block; Based on the display priority, at least one of the target written content blocks is compressed for display or moved to a temporary storage area to free up the display area; Generate and store association mapping information, which is the correspondence between the handwriting information and the compressed or migrated historical writing content blocks.

[0008] By adopting the above technical solution, the problem of traditional smart blackboards being interrupted by manual operation, lost historical content, or illegible fonts when there is insufficient writing space is solved by determining whether the handwriting is new content and implementing targeted space organization strategies. The solution can dynamically adjust the layout of the displayed content to ensure that new content has display space. At the same time, through compression, migration, and association mapping, historical content can be preserved and traced, thereby improving the continuity of teaching and the readability of the content.

[0009] Furthermore, the analysis of the writing characteristics of the handwriting information to determine whether the handwriting information belongs to newly added content includes: Obtain at least one segment of historical handwriting information that is temporally adjacent to the handwriting information; Semantic recognition is performed on the handwriting information and the historical handwriting information respectively, and their respective semantic features are extracted; Calculate the semantic correlation degree between the semantic features of the written handwriting information and the semantic features of the historical handwriting information; Calculate the spatial continuity coefficient between the written handwriting information and the historical handwriting information; If the semantic relevance exceeds a preset first threshold and the spatial continuity coefficient exceeds a preset second threshold, then the handwriting information is determined to be newly added content. If the semantic relevance does not exceed the first threshold, then the handwriting information is determined not to be new content; If the semantic relevance exceeds the first threshold but the spatial continuity coefficient does not exceed the second threshold, then the handwriting information is determined to be a semantic supplement or annotation to the historical handwriting information, and the handwriting information is determined not to be new content. The calculation method for the spatial continuity coefficient includes: Obtain the center point coordinate sequence of the written handwriting information and the center point coordinate sequence of the historical handwriting information; The writing direction vector of the historical handwriting information is determined, and the writing direction vector is obtained by linear fitting the coordinate sequence of the center point; Calculate the spatial continuity coefficient of the written handwriting information relative to the historical handwriting information, wherein the spatial continuity coefficient is a weighted sum of the distance component, the direction component, and the alignment component; The distance component The calculation method is as follows: ;in, The minimum Euclidean distance between the written handwriting information and the historical handwriting information is given. This is the preset maximum effective extension distance; The directional component The calculation method is as follows: ;in, The angle between the overall extension direction of the handwriting information and the writing direction vector of the historical handwriting information is given by linearly fitting the coordinate sequence. The alignment component The calculation method is as follows: ;in, This refers to the baseline position of the line containing the handwriting information. This represents the baseline position of the line containing the historical handwriting information. This is the preset maximum baseline offset tolerance.

[0010] By employing the aforementioned technical solutions, and integrating semantic relevance and spatial continuity coefficients, electronic devices accurately identify writing intentions, distinguishing between content continuity and entirely new content. This accurate judgment leads to more rational spatial organization, avoids misoperations, ensures clear and coherent display, optimizes the writing and reading experience, and enhances interactive efficiency and intelligence.

[0011] Further, calculating the semantic correlation between the semantic features of the written handwriting information and the semantic features of the historical handwriting information includes: Semantic recognition is performed on the handwriting information and the historical handwriting information respectively, and their respective keyword sets and sentence structure features are extracted; Based on the keyword set, a first relevance component is determined, which is positively correlated with the number of keywords that appear in both keyword sets. Based on the sentence structure features, a second correlation component is determined. The second correlation component is determined according to the relation markers that co-occur in the handwriting information and the historical handwriting information. Different relation markers correspond to different preset weights. The second correlation component is positively correlated with the sum of the weights of the co-occurring relation markers. Based on the positions of the handwriting information and the historical handwriting information in a preset knowledge graph, a third correlation component is determined. The third correlation component is negatively correlated with the shortest path length in the knowledge graph between the first knowledge node corresponding to the handwriting information and the second knowledge node corresponding to the historical handwriting information. If the first knowledge node and the second knowledge node are the same node, the third correlation component takes a preset maximum value. If there is no path connecting the first knowledge node and the second knowledge node in the knowledge graph, the third correlation component takes a preset minimum value. Based on the preset first weight, second weight, and third weight, the first correlation component, the second correlation component, and the third correlation component are weighted and fused to obtain the semantic correlation.

[0012] By employing the aforementioned technical solutions, semantic relevance calculation comprehensively considers keyword overlap, sentence structure similarity, and deep knowledge graph connections, accurately capturing semantic relationships between handwriting from multiple dimensions. This method avoids misjudgments from simple matching, improves the accuracy of new content recognition, makes space organization strategies more intelligent and reasonable, and optimizes display management and user experience.

[0013] Furthermore, the step of analyzing the writing characteristics of the handwriting information and determining whether the handwriting information belongs to newly added content also includes: Acquire voice input information that is time-synchronized with the handwriting information; The voice input information is subjected to speech recognition and converted into text information; Extract speech keywords from the text information; Semantic matching is performed between the spoken keywords and the historical written content blocks associated with the overlapping areas to obtain the matching degree, including: Semantic recognition is performed on the historical writing content blocks to extract a set of historical keywords; If the voice keyword is exactly the same as any historical keyword in the historical keyword set, it is recorded as a complete match; If the voice keyword is a synonym or near-synonym of any historical keyword in the set of historical keywords, it is recorded as an approximate match. Calculate the matching degree based on the number of exact matches and the number of near matches: Matching score = (Number of exact matches × First weight + Number of near matches × Second weight) / Total number of voice keywords; where the first weight is greater than the second weight; If the matching degree is lower than the preset second threshold, the handwriting information is determined to be newly added content. If the matching degree is higher than the preset second threshold, the handwriting information is not considered new content.

[0014] By adopting the above technical solution, when the semantic correlation between voice and historical content is low, the electronic device identifies it as new content and triggers spatial organization; when the correlation is high, it is determined to be correction and supplementation, avoiding erroneous organization. This multimodal mechanism significantly improves the accuracy of judgment in complex scenarios and solves the problem of difficulty in distinguishing content intent based solely on handwriting.

[0015] Further, determining the display priority of each of the target written content blocks includes: In response to the input of detected current handwriting information, the target writing content blocks are arranged in order of writing time from latest to earliest, and a first priority list for compression and display is generated; Obtain the current teaching knowledge point corresponding to the current handwriting information; Calculate the content relevance score between each target writing content block and the currently taught knowledge point; Arrange the target written content blocks in the first priority list in descending order according to the corresponding content relevance scores to obtain a relevance sequence. Then, generate a second priority list of the first preset number of target written content blocks in the relevance sequence to be migrated to the temporary storage area. In response to the completion of writing the current handwriting information, the second priority list is cleared, and the first priority list is updated according to the updated writing time information.

[0016] By adopting the above technical solution, the space organization strategy first sorts content by writing time to ensure that recent content is processed first, and then prioritizes highly relevant content based on its relevance to the current knowledge point for quick retrieval. After writing is completed, the priority is dynamically updated to ensure that the display organization always conforms to the teaching logic, improving teaching continuity and user experience.

[0017] Further, the calculation of the content relevance score between each of the target written content blocks and the currently taught knowledge point includes: Semantic recognition is performed on the target written content block to extract historical keyword sets, historical semantic vectors, and historical knowledge nodes; Semantic recognition is performed on the currently taught knowledge points to extract the current keyword set, the current semantic vector, and the current knowledge node; Based on the historical keyword set and the current keyword set, calculate the first relevance component, including: Count the number of keywords that appear together in the historical keyword set and the current keyword set; Count the total number of keywords contained in the historical keyword set and the current keyword set; The first relevance component is obtained by dividing the number of co-occurring keywords by the total number of keywords. Based on the historical semantic vector and the current semantic vector, a second relevance component is calculated, including: Calculate the dot product between the historical semantic vector and the current semantic vector; Calculate the product of the magnitude of the historical semantic vector and the magnitude of the current semantic vector; Divide the dot product by the product of the modulus to obtain the cosine similarity between the historical semantic vector and the current semantic vector, which is used as the second relevance component. Based on the positions of the historical knowledge nodes and the current knowledge nodes in the preset knowledge graph, a third relevance component is calculated, including: Obtain the shortest path length between the historical knowledge node and the current knowledge node in the knowledge graph; If the historical knowledge node and the current knowledge node are the same node, then the third relevance component is 1; If there is no path connecting the historical knowledge node and the current knowledge node in the knowledge graph, then the third relevance component takes the preset minimum value. If the historical knowledge node and the current knowledge node are different nodes and there is a connection path in the knowledge graph, then the third correlation component is calculated in a way that is negatively correlated with the shortest path length; Based on the preset first weight, second weight, and third weight, the first relevance component, the second relevance component, and the third relevance component are weighted and fused to obtain the content relevance score.

[0018] By employing the aforementioned technical solution, content relevance is calculated across three dimensions: keyword matching, semantic vector similarity, and knowledge graph association. A weighted fusion method is then used to obtain a more comprehensive relevance score. This approach enables electronic devices to accurately identify the content most relevant to the current knowledge point, allowing for reasonable compression or relocation during spatial organization to ensure the retention of key content and improve teaching efficiency and knowledge coherence.

[0019] Furthermore, after generating and storing the association mapping information, the process also includes: Obtain the first knowledge point corresponding to the handwriting information, and at least one second knowledge point corresponding to the compressed or migrated historical writing content block; Based on the association mapping information, establish a teaching association relationship between the first knowledge point and the second knowledge point; The teaching associations are updated to the preset knowledge graph to enrich the connection paths between knowledge points in the knowledge graph; In response to subsequent backtracking operations on the first or second knowledge point, based on the updated knowledge graph, extended knowledge points related to the currently taught content are recommended for the user to choose from.

[0020] By adopting the above technical solution, handwriting association mapping is upgraded to knowledge point teaching association and the knowledge graph is dynamically updated, enriching the connection paths of knowledge points in real time. When users review their work, electronic devices intelligently recommend relevant extended knowledge, solving the problem of insufficient deep association in traditional blackboards, providing personalized learning paths, promoting the integration of knowledge, and enhancing teaching effectiveness.

[0021] Secondly, this application provides a blackboard intelligent display control device, which adopts the following technical solution: The handwriting information acquisition module is used to acquire the current display content information and real-time input handwriting information of the blackboard display area; The overlapping area determination module is used to determine whether there is an overlapping area between the handwriting information and the currently displayed content information; The first handwriting display module is used to directly display the written handwriting on the blackboard display area when it is determined that there is no overlapping area. The content judgment module is used to analyze the writing characteristics of the handwriting information when there are overlapping areas, and to determine whether the handwriting information belongs to new content. The second handwriting display module is used to determine that the handwriting information is a correction or supplement to the currently displayed content information in the overlapping area when it is determined that it is not new content, and to merge the handwriting information with the currently displayed content information for display. The space organization strategy execution module is used to execute the space organization strategy when it is determined that the content is newly added, and to display the handwriting information in the released display area. The space organization strategy includes: Identify at least one target written content block associated with the overlapping region; Determine the display priority of each target written content block; Based on the display priority, at least one of the target written content blocks is compressed for display or moved to a temporary storage area to free up the display area; A storage module is used to generate and store association mapping information, which is the correspondence between the handwriting information and the compressed or migrated historical writing content blocks.

[0022] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device, comprising: At least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: perform the method as described in any one of the first aspects.

[0023] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method as described in any one of the first aspects.

[0024] For a detailed description of the second to fourth aspects of the present invention and their various implementations, please refer to the detailed description in the first aspect and its various implementations; and for a detailed description of the beneficial effects of the second to fourth aspects and their various implementations, please refer to the beneficial effect analysis in the first aspect and its various implementations, which will not be repeated here.

[0025] In summary, this application includes at least one of the following beneficial technical effects: 1. By determining whether the handwriting is new content and implementing targeted space organization strategies, the traditional smart blackboard solves the problems of interrupted teaching continuity, loss of historical content, or illegible font size when there is insufficient writing space. It can dynamically adjust the layout of the displayed content to ensure that new content has display space. At the same time, through compression, migration, and association mapping, historical content can be preserved and traced, thereby improving the continuity of teaching and the readability of the content. 2. By combining semantic relevance and spatial continuity coefficients, electronic devices accurately identify writing intentions, distinguish between content continuation and new content, and make accurate judgments to make spatial organization more reasonable. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating the blackboard intelligent display control method in the embodiments of this application.

[0027] Figure 2 This is a structural block diagram of the blackboard intelligent display control device in the embodiments of this application.

[0028] Figure 3 This is a structural block diagram of the electronic device in the embodiments of this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0031] This application discloses a method for intelligent blackboard display control. (Refer to...) Figure 1 This process is executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster consisting of multiple physical servers, a distributed electronic device, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, desktop computer, etc., but is not limited to these. (Steps S101 to S107)

[0032] Step S101: Obtain the current display content information and real-time input handwriting information of the blackboard display area.

[0033] Specifically, the blackboard display area refers to the display interface used to present teaching content and handwriting. This area can be the screen of an interactive whiteboard or the display panel of a smart blackboard. The currently displayed content information refers to the teaching materials such as text, graphics, and symbols that already exist and are being presented on the blackboard display area. The handwriting information refers to the handwriting trajectory data that the user inputs in real time on the blackboard display area using a writing tool. This information includes attributes such as stroke coordinates, timestamps, and pen pressure.

[0034] The currently displayed content can be obtained by periodically capturing the screen of the blackboard display area or by directly reading the display cache data. Handwriting information can be provided by the touch screen controller or digitizer, which includes data such as the coordinate sequence of strokes and timestamps.

[0035] Step S102: Determine whether there is an overlapping area between the handwriting information and the currently displayed content information.

[0036] Specifically, the overlapping area refers to the region where the real-time input handwriting information intersects or overlaps with the existing content displayed on the blackboard display area. This determination can be made by comparing the bounding box of the newly input handwriting information with the bounding boxes of existing content elements on the blackboard display area. If there is spatial intersection, it is considered that an overlapping area exists. Alternatively, a pixel-level comparison can be performed to determine whether the new handwriting covers the existing content.

[0037] If there is no overlapping area, proceed to step S103: display the handwriting directly on the blackboard display area; at this time, the new handwriting is directly rendered into the display cache and will not affect or cover any existing content.

[0038] If there are overlapping areas, proceed to step S104: analyze the writing characteristics of the handwriting information to determine whether the handwriting information is new content.

[0039] Specifically, this includes steps S104-11 to S104-17:

[0040] Step S104-11: Obtain at least one segment of historical handwriting information that is temporally adjacent to the handwriting information.

[0041] Specifically, the electronic device maintains a buffer or log of recent handwriting information and sorts it according to timestamps. When new handwriting information is received, the electronic device retrieves historical handwriting information completed within a preset time window from the buffer. "Temporally adjacent" can be determined based on the interval between the end time of the handwriting and the start time of the current handwriting.

[0042] Step S104-12: Perform semantic recognition on the handwriting information and historical handwriting information respectively, and extract their respective semantic features.

[0043] Specifically, semantic recognition can employ various natural language processing techniques. For example, for handwritten text, it can first be converted into text using optical character recognition (OCR) technology, and then the text can be converted into semantic vectors using word embedding models (such as Word2Vec, GloVe, BERT, etc.). Semantic vectors can capture the deep meaning of words or phrases. For non-textual handwriting (such as graphics and symbols), image recognition or pattern recognition techniques can be used to map it to predefined semantic categories or concepts.

[0044] Steps S104-13: Calculate the semantic correlation between the semantic features of the written handwriting information and the semantic features of the historical handwriting information. This includes steps S11 to S15.

[0045] Step S11: Perform semantic recognition on the handwriting information and historical handwriting information respectively, and extract their respective keyword sets and sentence structure features.

[0046] Specifically, when performing semantic recognition, electronic devices can employ natural language processing (NLP) techniques to analyze handwriting and historical handwriting information, transforming it into machine-understandable semantic representations. Keyword extraction can utilize algorithms such as lexical analysis, TF-IDF (Term Frequency-Inverse Document Frequency), and TextRank to identify the most representative words from the text. Sentence structure features can be acquired using syntactic analyzers to identify subject-verb-object structures, modification relationships, and parallel relationships within sentences.

[0047] Step S12: Based on the keyword set, determine the first relevance component. The first relevance component is positively correlated with the number of keywords that appear in both keyword sets.

[0048] Specifically, the first relevance component aims to reflect the degree of overlap between two handwriting entries in terms of topic vocabulary. This can be achieved by counting the number of common keywords in the keyword sets of both the handwriting and historical handwriting information, and comparing this number with the total number of keywords in both sets. For example, the number of common keywords can be directly used as the component value. The more common keywords, the closer the two handwriting entries are in their core concepts, and the higher the first relevance component value.

[0049] Step S13: Based on sentence structure features, determine the second correlation component. The second correlation component is determined based on the relation markers that co-occur in the handwriting information and historical handwriting information. Different relation markers correspond to different preset weights. The second correlation component is positively correlated with the sum of the weights of the co-occurring relation markers.

[0050] Specifically, the second relevance component is used to assess the similarity between two handwriting entries in terms of expression and logical relationship. This can be achieved by identifying relational markers in the text that indicate logical relationships, transitions, causal relationships, parallel relationships, etc., such as "because," "therefore," "but," "moreover," "for example," etc. Different relational markers can be assigned different weights based on their importance in semantic association; for example, a strong causal relationship such as "because-therefore" may be given a higher weight.

[0051] When these relational markers appear together in both handwriting and historical handwriting information, their corresponding weights are summed to obtain a second correlation component. This second correlation component is positively correlated with the sum of the weights of the co-occurring relational markers.

[0052] Step S14: Based on the positions of handwriting information and historical handwriting information in the preset knowledge graph, determine the third correlation component. The third correlation component is negatively correlated with the shortest path length of the first knowledge node corresponding to the handwriting information and the second knowledge node corresponding to the historical handwriting information in the knowledge graph. If the first knowledge node and the second knowledge node are the same node, the third correlation component takes the preset maximum value. If there is no path connecting the first knowledge node and the second knowledge node in the knowledge graph, the third correlation component takes the preset minimum value.

[0053] Specifically, the third correlation component is used to measure the deep association between two handwriting entries within the knowledge system. First, through entity recognition and linking technologies, concepts and entities in the text are matched with nodes in the knowledge graph, mapping handwriting information and historical handwriting information to predefined knowledge nodes in the knowledge graph. Then, the shortest path length between these two knowledge nodes in the knowledge graph is calculated. The shorter the path, the stronger the association between the two knowledge points, and the higher the value of the third correlation component.

[0054] If two handwriting entries correspond to the same node in the knowledge graph, it indicates that they point to the exact same knowledge point, and the third correlation component takes the preset maximum value (e.g., 1). If there is no path connecting these two nodes in the knowledge graph, it is considered that there is no direct knowledge connection between them, and the third correlation component takes the preset minimum value (e.g., 0). The third correlation component is negatively correlated with the shortest path length.

[0055] Step S15: Based on the preset first weight, second weight, and third weight, perform weighted fusion on the first relevance component, the second relevance component, and the third relevance component to obtain the semantic relevance.

[0056] Step S104-14: Calculate the spatial continuity coefficient between the written handwriting information and the historical handwriting information.

[0057] The calculation method for the spatial continuity coefficient includes (steps S21 to S23):

[0058] Step S21: Obtain the center point coordinate sequence of the handwriting information and the center point coordinate sequence of the historical handwriting information.

[0059] Specifically, for handwriting information, the two-dimensional coordinates of its trajectory points are extracted according to a preset sampling frequency, and noise reduction processing is performed on each trajectory point. Then, the center point of every two adjacent trajectory points is calculated, or for complex handwriting composed of multiple strokes, the geometric center of its minimum bounding rectangle is calculated, thus obtaining the center point coordinate sequence of the handwriting information. Where m is the number of center points, each All are two-dimensional coordinate vectors.

[0060] Similarly, at least one segment of historical handwriting information that is temporally adjacent to the written handwriting information is retrieved from the storage unit and processed in the same way to obtain the center point coordinate sequence of the historical handwriting information. Where n is the number of center points, each All are two-dimensional coordinate vectors.

[0061] Step S22: Determine the writing direction vector of the historical handwriting information. The writing direction vector is obtained by linear fitting of the center point coordinate sequence.

[0062] Specifically, the coordinate sequence of the center point Q is linearly fitted using the least squares method to obtain the fitted line L: y=kx+b. The direction vector of this fitted line is taken as the writing direction vector D=(1,k), and normalized to obtain the unit direction vector.

[0063] It should be noted that when the historical handwriting is multi-line text or complex graphics, the coordinate sequence of only the last complete content block written (such as the last line of text or the last mathematical formula) can be fitted to more accurately reflect the writing direction of its ending position.

[0064] Step S23: Calculate the spatial continuity coefficient of the written handwriting information relative to the historical handwriting information. The spatial continuity coefficient is a weighted sum of the distance component, the direction component, and the alignment component.

[0065] Distance component The calculation method is as follows: ;in, This represents the minimum Euclidean distance between written handwriting information and historical handwriting information. This is the preset maximum effective extension distance.

[0066] Specifically, This can be obtained by calculating the shortest distance between the bounding box of the new handwriting and the bounding box of the historical handwriting. It's an empirical value; for example, it can be set as a percentage of the width of the blackboard display area, or determined based on average character spacing and line spacing. When approaching 0, Approaching 1 indicates a very close distance; when Greater than hour, A value of 0 indicates that the distance is too great and there is no spatial continuity. This component quantifies the physical proximity of the old and new handwriting.

[0067] Directional components The calculation method is as follows: ;in, The angle between the overall extension direction of the written handwriting information and the writing direction vector of the historical handwriting information is given. The overall extension direction of the written handwriting information is obtained by linear fitting of the coordinate sequence.

[0068] Specifically, similar to historical handwriting, the overall direction of new handwriting can also be obtained by linearly fitting a sequence of coordinates of its center point. Then, the angle between these two direction vectors is calculated. . This component ensures that positive values ​​are contributed only when the directions are roughly the same or smoothly continuous, avoiding misjudging reverse writing as continuous. This component assesses the consistency of writing direction between new and old handwriting.

[0069] Align components The calculation method is as follows: ;in, This is the baseline position of the line containing the handwriting information. This represents the baseline position of the line containing the historical handwriting information. This is the preset maximum baseline offset tolerance.

[0070] Specifically, the baseline position can be determined by the bottom edge of the handwriting. This is a tolerance parameter; for example, it can be set to half the average row height. When and When very close, A value close to 1 indicates good alignment; when the baseline offset is close to 1, the alignment is good. Exceed hour, A value of 0 indicates poor alignment. Ensure that the subtrahend does not exceed 1 when the offset is too large, resulting in... It is negative. This component is specifically used to evaluate the vertical alignment of the text handwriting.

[0071] After the distance component, orientation component, and alignment component are calculated individually, they are weighted and summed according to preset weights to obtain the final spatial continuity coefficient. These weights can be adjusted and optimized according to actual application scenarios and user writing habits.

[0072] Step S104-15: If the semantic relevance exceeds the preset first threshold and the spatial continuity coefficient exceeds the preset second threshold, then the handwriting information is determined to be newly added content.

[0073] Specifically, the preset first and second thresholds can be set through machine learning model training or expert experience. When the semantic relevance is greater than 0.7 and the spatial continuity coefficient is greater than 0.8, the electronic device can determine it as new content. This indicates that the new handwriting is highly continuous with the historical content both semantically and spatially, and should be considered as new content requiring independent space.

[0074] Step S104-16: If the semantic relevance does not exceed the first threshold, then it is determined that the handwriting information does not belong to the newly added content.

[0075] Specifically, if the calculated semantic relevance is lower than a preset first threshold, the electronic device determines that it is not new content, that is, it is not new content that requires independent space, but rather a correction or supplement to the currently displayed content in the overlapping area.

[0076] Step S104-17: If the semantic relevance exceeds the first threshold but the spatial continuity coefficient does not exceed the second threshold, then the handwriting information is determined to be a semantic supplement or annotation to the historical handwriting information, and the handwriting information is determined not to be new content.

[0077] Specifically, when semantic relevance is high (e.g., above 0.7) but spatial continuity is low (e.g., below 0.5), electronic devices can further analyze the type of handwriting, such as whether it is an arrow, a circle, etc., to confirm whether it is a supplement or annotation. For example, if the handwriting is a circle or underline, even if the semantic relevance is high but the spatial continuity is low, it should be considered a supplement to the existing content.

[0078] However, relying solely on the characteristics of the handwriting itself can sometimes make it difficult to accurately distinguish whether a user wants to correct or supplement existing content or write entirely new content in overlapping areas. This may lead to misjudgment by electronic devices, affecting the accuracy of display control and user experience.

[0079] In response, this application further proposes that when analyzing the writing characteristics of handwriting information and determining whether the handwriting information belongs to new content, it also includes introducing voice input information for auxiliary judgment. This includes steps S104-21 to S104-26.

[0080] Step S104-21: Obtain voice input information that is synchronized with the handwriting information in time.

[0081] Specifically, voice input information typically refers to the spoken explanations, thoughts, or conversations captured in real time by a user through microphones or other sound-collecting devices while they are writing. By acquiring voice input information synchronized with the handwriting information, electronic devices can capture the user's immediate intentions and contextual information during the writing process, providing important auxiliary information for subsequent judgments.

[0082] Step S104-22: Perform speech recognition on the voice input information and convert it into text information.

[0083] Specifically, electronic devices utilize speech recognition technology to convert unstructured audio data into a text format that can be processed and analyzed by computers. For example, electronic devices can call pre-trained ASR models or cloud-based speech recognition services to accurately convert a user's spoken content into text, potentially including timestamp information for precise alignment with handwriting.

[0084] Extract speech keywords from the text information in step S104-23.

[0085] Specifically, the purpose of extracting speech keywords is to sift through lengthy texts to identify core, semantically representative words that reflect the key points of the user's spoken content. This can be achieved through Natural Language Processing (NLP) techniques, such as using the TF-IDF algorithm, TextRank algorithm, or dictionary-based keyword extraction methods to identify key entities or concepts such as nouns, verbs, and adjectives in the text.

[0086] Steps S104-24: Semantically match the speech keywords with the historical written content blocks associated with the overlapping areas to obtain the matching degree, including:

[0087] Semantic recognition is performed on the historical writing content blocks to extract a set of historical keywords. If a voice keyword is exactly the same as any historical keyword in the set of historical keywords, it is recorded as a complete match. If a voice keyword is a synonym or near-synonym of any historical keyword in the set of historical keywords, it is recorded as an approximate match. The matching degree is calculated based on the number of complete matches and the number of approximate matches: Matching degree = (number of complete matches × first weight + number of approximate matches × second weight) / total number of voice keywords. Wherein, the first weight is greater than the second weight.

[0088] Specifically, first, the electronic device extracts keywords from existing historical writing on the blackboard related to the overlapping areas. Then, it calculates the matching degree by comparing the spoken keywords with the set of historical keywords. If the spoken keyword is exactly the same as any historical keyword in the set of historical keywords, it is recorded as a complete match, indicating a direct and explicit semantic relationship between the two. If the spoken keyword is a synonym or near-synonym of any historical keyword in the set of historical keywords, it is recorded as an approximate match, indicating an indirect and semantically similar relationship between the two.

[0089] The determination of synonyms or near-synonyms can be based on a pre-set thesaurus, word vector models (such as Word2Vec, GloVe), or more complex semantic similarity calculation methods.

[0090] Finally, the matching degree is calculated based on the number of exact matches and the number of near matches. The first weight is greater than the second weight, reflecting the higher priority and importance of exact matches in determining semantic relevance.

[0091] Step S104-25: If the matching degree is lower than the preset second threshold, the handwriting information is determined to be newly added content.

[0092] Step S104-26: If the matching degree is higher than the preset second threshold, the handwriting information is determined to be not new content.

[0093] Specifically, based on the calculated matching degree, the electronic device can assist in determining whether the handwriting information is new content. If the matching degree is lower than a preset second threshold, the handwriting information is determined to be new content. This means that the content spoken by the user while writing has a low semantic correlation with the historical content in the overlapping area, and is likely introducing new knowledge points or concepts. Conversely, if the matching degree is higher than the preset second threshold, the handwriting information is determined not to be new content. This indicates that the content spoken by the user is highly related to historical content, and their writing behavior is more inclined to explain, supplement, or correct existing content.

[0094] The auxiliary judgment results can be combined with the judgment results based on handwriting features, for example, by fusion through weighted averaging, decision trees or machine learning models, to arrive at the final judgment conclusion.

[0095] Step S105: If it is not new content, then determine that the handwriting information is a correction or supplement to the currently displayed content information in the overlapping area, and merge the handwriting information with the currently displayed content information for display.

[0096] Specifically, blending can involve overlaying new handwriting with different colors or transparency onto existing content to create a distinction. Alternatively, if the new handwriting directly overwrites existing content, it can partially replace the original content.

[0097] Step S106: If it is newly added content, execute the space organization strategy and display the handwriting information in the freed-up display area.

[0098] The space organization strategy includes (steps Sa to Sc):

[0099] Step Sa: Identify at least one target written content block associated with the overlapping region.

[0100] Specifically, the electronic device identifies at least one target written content block associated with the overlapping area by grouping existing content elements that are spatially adjacent to or partially overlap with the overlapping area. These existing content elements include individual text paragraphs, formulas, or charts. For example, all content within a certain range around the overlapping area can be considered as one or more target written content blocks.

[0101] Step Sb: Determine the display priority of each target writing content block. This includes steps Sb1 to Sb5.

[0102] Step Sb1: In response to the input of the current handwriting information, arrange the target writing content blocks in order of writing time from late to early, and generate a first priority list to be compressed and displayed.

[0103] Specifically, when an electronic device detects that a user is inputting new handwriting information, it assumes that new content is being written. To initially determine the processing order of the target written content blocks, the electronic device sorts them according to the writing time information of each block. The writing time information can be the timestamp of when the block was created or last modified.

[0104] By sorting from latest to earliest, newer content blocks are given higher priority and are compressed for display first, so as to preserve as much older but still potentially valuable content as possible.

[0105] Step Sb2: Obtain the current teaching knowledge point corresponding to the current handwriting information.

[0106] Specifically, the knowledge points being taught can be obtained through various means. For example, by recognizing and semantically analyzing the user's voice input to extract keywords or themes; or by analyzing the semantic content of the current handwriting information and matching it with a pre-set teaching syllabus or knowledge graph; or by having the user manually input or select the knowledge points currently being taught. The obtained knowledge points will serve as an important basis for evaluating the relevance of historical content.

[0107] Step Sb3: Calculate the content relevance score between each target writing content block and the currently taught knowledge point. This includes steps Sb31 to Sb36.

[0108] Step Sb31: Perform semantic recognition on the target written content block and extract the historical keyword set, historical semantic vector and historical knowledge nodes.

[0109] Specifically, electronic devices perform semantic recognition on target written content blocks, including lexical analysis, syntactic analysis, and named entity recognition. The extraction of historical keyword sets can be achieved in various ways, such as using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm to identify representative words in the text, or extracting keywords through a pre-trained keyword extraction model. These keywords can comprehensively reflect the core theme of the content block.

[0110] Historical semantic vectors are typically generated using word embedding or document embedding techniques, such as Word2Vec, Doc2Vec, GloVe, or Transformer-based models (such as BERT, RoBERTa, etc.). These models map text content into a high-dimensional vector space, making semantically similar words or texts closer together in the vector space, thus capturing deeper semantic information.

[0111] Identifying historical knowledge nodes involves matching extracted keywords or semantic information with a pre-defined knowledge graph. For example, entity linking technology can be used to associate entities in the text (such as names of people, places, concepts, etc.) with corresponding nodes in the knowledge graph, thereby obtaining the representation of the knowledge points involved in the content block in the knowledge graph.

[0112] Step Sb32: Perform semantic recognition on the currently taught knowledge points, and extract the current keyword set, the current semantic vector, and the current knowledge node.

[0113] Specifically, the extraction of the current keyword set can employ the same or similar methods as the historical keyword set to ensure consistency in keyword extraction. Similarly, the generation of the current semantic vector uses the same or similar embedding models as the historical semantic vectors to ensure comparison within the same vector space. The identification of the current knowledge node also uses entity linking or concept matching to associate the currently taught knowledge point with the corresponding node in the knowledge graph.

[0114] Step Sb33: Calculate the first relevance component based on the historical keyword set and the current keyword set, including:

[0115] Count the number of keywords that appear together in the historical keyword set and the current keyword set; count the total number of keywords contained in the historical keyword set and the current keyword set; divide the number of keywords that appear together by the total number of keywords to obtain the first relevance component.

[0116] Specifically, this method can intuitively reflect the degree of commonality between the historical keyword set and the current keyword set in terms of subject words. For example, if the historical content block contains "Newton" and "mechanics", and the current knowledge point being taught contains "Newton" and "universal gravitation", then "Newton" is a common keyword, reflecting the connection between the two in terms of the person or basic concept.

[0117] Step Sb34: Calculate the second relevance component based on the historical semantic vector and the current semantic vector, including:

[0118] Calculate the dot product between the historical semantic vector and the current semantic vector; calculate the product of the magnitude of the historical semantic vector and the magnitude of the current semantic vector; divide the dot product by the product of the magnitudes to obtain the cosine similarity between the historical semantic vector and the current semantic vector, which is used as the second relevance component.

[0119] Specifically, cosine similarity is used to determine the degree of similarity between two vectors by calculating the cosine value of the angle between them. The smaller the angle, the closer the cosine value is to 1, indicating that the semantics are more similar. It can capture text content that is highly related in meaning even if there are no common keywords.

[0120] Step Sb35: Based on the positions of historical knowledge nodes and current knowledge nodes in the preset knowledge graph, calculate the third relevance component, including: Obtain the shortest path length between the historical knowledge node and the current knowledge node in the knowledge graph; if the historical knowledge node and the current knowledge node are the same node, the third relevance component is set to 1; if there is no path connecting the historical knowledge node and the current knowledge node in the knowledge graph, the third relevance component is set to the preset minimum value; if the historical knowledge node and the current knowledge node are different nodes and there is a connecting path in the knowledge graph, the third relevance component is calculated in a way that is negatively correlated with the shortest path length.

[0121] Specifically, a knowledge graph represents knowledge in the form of a graph, where nodes represent entities or concepts, and edges represent the relationships between them. By obtaining the shortest path length between historical knowledge nodes and current knowledge nodes in a preset knowledge graph, the closeness of their relationship within the knowledge system can be reflected. If a historical knowledge node and a current knowledge node are the same node, the third relevance component is set to 1, indicating complete consistency and the highest relevance. If there is no path connecting a historical knowledge node and a current knowledge node in the knowledge graph, the third relevance component is set to the preset minimum value, indicating extremely low relevance. Otherwise, the third relevance component is calculated in a way that is negatively correlated with the shortest path length, i.e., the shorter the path, the higher the relevance; for example, it can be expressed as a function of 1 / (1 + shortest path length).

[0122] Step Sb36: Based on the preset first weight, second weight, and third weight, the first relevance component, the second relevance component, and the third relevance component are weighted and fused to obtain the content relevance score.

[0123] Specifically, the preset weights can be adjusted based on actual application scenarios and experience. For example, different weights can be assigned based on the importance of keyword matching, semantic similarity, and knowledge graph association in the overall relevance assessment.

[0124] Step Sb4: Sort the target written content blocks in the first priority list in descending order according to their corresponding content relevance scores to obtain a relevance sequence. Then, generate a second priority list of the first preset number of target written content blocks in the relevance sequence to be migrated to the temporary storage area.

[0125] Specifically, after initially generating the first priority list, the electronic device further refines the sorting of these blocks using content relevance scores. The blocks in the resulting second priority list are those that are highly relevant to the current teaching content. Therefore, in addition to being compressed for display, they are also moved to a temporary storage area to ensure that they can be quickly restored for display when needed, thus avoiding the loss of critical information.

[0126] Step Sb5: In response to the completion of writing the current handwriting information, clear the second priority list and update the first priority list according to the updated writing time information.

[0127] Specifically, once the user completes inputting the current handwriting information, the current teaching context may change. At this point, the second priority list previously generated based on the current handwriting information and the currently taught knowledge points will no longer be applicable and therefore needs to be cleared. Simultaneously, since new writing content has been added to the display area, the writing time information for all content blocks may need to be updated. The electronic device will re-evaluate and update the first priority list based on the latest writing time information to adapt to the new display state and potential space management needs.

[0128] Step Sc: Based on the display priority, perform compression display or migration to temporary storage area operation on at least one target written content block to free up the display area.

[0129] Specifically, the target written content blocks in the first priority list of the plan are compressed and displayed, and the target written content blocks in the second priority list are migrated to the temporary storage area.

[0130] Step S107: Generate and store association mapping information, which is the correspondence between handwriting information and compressed or migrated historical handwriting content blocks.

[0131] Specifically, the association mapping information can be a one-to-many or many-to-many link between the identifier of the newly entered handwriting information and the identifier of the compressed or migrated historical handwriting content block. For example, recording the ID of the new handwriting and a list of IDs of all affected historical blocks can establish a logical connection between them.

[0132] Furthermore, the aforementioned association mapping information is mainly used for the management and restoration of displayed content, failing to fully explore its potential value in knowledge system construction and teaching assistance. This makes it difficult for users to electronically access extended knowledge related to the current content when reviewing or learning related knowledge, thus limiting the application of smart blackboards in deep learning and knowledge association.

[0133] In this regard, this application further proposes that after generating and storing the association mapping information, it also includes (steps S31 to S34):

[0134] Step S31: Obtain the first knowledge point corresponding to the handwriting information, and at least one second knowledge point corresponding to the compressed or migrated historical writing content block.

[0135] Specifically, when acquiring the first knowledge point corresponding to handwriting information and at least one second knowledge point corresponding to a compressed or migrated historical writing content block, the electronic device can utilize natural language processing, image recognition, or multimodal information fusion technologies to perform semantic analysis and entity recognition on the handwriting information and the content of the historical writing content block. For example, for text content, methods such as keyword extraction, topic modeling, and named entity recognition can be used to match it with knowledge nodes in a pre-defined knowledge graph; for non-text content such as diagrams and formulas, technologies such as image recognition and symbol recognition can be used to parse it into corresponding knowledge concepts. The first and second knowledge points can be specific concepts, theorems, formulas, cases, events, etc., representing the core semantics of the written content.

[0136] Step S32: Based on the association mapping information, establish the teaching association relationship between the first knowledge point and the second knowledge point.

[0137] Specifically, electronic devices leverage the existing correspondence between handwriting information and historical written content blocks to elevate this content-level association to a knowledge-point-level pedagogical association. This pedagogical association can include, but is not limited to, various types such as "explanation," "supplementation," "expansion," "comparison," "prerequisite knowledge," and "application examples." For instance, if the handwriting information further elaborates on a historical written content block, an "explanation relationship" is established; if the handwriting information provides additional information about the historical content, a "supplementary relationship" is established. This relationship can be established through pre-defined semantic rules, machine learning-based classification models, or human expert annotation.

[0138] Step S33: Update the teaching relationships to the preset knowledge graph to enrich the connection paths between knowledge points in the knowledge graph.

[0139] Specifically, electronic devices add newly established teaching relationships as new edges or attributes to the knowledge graph. A knowledge graph is a structured knowledge base composed of knowledge points (nodes) and the relationships between them (edges). Through dynamic updates, the knowledge graph can reflect the actual connections formed between knowledge points in real time during the teaching process. For example, if the "first knowledge point" is the "law of conservation of energy" and the "second knowledge point" is the "first law of thermodynamics," and an "equivalence relation" is established, then an "equivalent" edge connecting these two knowledge points will be added to the knowledge graph. This makes the knowledge graph no longer static, but rather capable of continuously evolving and improving as teaching activities progress, thus more accurately reflecting the dynamic structure of knowledge.

[0140] Step S34: In response to subsequent backtracking operations on the first or second knowledge point, based on the updated knowledge graph, recommend extended knowledge points related to the current teaching content for the user to choose from.

[0141] Specifically, "backtracking" refers to users refocusing on or querying a specific knowledge point displayed on the smart blackboard through various interactive methods such as clicking, selecting, and voice querying. When the electronic device detects such an operation, it uses the updated knowledge graph to intelligently find and recommend other knowledge points related to the backtracked knowledge point, following newly established teaching connections and other existing relationships within the knowledge graph. For example, if a user backtracks on "Newton's First Law," the electronic device can recommend related knowledge points such as "inertia," "Newton's Second Law," and "force" based on the knowledge graph, presenting them to the user in the form of lists, diagrams, or mind maps for selection and viewing, thereby enabling expanded learning and in-depth exploration of knowledge.

[0142] To better implement the above method, this application also provides a blackboard intelligent display control device, referring to... Figure 2 The blackboard intelligent display control device 200 includes: The handwriting information acquisition module 201 is used to acquire the current display content information and real-time input handwriting information of the blackboard display area; The overlapping area judgment module 202 is used to determine whether there is an overlapping area between the handwriting information and the currently displayed content information; The first handwriting display module 203 is used to directly display the written handwriting on the blackboard display area when it is determined that there is no overlapping area; The content judgment module 204 is used to analyze the writing characteristics of the handwriting information when there are overlapping areas, and to determine whether the handwriting information belongs to new content. The second handwriting display module 205 is used to determine that the handwriting information is a correction or supplement to the currently displayed content information in the overlapping area when it is determined that it is not new content, and to merge the handwriting information with the currently displayed content information for display. The space organization strategy execution module 206 is used to execute the space organization strategy when it is determined that the content is newly added, and to display the handwriting information in the released display area. Space organization strategies include: Identify at least one target written content block associated with the overlapping region; Determine the display priority of each target writing content block; Based on display priority, perform operations to compress the display or migrate it to a temporary storage area for at least one target block of written content in order to free up the display area; Storage module 207 is used to generate and store association mapping information, which is the correspondence between handwriting information and compressed or migrated historical handwriting content blocks.

[0143] The various variations and specific examples of the methods in the foregoing embodiments are also applicable to the blackboard intelligent display control device of this embodiment. Through the foregoing detailed description of the blackboard intelligent display control method, those skilled in the art can clearly understand the implementation method of the blackboard intelligent display control device in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0144] To better implement the above methods, embodiments of this application provide an electronic device, referring to... Figure 3The electronic device 300 includes a processor 301, a memory 303, and a display screen 305. The memory 303 and the display screen 305 are both connected to the processor 301, such as via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0145] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0146] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 may be divided into address bus, data bus, control bus, etc.

[0147] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or 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 not limited thereto.

[0148] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0149] Figure 3 The electronic device 300 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0150] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the program implements the blackboard intelligent display control method provided in the above embodiments. By determining whether the handwriting is new content and executing a space organization strategy accordingly, it solves the problems of traditional smart blackboards where manual operation interrupts teaching continuity, historical content is lost, or fonts are too small to read when there is insufficient writing space. It can dynamically adjust the layout of the displayed content to ensure that new content has display space. At the same time, through compression, migration, and association mapping, historical content is preserved and traceable, thereby improving the continuity of teaching and the readability of the content.

[0151] In this embodiment, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0152] The computer program in this embodiment includes program code for performing all the aforementioned methods. The program code may include instructions corresponding to the method steps provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed entirely on the user's computer as a standalone software package.

[0153] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

[0154] Additionally, it should be understood that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A blackboard intelligent display control method, characterized in that, include: Obtain information on the current displayed content and real-time handwriting input in the blackboard display area; Determine whether there is an overlapping area between the handwriting information and the currently displayed content information; If there is no overlapping area, the handwriting will be displayed directly on the blackboard display area; If there are overlapping areas, the writing characteristics of the handwriting information are analyzed to determine whether the handwriting information belongs to newly added content; If it is not new content, then the handwriting information is determined to be a correction or supplement to the currently displayed content information in the overlapping area, and the handwriting information is merged with the currently displayed content information for display. If it is newly added content, then the space organization strategy will be executed to display the handwriting information in the released display area; The space organization strategy includes: Identify at least one target written content block associated with the overlapping region; Determine the display priority of each target written content block; Based on the display priority, at least one of the target written content blocks is compressed for display or moved to a temporary storage area to free up the display area; Generate and store association mapping information, which is the correspondence between the handwriting information and the compressed or migrated historical writing content blocks.

2. The method of claim 1, wherein, The analysis of the handwriting characteristics of the handwriting information to determine whether the handwriting information belongs to newly added content includes: Obtain at least one segment of historical handwriting information that is temporally adjacent to the handwriting information; Semantic recognition is performed on the handwriting information and the historical handwriting information respectively, and their respective semantic features are extracted; Calculate the semantic correlation degree between the semantic features of the written handwriting information and the semantic features of the historical handwriting information; Calculate the spatial continuity coefficient between the written handwriting information and the historical handwriting information; If the semantic relevance exceeds a preset first threshold and the spatial continuity coefficient exceeds a preset second threshold, then the handwriting information is determined to be newly added content. If the semantic relevance does not exceed the first threshold, then the handwriting information is determined not to be new content; If the semantic relevance exceeds the first threshold but the spatial continuity coefficient does not exceed the second threshold, then the handwriting information is determined to be a semantic supplement or annotation to the historical handwriting information, and the handwriting information is determined not to be new content. The calculation method for the spatial continuity coefficient includes: Obtain the center point coordinate sequence of the written handwriting information and the center point coordinate sequence of the historical handwriting information; The writing direction vector of the historical handwriting information is determined, and the writing direction vector is obtained by linear fitting the coordinate sequence of the center point; Calculate the spatial continuity coefficient of the written handwriting information relative to the historical handwriting information, wherein the spatial continuity coefficient is a weighted sum of the distance component, the direction component, and the alignment component; The distance component The calculation method is as follows: ;in, The minimum Euclidean distance between the written handwriting information and the historical handwriting information is given. This is the preset maximum effective extension distance; The directional component The calculation method is as follows: ;in, The angle between the overall extension direction of the handwriting information and the writing direction vector of the historical handwriting information is given by linearly fitting the coordinate sequence. The alignment component The calculation method is as follows: ;in, This refers to the baseline position of the line containing the handwriting information. This represents the baseline position of the line containing the historical handwriting information. This is the preset maximum baseline offset tolerance.

3. The method according to claim 2, characterized in that, The calculation of the semantic correlation between the semantic features of the written handwriting information and the semantic features of the historical handwriting information includes: Semantic recognition is performed on the handwriting information and the historical handwriting information respectively, and their respective keyword sets and sentence structure features are extracted; Based on the keyword set, a first relevance component is determined, which is positively correlated with the number of keywords that appear in both keyword sets. Based on the sentence structure features, a second correlation component is determined. The second correlation component is determined according to the relation markers that co-occur in the handwriting information and the historical handwriting information. Different relation markers correspond to different preset weights. The second correlation component is positively correlated with the sum of the weights of the co-occurring relation markers. Based on the positions of the handwriting information and the historical handwriting information in a preset knowledge graph, a third correlation component is determined. The third correlation component is negatively correlated with the shortest path length in the knowledge graph between the first knowledge node corresponding to the handwriting information and the second knowledge node corresponding to the historical handwriting information. If the first knowledge node and the second knowledge node are the same node, the third correlation component takes a preset maximum value. If there is no path connecting the first knowledge node and the second knowledge node in the knowledge graph, the third correlation component takes a preset minimum value. Based on the preset first weight, second weight, and third weight, the first correlation component, the second correlation component, and the third correlation component are weighted and fused to obtain the semantic correlation.

4. The method according to claim 1 or 2, characterized in that, The step of analyzing the writing characteristics of the handwriting information and determining whether the handwriting information belongs to newly added content also includes: Acquire voice input information that is time-synchronized with the handwriting information; The voice input information is subjected to speech recognition and converted into text information; Extract speech keywords from the text information; Semantic matching is performed between the spoken keywords and the historical written content blocks associated with the overlapping areas to obtain the matching degree, including: Semantic recognition is performed on the historical writing content blocks to extract a set of historical keywords; If the voice keyword is exactly the same as any historical keyword in the historical keyword set, it is recorded as a complete match; If the voice keyword is a synonym or near-synonym of any historical keyword in the set of historical keywords, it is recorded as an approximate match. Calculate the matching degree based on the number of exact matches and the number of near matches: Matching score = (Number of exact matches × First weight + Number of near matches × Second weight) / Total number of voice keywords; where the first weight is greater than the second weight; If the matching degree is lower than the preset second threshold, the handwriting information is determined to be newly added content. If the matching degree is higher than the preset second threshold, the handwriting information is not considered new content.

5. The method according to claim 1, characterized in that, Determining the display priority of each of the target written content blocks includes: In response to the input of detected current handwriting information, the target writing content blocks are arranged in order of writing time from latest to earliest, and a first priority list for compression and display is generated; Obtain the current teaching knowledge point corresponding to the current handwriting information; Calculate the content relevance score between each target writing content block and the currently taught knowledge point; Arrange the target written content blocks in the first priority list in descending order according to the corresponding content relevance scores to obtain a relevance sequence. Then, generate a second priority list of the first preset number of target written content blocks in the relevance sequence to be migrated to the temporary storage area. In response to the completion of writing the current handwriting information, the second priority list is cleared, and the first priority list is updated according to the updated writing time information.

6. The method according to claim 5, characterized in that, The calculation of the content relevance score between each of the target written content blocks and the currently taught knowledge point includes: Semantic recognition is performed on the target written content block to extract historical keyword sets, historical semantic vectors, and historical knowledge nodes; Semantic recognition is performed on the currently taught knowledge points to extract the current keyword set, the current semantic vector, and the current knowledge node; Based on the historical keyword set and the current keyword set, calculate the first relevance component, including: Count the number of keywords that appear together in the historical keyword set and the current keyword set; Count the total number of keywords contained in the historical keyword set and the current keyword set; The first relevance component is obtained by dividing the number of co-occurring keywords by the total number of keywords. Based on the historical semantic vector and the current semantic vector, a second relevance component is calculated, including: Calculate the dot product between the historical semantic vector and the current semantic vector; Calculate the product of the magnitude of the historical semantic vector and the magnitude of the current semantic vector; Divide the dot product by the product of the modulus to obtain the cosine similarity between the historical semantic vector and the current semantic vector, which is used as the second relevance component. Based on the positions of the historical knowledge nodes and the current knowledge nodes in the preset knowledge graph, a third relevance component is calculated, including: Obtain the shortest path length between the historical knowledge node and the current knowledge node in the knowledge graph; If the historical knowledge node and the current knowledge node are the same node, then the third relevance component is 1; If there is no path connecting the historical knowledge node and the current knowledge node in the knowledge graph, then the third relevance component takes the preset minimum value. If the historical knowledge node and the current knowledge node are different nodes and there is a connection path in the knowledge graph, then the third correlation component is calculated in a way that is negatively correlated with the shortest path length; Based on the preset first weight, second weight, and third weight, the first relevance component, the second relevance component, and the third relevance component are weighted and fused to obtain the content relevance score.

7. The method according to claim 1, characterized in that, After generating and storing the associated mapping information, the process further includes: Obtain the first knowledge point corresponding to the handwriting information, and at least one second knowledge point corresponding to the compressed or migrated historical writing content block; Based on the association mapping information, establish a teaching association relationship between the first knowledge point and the second knowledge point; The teaching associations are updated to the preset knowledge graph to enrich the connection paths between knowledge points in the knowledge graph; In response to subsequent backtracking operations on the first or second knowledge point, based on the updated knowledge graph, extended knowledge points related to the currently taught content are recommended for the user to choose from.

8. A blackboard intelligent display control device, characterized in that, include: The handwriting information acquisition module is used to acquire the current display content information and real-time input handwriting information of the blackboard display area; The overlapping area determination module is used to determine whether there is an overlapping area between the handwriting information and the currently displayed content information; The first handwriting display module is used to directly display the written handwriting on the blackboard display area when it is determined that there is no overlapping area. The content judgment module is used to analyze the writing characteristics of the handwriting information when there are overlapping areas, and to determine whether the handwriting information belongs to new content. The second handwriting display module is used to determine that the handwriting information is a correction or supplement to the currently displayed content information in the overlapping area when it is determined that it is not new content, and to merge the handwriting information with the currently displayed content information for display. The space organization strategy execution module is used to execute the space organization strategy when it is determined that the content is newly added, and to display the handwriting information in the released display area. The space organization strategy includes: Identify at least one target written content block associated with the overlapping region; Determine the display priority of each target written content block; Based on the display priority, at least one of the target written content blocks is compressed for display or moved to a temporary storage area to free up the display area; A storage module is used to generate and store association mapping information, which is the correspondence between the handwriting information and the compressed or migrated historical writing content blocks.

9. An electronic device, characterized in that, include: At least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method as described in any one of claims 1 to 7.

Images