Calligraphy teaching method and system based on dynamic handwriting analysis

Abstract

The invention discloses a calligraphy teaching method and system based on dynamic handwriting analysis, and the method comprises the following steps: S1, collecting dynamic handwriting data in a writing process of a user, carrying out the preprocessing of the dynamic handwriting data, removing noise data, and complementing the missing stroke state data; s2, extracting handwriting feature parameters of the preprocessed dynamic handwriting data; s3, performing matching analysis on the extracted handwriting feature parameters and a preset standard handwriting feature template to obtain difference parameters between the user handwriting and standard handwriting; and S4, generating calligraphy teaching feedback information according to the difference parameters, and issuing the calligraphy teaching feedback information to terminal equipment of the user. The feedback information is accurately output through multi-mode synchronous rendering, a traditional manual subjective comment mode is replaced, teaching feedback can be quantified and can be carried out on the ground, and the digitization and high-efficiency level of calligraphy teaching is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent teaching technology, and in particular to a calligraphy teaching method and system based on dynamic handwriting analysis. Background Technology

[0002] Calligraphy teaching has long relied on manual feedback from teachers. The evaluation of dynamic handwriting characteristics such as brush tip angle, ink diffusion, and brush movement acceleration lacks quantitative standards. Teaching feedback is highly subjective and difficult to accurately match the learner's writing problems.

[0003] Existing digital calligraphy teaching solutions mostly focus on static handwriting trajectory comparison or only collect single pressure / speed data, using unweighted cosine similarity algorithms to analyze handwriting matching, without constructing a multi-dimensional feature system tailored to specific characteristics. Such solutions cannot accurately capture the rhythmic changes in pressure and pauses, or the coupling relationship between brush pressure and ink volume, resulting in a disconnect between matching analysis results and actual calligraphy teaching needs, and generating correction suggestions that lack specificity.

[0004] The current challenge lies in constructing a multi-dimensional feature weighted matching model that adapts to the mechanism of calligraphy brushstrokes, quantitatively extracting unique features such as brush tip, ink volume, and brushstroke rhythm and assigning them reasonable weights, and generating feedback information that fits the actual teaching situation through precise dynamic handwriting analysis, thereby improving the digitalization and precision of calligraphy teaching. Summary of the Invention

[0005] This application provides a calligraphy teaching method and system based on dynamic handwriting analysis to solve the above-mentioned problems.

[0006] On the one hand, this application provides a calligraphy teaching method based on dynamic handwriting analysis. The method includes the following steps: Step S1: Collect dynamic handwriting data during the user's writing process, preprocess the dynamic handwriting data to remove noise data and complete missing pen stroke state data; Step S2: Extract handwriting feature parameters from the preprocessed dynamic handwriting data; Step S3: Match and analyze the extracted handwriting feature parameters with a preset standard calligraphy handwriting feature template to obtain the difference parameters between the user's handwriting and the standard handwriting; Step S4: Generate calligraphy teaching feedback information based on the difference parameters and send it to the user's terminal device.

[0007] In one implementation of this application, step S1, which involves collecting dynamic handwriting data, specifically includes: collecting sensor data based on the trajectory positioning sensor, pressure sensing unit, angle sensing unit, and ink volume detection unit integrated in the acquisition device; aligning the timestamps of each sensor data using a synchronous clock signal; eliminating inherent zero-point drift errors of the device using a sensor baseline calibration algorithm before acquisition; performing real-time data validity verification during acquisition to remove abnormal data exceeding a reasonable threshold; and transmitting the collected dynamic handwriting data to the data processing unit via a high-speed serial bus, with a data packet verification mechanism used during the transmission process.

[0008] In one implementation of this application, step S2, extracting handwriting feature parameters, specifically includes: extracting stroke morphology features through geometric modeling of the trajectory coordinate sequence; smoothing the writing trajectory using a Bezier curve fitting algorithm; calculating the quantitative values ​​of the starting and ending stroke exposure angles and the lifting and pressing amplitude through curve differentiation; determining the straightness and curvature of the strokes and the opening and closing angle of the brush tip based on the detection of curvature extreme points; analyzing the writing rhythm features through time series analysis; performing sliding window filtering on the writing speed sequence; extracting statistical features such as the mean and variance of speed within a single stroke; obtaining the speed change rate at the stroke turning point through gradient calculation; and statistically analyzing the time proportion parameter of the lifting and pressing action based on the timestamp difference.

[0009] In one implementation of this application, in step S2, the handwriting feature parameters include stroke shape features, pen stroke rhythm features, pen pressure distribution features, and ink color diffusion features.

[0010] In one implementation of this application, the method further includes: extracting pen movement rhythm features using a joint calculation algorithm of pen movement speed and acceleration, wherein the calculation formula for real-time pen movement acceleration is as follows:

[0011] Among them, a i v represents the real-time pen movement acceleration corresponding to the i-th sampling point, used to characterize the speed change trend during the lifting and pressing process; i v represents the real-time writing speed corresponding to the i-th sampling point; i+1 t represents the real-time writing speed corresponding to the (i+1)th sampling point; i t is the timestamp of the i-th sampling point; i+1 This is the timestamp of the (i+1)th sampling point.

[0012] In one implementation of this application, a pressure-ink volume coupled feature extraction algorithm is used to obtain ink color diffusion features, and the calculation formula is as follows:

[0013] Where I(x,y) is the ink density value at coordinate (x,y); k is the ink volume coefficient, which is determined by the type of brush bristles and ink concentration used; P(x,y) is the brush pressure value at coordinate (x,y); v(x,y) is the real-time writing speed at coordinate (x,y); and d0 is the base ink value, which represents the ink base without additional pressure.

[0014] In one implementation of this application, a multi-dimensional feature-weighted matching algorithm is used to calculate the similarity between the user's handwriting and the standard handwriting. Based on the similarity, the difference parameter between the user's handwriting and the standard handwriting is obtained. The similarity calculation formula is as follows:

[0015] Where S is the overall similarity between the user's handwriting and the standard handwriting; n is the number of categories of handwriting features; w k Let A be the weight coefficient of the k-th class feature, satisfying that the sum of the feature weights is 1, obtained through training with a large number of calligraphy samples; m is the number of parameter dimensions included in the k-th class feature; A k,i B represents the i-th dimension parameter value of the k-th class feature of the user's handwriting. k,i The i-th dimension parameter value is the k-th feature of the standard handwriting template.

[0016] On the other hand, this application also provides a calligraphy teaching system based on dynamic handwriting analysis, which applies the aforementioned calligraphy teaching method based on dynamic handwriting analysis, such as... Figure 2 As shown, the system includes: a dynamic handwriting acquisition module 201, used to acquire dynamic handwriting data during the user's writing process; a data preprocessing module 202, used to perform noise removal, missing data completion, and data standardization on the dynamic handwriting data; a feature extraction module 203, used to extract specific handwriting feature parameters from the preprocessed dynamic handwriting data; a matching analysis module 204, used to match and analyze the extracted handwriting feature parameters with standard calligraphy handwriting feature templates to obtain difference parameters; and a teaching feedback module 205, used to generate targeted calligraphy teaching feedback information based on the difference parameters.

[0017] In one implementation of this application, the system further includes a standard handwriting template library, which stores standard calligraphy handwriting feature templates of different script styles and different calligraphic styles, and supports the addition, modification, deletion and categorized retrieval of templates.

[0018] In one implementation of this application, the system further includes a user interaction module, which is used to receive the user's writing mode selection and font switching operation instructions, display teaching feedback information and standard pen stroke demonstration data, and to query, store and perform multi-version comparison analysis of the user's historical handwriting data.

[0019] This application provides a calligraphy teaching method and system based on dynamic handwriting analysis, which has the following beneficial effects: 1. By constructing a multi-dimensional feature weighted matching model, reasonable weights are assigned to exclusive features such as pen pressure and ink bleeding, breaking through the limitations of traditional unweighted matching and single feature analysis, and realizing quantitative and accurate analysis of the differences between user handwriting and standard handwriting.

[0020] 2. Based on the mechanism of brush movement, a feature extraction algorithm is designed to capture unique dynamic handwriting features such as brush tip angle, brush movement acceleration, and pressure-ink volume coupling relationship. This solves the problem that existing digital solutions only focus on static trajectories and have poor adaptability, and is in line with the core teaching of calligraphy, such as the lifting, pressing, pausing and changing ink color.

[0021] 3. Relying on the precise data and differential parameter quantification mapping technology of multi-sensor collaborative calibration, structured correction suggestions are generated, and the feedback information is accurately output through multi-modal synchronous rendering, replacing the traditional manual subjective evaluation mode. This makes teaching feedback quantifiable and implementable, improving the digitalization and efficiency of calligraphy teaching. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a calligraphy teaching method based on dynamic handwriting analysis, provided for an embodiment of this application; Figure 2 This is a diagram illustrating the composition of a calligraphy teaching system based on dynamic handwriting analysis, provided as an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] This application provides a calligraphy teaching method and system based on dynamic handwriting analysis. The technical solution proposed in this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This document provides a flowchart of a calligraphy teaching method based on dynamic handwriting analysis, as an embodiment of this application. Figure 1 As shown, the method mainly includes the following steps: Step S1: Collect dynamic handwriting data during the user's writing process, preprocess the dynamic handwriting data to remove noise data and fill in the missing pen stroke state data. Step S2: Extract handwriting feature parameters from the preprocessed dynamic handwriting data; Step S3: Match and analyze the extracted handwriting feature parameters with the preset standard calligraphy handwriting feature template to obtain the difference parameters between the user's handwriting and the standard handwriting; Step S4: Generate calligraphy teaching feedback information based on the difference parameters and send it to the user's terminal device.

[0026] Furthermore, in step S1, collecting dynamic handwriting data specifically includes: The acquisition device collects sensor data based on the integrated trajectory positioning sensor, pressure sensing unit, angle sensing unit, and ink volume detection unit. The timestamps of the data from each sensor are aligned by synchronizing the clock signal. Before data acquisition, the sensor baseline calibration algorithm is used to eliminate the inherent zero-point drift error of the equipment. During the acquisition process, the data validity is verified in real time, and abnormal data exceeding the reasonable threshold is removed. The collected dynamic handwriting data is transmitted to the data processing unit via a high-speed serial bus, and the transmission process employs a data packet verification mechanism.

[0027] Furthermore, in step S2, extracting handwriting feature parameters specifically includes: The stroke shape features are extracted by geometric modeling of the trajectory coordinate sequence, the writing trajectory is smoothed by Bezier curve fitting algorithm, and the quantitative values ​​of the starting stroke concealment angle and the ending stroke lifting and pressing amplitude are calculated by curve differentiation. The curvature extreme point detection determines the straightness of the stroke and the opening and closing angle of the pen tip. By analyzing the characteristics of pen stroke rhythm through time series analysis, sliding window filtering is applied to the writing speed sequence to extract statistical features such as the mean and variance of speed within a single stroke. The speed change rate at the turning point of the stroke is obtained through gradient calculation, and the time ratio parameter of the pressing and lifting action is statistically calculated based on the timestamp difference.

[0028] Furthermore, in step S2, the handwriting feature parameters include stroke shape features, pen stroke rhythm features, pen pressure distribution features, and ink color diffusion features.

[0029] Furthermore, the method also includes: extracting pen movement rhythm features using a joint calculation algorithm of pen movement speed and acceleration, wherein the calculation formula for real-time pen movement acceleration is as follows:

[0030] Among them, a iv represents the real-time pen movement acceleration corresponding to the i-th sampling point, used to characterize the speed change trend during the lifting and pressing process; i v represents the real-time writing speed corresponding to the i-th sampling point; i+1 t represents the real-time writing speed corresponding to the (i+1)th sampling point; i t is the timestamp of the i-th sampling point; i+1 This is the timestamp of the (i+1)th sampling point.

[0031] Furthermore, the pressure-ink volume coupled feature extraction algorithm is used to obtain the ink color diffusion features, and the calculation formula is as follows:

[0032] Where I(x,y) is the ink density value at coordinate (x,y); k is the ink volume coefficient, which is determined by the type of brush bristles and ink concentration used; P(x,y) is the brush pressure value at coordinate (x,y); v(x,y) is the real-time writing speed at coordinate (x,y); and d0 is the base ink value, which represents the ink base without additional pressure.

[0033] Further, in step S3, a multi-dimensional feature weighted matching algorithm is used to calculate the similarity between the user's handwriting and the standard handwriting. Based on the similarity, the difference parameter between the user's handwriting and the standard handwriting is obtained. The similarity calculation formula is as follows:

[0034] Where S is the overall similarity between the user's handwriting and the standard handwriting; n is the number of categories of handwriting features; w k Let A be the weight coefficient of the k-th class feature, satisfying that the sum of the feature weights is 1, obtained through training with a large number of calligraphy samples; m is the number of parameter dimensions included in the k-th class feature; A k,i B represents the i-th dimension parameter value of the k-th class feature of the user's handwriting. k,i The i-th dimension parameter value is the k-th feature of the standard handwriting template.

[0035] The above is an embodiment of a calligraphy teaching method based on dynamic handwriting analysis provided by this application. Based on the same inventive concept, this application also provides a calligraphy teaching system based on dynamic handwriting analysis. Figure 2 A diagram illustrating the composition of a calligraphy teaching system based on dynamic handwriting analysis, provided as an embodiment of this application, is shown below. Figure 2As shown, the system mainly includes: a dynamic handwriting acquisition module 201, used to acquire dynamic handwriting data during the user's writing process; a data preprocessing module 202, used to perform noise removal, missing data completion, and data standardization on the dynamic handwriting data; a feature extraction module 203, used to extract exclusive handwriting feature parameters from the preprocessed dynamic handwriting data; a matching analysis module 204, used to match and analyze the extracted handwriting feature parameters with standard calligraphy handwriting feature templates to obtain difference parameters; and a teaching feedback module 205, used to generate targeted calligraphy teaching feedback information based on the difference parameters.

[0036] Furthermore, the system also includes a standard handwriting template library, which stores standard calligraphy handwriting feature templates of different calligraphic styles and different calligraphic styles, and supports the addition, modification, deletion and categorized retrieval of templates.

[0037] Furthermore, the system also includes a user interaction module, which is used to receive the user's writing mode selection and font switching operation commands, display teaching feedback information and standard pen stroke demonstration data, and query, store and perform multi-version comparison analysis of the user's historical handwriting data.

[0038] Below is an example of this application in a specific application scenario: an application example of a primary school calligraphy classroom based on dynamic handwriting analysis.

[0039] The hardware deployment is as follows: Student calligraphy study desks (30 sets, suitable for classroom teaching); core equipment: integrated customized writing board (built-in trajectory positioning sensor and pressure sensing unit), pen barrel angle detection module (installed at the end of the pen barrel), ink volume monitoring ink cartridge (embedded in the desktop ink cartridge slot, real-time detection of ink remaining and ink output during writing); interactive terminal: 10-inch touch screen (embedded in the upper right corner of the desktop, anti-accidental touch design), local data processing unit (supports real-time preprocessing data), Wi-Fi communication module (establishes a dedicated local area network connection with the teacher's desk); auxiliary configuration: anti-slip writing mat, adjustable height pen holder, ink refill interface (compatible with standard student ink bottles). The teacher's calligraphy teaching desk (1 set, core control terminal) includes: a 15-inch touchscreen (supporting split-screen display of real-time data from 30 students), a high-performance data processing host (integrating a matching analysis module and a standard handwriting template library); a communication module: a dual-band Wi-Fi router (ensuring low-latency communication between teacher and student devices), and Bluetooth emergency communication backup; teaching aids: a high-definition camera (capable of capturing teacher demonstrations and synchronizing them to student desks), and a voice broadcast unit (supporting batch notifications or individual guidance). All student desks and the teacher's desk achieve real-time data transmission via a local area network. The teacher's desk can centrally manage template usage and data collection modes for student desks, and student writing data and difference analysis results can be synchronized and archived on the teacher's desk.

[0040] In the pre-class preparation stage (teacher operation), the teacher logs into the system via the teacher's desk touchscreen, selects the teaching content as "Regular Script Calligraphy Copybook - Basic Stroke 'Horizontal'", and retrieves the standard handwriting feature template for this stroke from the template library (including stroke shape: 35° starting angle with concealed tip, 0.8mm lifting and pressing range at the end of the stroke; stroke rhythm: average speed of a single stroke 2.5cm / s, lifting and pressing action time ratio 30%; ink color diffusion: pressure-ink volume coupling benchmark value, etc.). The teacher distributes the teaching task to 30 sets of student desks in batches through the system. The student desk touchscreen automatically displays the standard stroke animation of the "horizontal" stroke (including the action breakdown of the starting, middle, and ending strokes) and a demonstration diagram of ink color changes.

[0041] During the student writing and data collection phase (student operation + system automation), students take out the accompanying ink cartridge, dip it in the ink level monitoring cartridge, and practice writing horizontal strokes on the writing board following the demonstration animation. During the writing process: a trajectory positioning sensor collects the writing trajectory coordinate sequence in real time (sampling frequency 50Hz); a pressure sensing unit detects the pressure value of the pen tip on the writing board (accuracy 0.1g); an angle sensing unit records the angle change between the pen and the writing board; and an ink level detection unit captures the ink output rate during writing. The local data processing unit on the student's desk aligns the timestamps of each sensor using a synchronous clock signal, employs a baseline calibration algorithm to eliminate zero-point drift, and removes abnormal data exceeding reasonable ranges (such as erroneous data where the pen angle is greater than 90°). It also supplements data missing due to occasional hand obstruction. After completing three horizontal strokes, the student clicks the "submit" button on the touchscreen, and the pre-processed dynamic handwriting data is transmitted to the teacher's desk in real time via Wi-Fi.

[0042] In the feature extraction and matching analysis stage (system collaborative operation), basic handwriting feature parameters are extracted locally on the student's desk: the writing trajectory is smoothed by fitting a Bézier curve, and the starting angle of the student's horizontal stroke (e.g., 48°) and the lifting and pressing amplitude at the end of the stroke (e.g., 1.2mm) are calculated; the speed sequence is processed by a sliding window filter to obtain the average speed of a single stroke (e.g., 3.8cm / s) and the proportion of lifting and pressing time (e.g., 22%). Combined with the acceleration sequence calculated in real time, the average acceleration at the beginning stage (e.g., -0.2cm / s²), the average acceleration during the writing stage (e.g., 0.1cm / s²), and the average acceleration at the end stage (e.g., 0.15cm / s²) are obtained; the ink concentration distribution is calculated by a pressure-ink volume coupling algorithm (e.g., the ink concentration value at coordinates (2.3cm, 1.5cm) is higher than the standard value by 0.3). After receiving the feature parameters of all students, the teacher's desk calls a multi-dimensional feature weighted matching algorithm for batch analysis: setting the weight of stroke shape feature to 0.4, the weight of pen rhythm feature to 0.3, the weight of ink color diffusion feature to 0.2, and the weight of pen tip pressure distribution feature to 0.1 (derived from training samples of elementary school calligraphy teaching); substituting into the similarity formula to calculate the comprehensive similarity of each student (e.g., student A has a similarity of 82%, student B has a similarity of 65%), and generating difference parameters (e.g., student A's "starting stroke concealing angle is too steep 13°" and "pen speed is too fast 1.3cm / s"; student B's "ending stroke lifting and pressing amplitude is less than 0.4mm" and "ink color diffusion is uneven, and the pressure in the middle of the stroke is too small").

[0043] During the teaching feedback and interaction phase (teacher-student collaboration), student feedback is as follows: The student's touchscreen displays a personalized difference report, presented in an "animated comparison + text prompts" format—the left side shows the standard horizontal stroke trajectory (red), and the right side shows the student's writing trajectory (blue), with differences highlighted in yellow; this is accompanied by text prompts, and a targeted demonstration video (such as a slow-motion replay of the initial stroke) plays simultaneously. Teacher control is also provided: The teacher's large screen displays the similarity scores and core differences of 30 students in a split-screen format. Clicking on student B's name allows viewing detailed difference parameters, and student B can be individually called via the voice broadcast unit. If the teacher discovers that 5 students share the common problem of "writing too fast," clicking "batch push" sends a "writing rhythm practice task" (including a standard speed metronome animation) to the desktops of these 5 students, and the common problem analysis is displayed on the teacher's large screen.

[0044] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0045] It should also be noted that 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 a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0046] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A calligraphy teaching method based on dynamic handwriting analysis, characterized in that, The method includes the following steps: Step S1: Collect dynamic handwriting data during the user's writing process, preprocess the dynamic handwriting data to remove noise data and fill in the missing pen stroke state data. Step S2: Extract handwriting feature parameters from the preprocessed dynamic handwriting data; Step S3: Match and analyze the extracted handwriting feature parameters with the preset standard calligraphy handwriting feature template to obtain the difference parameters between the user's handwriting and the standard handwriting; Step S4: Generate calligraphy teaching feedback information based on the difference parameters and send it to the user's terminal device.

2. The calligraphy teaching method based on dynamic handwriting analysis according to claim 1, characterized in that, In step S1, collecting dynamic handwriting data specifically includes: The acquisition device collects sensor data based on the integrated trajectory positioning sensor, pressure sensing unit, angle sensing unit, and ink volume detection unit. The timestamps of the data from each sensor are aligned by synchronizing the clock signal. Before data acquisition, the sensor baseline calibration algorithm is used to eliminate the inherent zero-point drift error of the equipment. During the acquisition process, the data validity is verified in real time, and abnormal data exceeding the reasonable threshold is removed. The collected dynamic handwriting data is transmitted to the data processing unit via a high-speed serial bus, and the transmission process employs a data packet verification mechanism.

3. The calligraphy teaching method based on dynamic handwriting analysis according to claim 1, characterized in that, In step S2, the handwriting feature parameters are extracted, specifically including: The stroke shape features are extracted by geometric modeling of the trajectory coordinate sequence, the writing trajectory is smoothed by Bezier curve fitting algorithm, and the quantitative values ​​of the starting stroke concealment angle and the ending stroke lifting and pressing amplitude are calculated by curve differentiation. The curvature extreme point detection determines the straightness of the stroke and the opening and closing angle of the pen tip. By analyzing the characteristics of pen stroke rhythm through time series analysis, sliding window filtering is applied to the writing speed sequence to extract the mean and variance of speed within a single stroke. The speed change rate at the turning point of the stroke is obtained through gradient calculation, and the time ratio parameter of the pressing and lifting action is statistically calculated based on the timestamp difference.

4. The calligraphy teaching method based on dynamic handwriting analysis according to claim 1, characterized in that, In step S2, the handwriting feature parameters include stroke shape features, pen stroke rhythm features, pen pressure distribution features, and ink color diffusion features.

5. The calligraphy teaching method based on dynamic handwriting analysis according to claim 4, characterized in that, The method further includes: extracting pen movement rhythm features using a joint calculation algorithm of pen movement speed and acceleration, wherein the calculation formula for real-time pen movement acceleration is as follows: Among them, a i v represents the real-time pen movement acceleration corresponding to the i-th sampling point, used to characterize the speed change trend during the lifting and pressing process; i v represents the real-time writing speed corresponding to the i-th sampling point; i+1 t represents the real-time writing speed corresponding to the (i+1)th sampling point; i t is the timestamp of the i-th sampling point; i+1 This is the timestamp of the (i+1)th sampling point.

6. The calligraphy teaching method based on dynamic handwriting analysis according to claim 4, characterized in that, The pressure-ink volume coupled feature extraction algorithm is used to obtain ink color diffusion features. The calculation formula is as follows: Where I(x,y) is the ink density value at coordinate (x,y); k is the ink volume coefficient, which is determined by the type of brush bristles and ink concentration used; P(x,y) is the brush pressure value at coordinate (x,y); v(x,y) is the real-time writing speed at coordinate (x,y); and d0 is the base ink value, which represents the ink base without additional pressure.

7. The calligraphy teaching method based on dynamic handwriting analysis according to claim 1, characterized in that, In step S3, a multi-dimensional feature weighted matching algorithm is used to calculate the similarity between the user's handwriting and the standard handwriting. Based on the similarity, the difference parameters between the user's handwriting and the standard handwriting are obtained. The similarity calculation formula is as follows: Where S is the overall similarity between the user's handwriting and the standard handwriting; n is the number of categories of handwriting features; w k Let A be the weight coefficient of the k-th class feature, satisfying that the sum of the feature weights is 1, obtained through training with a large number of calligraphy samples; m is the number of parameter dimensions included in the k-th class feature; A k,i B represents the i-th dimension parameter value of the k-th class feature of the user's handwriting. k,i The i-th dimension parameter value is the k-th feature of the standard handwriting template.

8. A calligraphy teaching system based on dynamic handwriting analysis, employing the calligraphy teaching method based on dynamic handwriting analysis as described in any one of claims 1-7, characterized in that, The system includes: The dynamic handwriting capture module is used to collect dynamic handwriting data during the user's writing process; The data preprocessing module is used to perform noise removal, missing data completion, and data standardization on the dynamic handwriting data. The feature extraction module is used to extract specific handwriting feature parameters from the preprocessed dynamic handwriting data; The matching analysis module is used to match and analyze the extracted handwriting feature parameters with standard calligraphy handwriting feature templates to obtain difference parameters; The teaching feedback module is used to generate targeted calligraphy teaching feedback information based on the aforementioned difference parameters.

9. A calligraphy teaching system based on dynamic handwriting analysis according to claim 8, characterized in that, The system also includes a standard handwriting template library, which stores standard calligraphy handwriting feature templates of different script styles and different calligraphic styles, and supports the addition, modification, deletion and categorized retrieval of templates.

10. A calligraphy teaching system based on dynamic handwriting analysis according to claim 8, characterized in that, The system also includes a user interaction module, which is used to receive the user's writing mode selection and font switching operation commands, display teaching feedback information and standard pen stroke demonstration data, and query, store and compare multiple versions of the user's historical handwriting data.

Images