Handwritten chinese character component evaluation method, device and equipment and storage medium

Abstract

The application discloses a handwritten Chinese character component evaluation method, device and equipment and a storage medium. The evaluation method comprises the following steps: a component composition query table corresponding to a Chinese character is constructed, and the component composition query table comprises a component composition sequence corresponding to the Chinese character construction; a stroke order query table corresponding to a Chinese character component is constructed, and the stroke order query table comprises a stroke order sequence corresponding to the component construction; handwritten stroke data of a collected Chinese character is taken as a training sample, a component composition sequence and a stroke order sequence corresponding to the training sample are taken as labels, and a component recognition model is trained; and an evaluation result of handwritten Chinese character stroke to be evaluated is obtained based on the component recognition model, the component composition query table and the stroke order query table. The application is suitable for users with different writing styles and writing habits, and can achieve high accuracy, so as to help the user to master the correct writing method of the Chinese character more quickly.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device, equipment, and storage medium for evaluating handwritten Chinese character components. Background Art

[0002] Chinese character components are the structural units composed of strokes and have the function of combining Chinese characters. Most people are used to remembering the writing methods of the strokes within the components and the combination methods between the components to remember the writing of the entire Chinese character. When learning Chinese character writing, timely error feedback can help learners quickly and accurately correct errors, so as to quickly master Chinese character writing. Some current automatic handwritten Chinese character correct / error evaluation methods or systems mostly make judgments from the perspectives of the overall number of strokes of Chinese characters, stroke types, stroke orders, the number of components, component types, etc., and return the judgment results to users. During the process of Chinese character writing learning by Chinese character beginners, there are many types of writing errors that may occur, including: missing strokes, extra strokes, connected strokes, incorrect stroke orders, wrong strokes, missing components, fewer components, incorrect components, etc., and the writing results may lead to multiple writing errors occurring simultaneously.

[0003] When a user writes Chinese characters, the occurrence of incorrect components is usually caused by incorrect strokes. For example, when the component "two" is written incorrectly as the component "ice point", it is because the strokes "horizontal, horizontal" are written as "dot, lift", that is, incorrect strokes lead to incorrect components; when the component "sun" is written as the component "mouth", it is because the strokes "vertical, horizontal fold, horizontal, horizontal" are written as "vertical, horizontal fold, horizontal", that is, fewer strokes lead to incorrect components. Current automatic handwritten Chinese character correct / error evaluation methods or systems usually separate the stroke correct / error evaluation from the component correct / error judgment, that is, perform evaluations separately from the stroke perspective and the component perspective, so it is difficult to give the correlation feedback between component errors and stroke errors, thus weakening the user's memory of the stroke composition within the components. Summary of the Invention

[0004] In view of the above technical problems, the present invention provides a method, device, equipment, and storage medium for evaluating handwritten Chinese character components. This method can find the corresponding relationship between strokes and components while predicting the component composition sequence of the currently written Chinese character, so that when an incorrect component occurs, the correlation between the incorrect component and the incorrect stroke can be found and corresponding feedback can be given to the user, thereby strengthening the user's memory of the stroke composition within the components.

[0005] Other features and advantages of the present disclosure will become apparent through the following detailed description, or be partially learned through the practice of the present disclosure.

[0006] According to one aspect of the present invention, a method for evaluating handwritten Chinese character components is provided. The evaluation method includes:

[0007] Construct a component composition lookup table for Chinese characters, the component composition lookup table including the component composition sequence corresponding to the construction of Chinese characters;

[0008] Construct a stroke order lookup table corresponding to Chinese character components, wherein the stroke order lookup table includes the stroke order sequence corresponding to the component construction;

[0009] The collected handwritten Chinese characters are used as training samples, and the component composition sequence and stroke order sequence corresponding to the training samples are used as labels to train a component recognition model.

[0010] Based on the component recognition model, the component composition lookup table, and the stroke order lookup table, the evaluation results of the handwritten Chinese characters to be evaluated are obtained.

[0011] Furthermore, the handwritten handwriting data includes a sequence of trajectory points for each stroke of the corresponding Chinese character, and the sequence of trajectory points includes the relationship between the trajectory points and the strokes.

[0012] Furthermore, the handwritten handwriting data is expressed as follows:

[0013]

[0014] Where n is the number of strokes in a Chinese character, ci is the number of trajectory points of the i-th stroke during writing, (x ij y ij In the sequence (xij, yij), xij and yij represent the coordinates of the j-th trajectory point of the i-th stroke in a Chinese character, i indicates that the current trajectory point belongs to the i-th stroke, and k indicates that the current trajectory point is the k-th trajectory point in the total trajectory point sequence. ij y ij , i, k) represents the relationship between trajectory points and strokes.

[0015] Furthermore, the component identification model is obtained based on a sequence-to-sequence model structure.

[0016] Furthermore, the step of obtaining the evaluation results of the handwritten Chinese characters to be evaluated based on the component recognition model, the component composition lookup table, and the stroke order lookup table includes:

[0017] The handwritten Chinese characters to be evaluated are analyzed to obtain the Chinese character body and the stroke type corresponding to each stroke;

[0018] Based on the component composition lookup table and the stroke order lookup table, obtain the correct component composition sequence and stroke order sequence of the handwritten Chinese character;

[0019] Based on the component recognition model, component prediction is performed on the handwritten Chinese character to obtain the correspondence between the component prediction results and the strokes;

[0020] The evaluation result is obtained by comparing the correspondence between the component prediction result and the stroke with the correct component composition sequence and the stroke sequence.

[0021] According to a second aspect of this disclosure, a handwritten Chinese character component evaluation device is provided, comprising: an information creation module, which is used to construct a component composition lookup table corresponding to a Chinese character, the component composition lookup table including a sequence of component compositions corresponding to the construction of the Chinese character, and a stroke order lookup table corresponding to the Chinese character components, the stroke order lookup table including a sequence of strokes corresponding to the construction of the components; a model generation module, which is used to train a component recognition model by using collected handwritten handwriting data of Chinese characters as training samples and using the component composition sequence and the stroke order sequence corresponding to the training samples as labels; and an evaluation module, which is used to obtain the evaluation result of the handwritten Chinese character handwriting to be evaluated based on the component recognition model, the component composition lookup table, and the stroke order lookup table.

[0022] According to a third aspect of this disclosure, a handwritten Chinese character component evaluation device is provided, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, cause the processor to: construct a component composition lookup table corresponding to a Chinese character, the component composition lookup table including a sequence of component compositions corresponding to the Chinese character construction; construct a stroke order lookup table corresponding to a Chinese character component, the stroke order lookup table including a sequence of strokes corresponding to the component construction; use collected handwritten handwriting data of Chinese characters as training samples, and use the component composition sequence and the stroke order sequence corresponding to the training samples as labels to train a component recognition model; and obtain an evaluation result of the handwritten Chinese character handwriting to be evaluated based on the component recognition model, the component composition lookup table, and the stroke order lookup table.

[0023] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, performs the evaluation method described above.

[0024] The technical solution disclosed herein has the following beneficial effects:

[0025] Predicting the composition sequence of Chinese characters based on component recognition models is applicable to users with different writing styles and habits, and can achieve a high accuracy rate.

[0026] By associating strokes with component recognition results, we can analyze the reasons for component errors from the perspective of strokes, thereby strengthening users' memory of the stroke composition within components and helping them to master the correct way of writing Chinese characters more quickly. Attached Figure Description

[0027] Figure 1 This is a flowchart of a handwritten Chinese character component evaluation method in the embodiments of this specification;

[0028] Figure 2 A flowchart of the method for evaluating handwritten Chinese characters using a component recognition model in the embodiments of the specification;

[0029] Figure 3 Example diagrams illustrating the evaluation of correct Chinese character writing in the embodiments of the instruction manual;

[0030] Figure 4 Example diagrams illustrating the evaluation of incorrect Chinese character writing in the embodiments of the instruction manual;

[0031] Figure 5 This is a schematic diagram of a handwritten Chinese character component evaluation device in an embodiment of this specification;

[0032] Figure 6 This specification describes a terminal device used to implement a method for evaluating handwritten Chinese character components in an embodiment of this specification.

[0033] Figure 7 This is a computer-readable storage medium used in the embodiments of this specification to implement a method for evaluating handwritten Chinese character components. Detailed Implementation

[0034] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0035] In addition, the accompanying drawings are only schematic illustrations of the present disclosure. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0036] As Figure 1 shown, an embodiment of this specification provides a method for evaluating handwritten Chinese character components. The execution subject of this method may be a terminal device, and the terminal device may be, for example, a mobile phone, a tablet computer, a personal computer, etc. This method may specifically include the following steps S101 to S104:

[0037] In step S101, a component composition query table corresponding to the Chinese character is constructed, and the component composition query table includes the component composition sequence corresponding to the construction of the Chinese character.

[0038] Among them, constructing a component composition query table for Chinese characters means constructing a corresponding component composition sequence for each Chinese character, and decomposing each Chinese character into a component sequence as the determination basis for whether a component is written wrongly. For example, for the Chinese character "件", its component composition sequence is "亻, 牛". When the component sequence written by the user is "彳, 牛", it can be determined that at least a component is written wrongly; when the component sequence written by the user is "口, 亻, 牛", it can be determined that at least a component is written too many; when the component sequence written by the user is "牛", it can be determined that at least a component is written too few.

[0039] In step S102, a stroke order query table corresponding to the Chinese character component is constructed, and the stroke order query table includes the stroke order sequence corresponding to the construction of the component.

[0040] Among them, constructing a component stroke order query table means constructing a corresponding stroke order for each component as the determination basis for whether a stroke in the component is written wrongly. For example, for the component "牛", its stroke order is "撇, 横, 横, 竖". When the stroke order of the component written by the user is "竖, 横, 横, 竖", it can be determined that at least a stroke is written wrongly; when the stroke order of the component written by the user is "撇, 竖, 横, 横", it can be determined that at least the stroke order is written wrongly; when the stroke order of the component written by the user is "撇, 横, 横, 竖, 横", it can be determined that at least a stroke is written too many; when the stroke order of the component written by the user is "横, 横, 竖", it can be determined that at least a stroke is written too few.

[0041] In step S103, the collected handwritten Chinese characters are used as training samples, and the component composition sequence and stroke sequence corresponding to the training samples are used as labels to train a component recognition model.

[0042] With sufficient training samples and labels composed of the component sequences of the current handwritten Chinese characters arranged in the writing order, the resulting component recognition model can automatically identify the type, components, and stroke order of the handwritten characters in subsequent evaluations.

[0043] As a supplement, the handwritten handwriting data includes a sequence of trajectory points for each stroke of the corresponding Chinese character, and the sequence of trajectory points includes the relationship between the trajectory points and the strokes.

[0044] Specifically, the handwritten handwriting data is expressed as follows:

[0045]

[0046] Where n is the number of strokes in a Chinese character, ci is the number of trajectory points of the i-th stroke during writing, (x ij y ij In the sequence (xij, yij), xij and yij represent the coordinates of the j-th trajectory point of the i-th stroke in a Chinese character, i indicates that the current trajectory point belongs to the i-th stroke, and k indicates that the current trajectory point is the k-th trajectory point in the total trajectory point sequence. ij y ij (i, k) represents the relationship between trajectory points and strokes. That is, based on this data recording format, the correspondence between any trajectory point and stroke in the total trajectory point sequence can be known.

[0047] In step S104, the evaluation results of the handwritten Chinese characters to be evaluated are obtained based on the component recognition model, the component composition lookup table, and the stroke order lookup table.

[0048] As a supplement, step S104 specifically includes steps S201-S204:

[0049] In step S201, the handwritten Chinese characters to be evaluated are analyzed to obtain the Chinese character body and the stroke type corresponding to each stroke.

[0050] The process involves obtaining the stroke order of the current handwritten Chinese character based on its handwriting data. This handwriting data can be obtained through hardware interaction such as writing tablets or touch screens. Then, the handwriting shape is input into a model or recognition software to obtain the current handwritten Chinese character and the stroke type corresponding to each stroke.

[0051] In step S202, based on the component composition lookup table and the stroke order lookup table, the correct component composition sequence and stroke order sequence of the handwritten Chinese character are obtained.

[0052] After the handwritten Chinese character is identified in the above steps, the query components can be called to form a query table and a stroke order query table, and the correct reference data for subsequent evaluation can be retrieved.

[0053] In step S203, based on the component recognition model, component prediction is performed on the handwritten Chinese character to obtain the correspondence between the component prediction result and the stroke.

[0054] The component recognition model can be based on a sequence-to-sequence model structure, and may include an encoder and a decoder. The encoder receives input features and performs deep feature extraction, while the decoder receives the deep features extracted by the encoder to predict the output sequence. In constructing the component recognition model, the encoder uses a multi-layer BiLSTM (Bidirectional Long Short-Term Memory) network to receive features and perform deep feature extraction. The decoder uses a multi-layer GRU (Gated Recurrent Unit) model with an attention mechanism to receive the deep features extracted by the encoder and predict the structural sequence.

[0055] When a component recognition model predicts component sequences, it can record the weights at each trajectory point during each decoding process. Based on the weights, it determines the trajectory points relied upon for each component prediction. Furthermore, by establishing the correspondence between trajectory points and strokes, it determines the strokes relied upon for component prediction, thus establishing the relationship between components and strokes.

[0056] In step S204, the correspondence between the component prediction result and the stroke is compared with the correct component composition sequence and the stroke sequence to obtain the evaluation result.

[0057] The evaluation results obtained through comparison include:

[0058] 1. By comparing the currently identified component sequence with the correct component sequence of the current Chinese character, it can be determined whether there are any component writing errors such as incorrect writing, too many components, or too few components in the writing of the Chinese character.

[0059] 2. Based on the correspondence between the currently identified components and strokes, compare it with the correct stroke order of each component to determine whether there are any errors in the writing of strokes within the component, such as incorrect stroke order, incorrect strokes, too many strokes, or too few strokes.

[0060] 3. Perform correlation analysis between component writing errors and stroke writing errors, and provide the analysis results back to the user.

[0061] Exemplary, a specific example is provided herein.

[0062] Given the target Chinese character "垡", according to the Chinese character component composition query table and the component stroke order query table, its correct component composition sequence is "亻, 戈, 土", and the correct Chinese character stroke order is "撇, 竖, 横, 斜钩, 撇, 点, 横, 竖, 横". Among them, the correct stroke order of the component "亻" is "撇, 竖", the correct stroke order of the component "戈" is "横, 斜钩, 撇, 点", and the correct stroke order of the component "土" is "横, 竖, 横".

[0063] As Figure 3 shown, Figure 3 is an example of correct writing. The actual writing stroke order therein is "撇, 竖, 横, 斜钩, 撇, 点, 横, 竖, 横", which is consistent with the correct stroke order. According to the component recognition model, the actual writing component sequence obtained by the user is "亻, 戈, 土", which is consistent with the correct component composition sequence.

[0064] As Figure 4 shown, Figure 4 is an example of incorrect writing. The actual writing stroke order therein is "撇, 撇, 竖, 横, 斜钩, 点, 横, 竖, 横". According to the recognition result of the component recognition model, the actual writing component sequence is "彳, 弋, 土". The writing stroke order of the component "彳" is "撇, 撇, 竖", the writing stroke order of the component "弋" is "横, 斜钩, 点", and the writing stroke order of the component "土" is "横, 竖, 横". Comparing the actual writing component sequence and the actual writing stroke order of each component with the correct component sequence and the correct writing stroke order of each component, it can be obtained that the user made a mistake in writing the component during the writing process, and the component "亻" was written as the component "彳" due to writing an extra stroke "撇", and the component "戈" was written as the component "弋" due to missing a stroke "撇".

[0065] Based on the same idea, as Figure 5 shown, an exemplary embodiment of the present disclosure further provides a handwritten Chinese character component evaluation device 500, including an information creation module 501. The information creation module 501 is used to construct a component composition query table corresponding to the Chinese character, and the component composition query table includes the component composition sequence corresponding to the Chinese character construction, and is used to construct a stroke order query table corresponding to the Chinese character component. The stroke order query table includes the stroke order sequence corresponding to the component construction; a model generation module 502. The model generation module 502 is used to use the handwritten handwriting data of the collected Chinese characters as training samples, and use the component composition sequence and the stroke order sequence corresponding to the training samples as labels to train and obtain a component recognition model; an evaluation module 503. The evaluation module 503 is used to obtain the evaluation result of the handwritten Chinese character handwriting to be evaluated based on the component recognition model, the component composition query table, and the stroke order query table.

[0066] The aforementioned handwritten Chinese character component evaluation device 500 predicts the composition sequence of Chinese character components based on a component recognition model. It is suitable for users with different writing styles and habits, achieving a high accuracy rate. By associating strokes with component recognition results, the causes of component errors can be analyzed from a stroke perspective, thereby strengthening the user's memory of the stroke composition within a component and helping them master the correct way to write Chinese characters more quickly.

[0067] The specific details of each module / unit in the above-mentioned device have been described in detail in the method section of the implementation. For any undisclosed details, please refer to the implementation content of the method section, and therefore will not be repeated here.

[0068] Based on the same idea, this specification also provides a handwritten Chinese character component evaluation device, such as... Figure 6 As shown.

[0069] The handwritten Chinese character component evaluation device can be the terminal device or server provided in the above embodiments.

[0070] The handwritten Chinese character component evaluation device can vary considerably due to differences in configuration or performance. It may include one or more processors 601 and memory 602, and the memory 602 may store one or more application programs or data. The memory 602 may include readable media in the form of volatile memory cells, such as random access memory (RAM) and / or cache memory cells, and may further include read-only memory cells. The application programs stored in the memory 602 may include one or more program modules (not shown in the figures), such program modules including but not limited to: operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Furthermore, the processor 601 may be configured to communicate with the memory 602 and execute a series of computer-executable instructions stored in the memory 602 on the handwritten Chinese character component evaluation device. The handwritten Chinese character component evaluation device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more I / O interfaces (input / output interfaces) 605, and one or more external devices 606 (e.g., keyboards, drawing tablets, Bluetooth devices, etc.). It can also communicate with one or more devices that enable user interaction with the device, and / or with any device that enables the device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed through I / O interfaces 605. Furthermore, the device can also communicate with one or more networks (e.g., local area networks (LANs)) through wired or wireless interfaces 604.

[0071] Specifically, in this embodiment, the handwritten Chinese character component evaluation device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the handwritten Chinese character component evaluation device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0072] A component composition lookup table is constructed for each Chinese character, including the component composition sequence corresponding to the Chinese character construction. A stroke order lookup table is constructed for each Chinese character component, including the stroke order sequence corresponding to the component construction. The collected handwritten handwriting data of Chinese characters is used as training samples, and the component composition sequence and stroke order sequence corresponding to the training samples are used as labels to train a component recognition model. Based on the component recognition model, the component composition lookup table, and the stroke order lookup table, the evaluation result of the handwritten Chinese character handwriting to be evaluated is obtained.

[0073] Based on the same idea, exemplary embodiments of this disclosure also provide a computer-readable storage medium storing a program product capable of implementing the methods described above. In some possible embodiments, various aspects of this disclosure can also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to the various exemplary embodiments of this disclosure.

[0074] refer to Figure 7 As shown, a program product 800 for implementing the above-described method according to an exemplary embodiment of the present disclosure is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0075] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0076] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0077] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0078] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0079] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the exemplary embodiments of this disclosure.

[0080] Furthermore, the above figures are merely illustrative representations of the processes included in the methods according to exemplary embodiments of this disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0081] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0082] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0083] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for evaluating handwritten Chinese character components, characterized in that, The evaluation methods include: Construct a component composition lookup table for Chinese characters, the component composition lookup table including the component composition sequence corresponding to the construction of Chinese characters; Construct a stroke order lookup table corresponding to Chinese character components, wherein the stroke order lookup table includes the stroke order sequence corresponding to the component construction; The collected handwritten Chinese characters are used as training samples, and the component composition sequence and stroke sequence corresponding to the training samples are used as labels to train a component recognition model. The handwritten handwriting data includes the trajectory point sequence of each stroke of the corresponding Chinese character, and the trajectory point sequence includes the relationship between trajectory points and strokes. The handwritten handwriting data is expressed as follows: Where n is the number of strokes in the Chinese character. c i represents the number of points on the trajectory of the i-th stroke during writing. middle xij and yij This represents the coordinates of the j-th trajectory point of the i-th stroke in a Chinese character, where i indicates that the current trajectory point belongs to the i-th stroke, and k indicates that the current trajectory point is the k-th trajectory point in the total sequence of trajectory points. This is represented as the relationship between trajectory points and strokes; Based on the component recognition model, the component composition lookup table, and the stroke order lookup table, the evaluation result of the handwritten Chinese character to be evaluated is obtained, including: analyzing the handwritten Chinese character to be evaluated to obtain the Chinese character body and the stroke type corresponding to each stroke; obtaining the correct component composition sequence and stroke order sequence of the handwritten Chinese character based on the component composition lookup table and the stroke order lookup table; predicting components of the handwritten Chinese character based on the component recognition model to obtain the correspondence between the component prediction result and the strokes; comparing the correspondence between the component prediction result and the strokes with the correct component composition sequence and stroke order sequence to obtain the evaluation result.

2. The method for evaluating handwritten Chinese character components according to claim 1, characterized in that, The component identification model is based on a sequence-to-sequence model structure.

3. A device for evaluating handwritten Chinese character components, comprising: The information creation module is used to construct a component composition lookup table for Chinese characters, which includes the component composition sequence corresponding to the construction of Chinese characters, and to construct a stroke order lookup table for Chinese character components, which includes the stroke order sequence corresponding to the component construction. A model generation module is used to train a component recognition model by using collected handwritten Chinese character data as training samples and the component composition sequence and stroke sequence corresponding to the training samples as labels. The handwritten handwriting data includes a sequence of trajectory points for each stroke of the corresponding Chinese character, and the sequence of trajectory points includes the relationship between trajectory points and strokes. The handwritten handwriting data is expressed as follows: Where n is the number of strokes in the Chinese character. c i represents the number of points on the trajectory of the i-th stroke during writing. middle xij and yij This represents the coordinates of the j-th trajectory point of the i-th stroke in a Chinese character, where i indicates that the current trajectory point belongs to the i-th stroke, and k indicates that the current trajectory point is the k-th trajectory point in the total sequence of trajectory points. This is represented as the relationship between trajectory points and strokes; The evaluation module is used to obtain the evaluation result of the handwritten Chinese character to be evaluated based on the component recognition model, the component composition lookup table, and the stroke order lookup table. This includes: analyzing the handwritten Chinese character to be evaluated to obtain the character body and the stroke type corresponding to each stroke; obtaining the correct component composition sequence and stroke order sequence of the handwritten Chinese character based on the component composition lookup table and the stroke order lookup table; predicting components of the handwritten Chinese character based on the component recognition model to obtain the correspondence between the component prediction result and the strokes; and comparing the correspondence between the component prediction result and the strokes with the correct component composition sequence and stroke order sequence to obtain the evaluation result.

4. A device for evaluating handwritten Chinese character components, comprising: processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Construct a component composition lookup table for Chinese characters, the component composition lookup table including the component composition sequence corresponding to the construction of Chinese characters; Construct a stroke order lookup table corresponding to Chinese character components, wherein the stroke order lookup table includes the stroke order sequence corresponding to the component construction; The collected handwritten Chinese characters are used as training samples, and the component composition sequence and stroke sequence corresponding to the training samples are used as labels to train a component recognition model. The handwritten handwriting data includes the trajectory point sequence of each stroke of the corresponding Chinese character, and the trajectory point sequence includes the relationship between trajectory points and strokes. The handwritten handwriting data is expressed as follows: Where n is the number of strokes in the Chinese character. c i represents the number of points on the trajectory of the i-th stroke during writing. middle xij and yij This represents the coordinates of the j-th trajectory point of the i-th stroke in a Chinese character, where i indicates that the current trajectory point belongs to the i-th stroke, and k indicates that the current trajectory point is the k-th trajectory point in the total sequence of trajectory points. This is represented as the relationship between trajectory points and strokes; Based on the component recognition model, the component composition lookup table, and the stroke order lookup table, the evaluation result of the handwritten Chinese character to be evaluated is obtained, including: analyzing the handwritten Chinese character to be evaluated to obtain the Chinese character body and the stroke type corresponding to each stroke; obtaining the correct component composition sequence and stroke order sequence of the handwritten Chinese character based on the component composition lookup table and the stroke order lookup table; predicting components of the handwritten Chinese character based on the component recognition model to obtain the correspondence between the component prediction result and the strokes; comparing the correspondence between the component prediction result and the strokes with the correct component composition sequence and stroke order sequence to obtain the evaluation result.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the handwritten Chinese character component evaluation method as described in any one of claims 1 to 2.

Images