A go wrong question practicing method and device, a storage medium and an equipment

Abstract

The application discloses a method and device for practicing go wrong questions, a storage medium and equipment. The method comprises the following steps: first, obtaining target go wrong question data answered incorrectly by a target user; then, determining a target go examination knowledge point to which the target go wrong question data belongs according to the target go wrong question data; next, determining a display node corresponding to the target go wrong question data according to a preset learning path in a go question library, the target go examination knowledge point and remaining question library data in the go question library; and further, displaying the target go wrong question data to the target user according to the display node corresponding to the target go wrong question data, so that the target user practices the target go wrong question again. It can be seen that the target go wrong question data is re-included in the remaining question library, and a node for displaying the target go wrong question data to the target user again is constructed, so that the target go wrong question can be actively displayed to the target user for practice in subsequent question brushing of the target user, and the learning quality of the target user is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, storage medium, and device for practicing Go mistakes. Background Technology

[0002] Existing electronic learning aids, such as learning machines and tablets, all have question banks to help users understand various knowledge points, such as those related to Go (the board game). This allows users to practice questions from these banks while learning Go, aiding in mastering various Go-related knowledge points. Some learning apps also offer similar functionality. Furthermore, to facilitate review of Go-related mistakes, these devices typically include a Go error log (such as an error notebook), where incorrect answers can be automatically entered or manually added by the user.

[0003] However, existing Go error notebooks or error databases do not actively display them to users; they can only passively wait for users to learn on their own. Users usually have low interest in error notebooks or error databases, which is not conducive to users eliminating weaknesses and improving their Go skills through Go error practice. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and device for practicing Go mistakes, which can actively display incorrect problems to users when they are practicing Go problems, thereby allowing users to actively practice Go mistakes once or multiple times, and thus improving the quality of users' Go learning.

[0005] This application provides a method for practicing Go (Weiqi) mistakes, including:

[0006] Obtain data on incorrect answers to target Go questions by target users;

[0007] Based on the target Go error data, determine the target Go knowledge points to which the target error data belongs;

[0008] Based on the preset learning path in the Go question bank, the target Go knowledge points to be tested, and the remaining question bank data in the Go question bank, determine the display node corresponding to the target Go wrong question data;

[0009] Based on the display node corresponding to the target Go incorrect problem data, the target Go incorrect problem data is displayed to the target user so that the target user can practice the target Go incorrect problem again.

[0010] In one possible implementation, determining the target Go knowledge point to which the target incorrect question data belongs based on the target incorrect question data includes:

[0011] The target Go incorrect question data is input into a pre-built Go knowledge point identification model to predict the target Go knowledge point to which the target incorrect question data belongs.

[0012] In one possible implementation, the Go knowledge point identification model is constructed as follows:

[0013] Obtain sample Go practice problem data;

[0014] Using the sample Go practice problem data and the target loss constraint function, the initial Go knowledge point recognition model is trained to obtain the Go knowledge point recognition model.

[0015] In one possible implementation, the initial Go knowledge point identification model is an end-to-end model consisting of an encoder and a decoder.

[0016] In one possible implementation, the method further includes:

[0017] Obtain verification Go practice problem data;

[0018] Input the verification Go practice question data into the Go knowledge point recognition model to obtain the Go knowledge point prediction result corresponding to the verification Go practice question data;

[0019] When the prediction result of the Go examination knowledge points of the verification Go practice question data is inconsistent with the annotation result of the Go examination knowledge points of the verification Go practice question data, the verification Go practice question data is used again as the sample Go practice question data to update the Go examination knowledge point recognition model.

[0020] In one possible implementation, determining the display node corresponding to the target Go incorrect question data based on the preset learning path in the Go question bank, the target Go knowledge points to be tested, and the remaining question bank data in the Go question bank includes:

[0021] Based on the target Go knowledge points to be tested, determine the position of the target Go incorrect questions in the remaining question bank data;

[0022] Based on the position of the target Go incorrect question data in the remaining question bank data and the preset learning path in the Go question bank, determine the display node corresponding to the target Go incorrect question data in the new remaining question bank data.

[0023] In one possible implementation, the display node corresponding to the target Go incorrect question data in the new remaining question bank data includes the time order and / or position order of the target Go incorrect question data in the new remaining question bank data.

[0024] This application also provides a Go (Weiqi) error correction practice device, including:

[0025] The first acquisition unit is used to acquire target Go problem data that the target user answered incorrectly.

[0026] The first determining unit is used to determine the target Go knowledge point to which the target Go incorrect question data belongs based on the target Go incorrect question data;

[0027] The second determining unit is used to determine the display node corresponding to the target Go incorrect question data based on the preset learning path in the Go question bank, the target Go knowledge points to be examined, and the remaining question bank data in the Go question bank.

[0028] The display unit is used to display the target Go incorrect problem data to the target user according to the display node corresponding to the target Go incorrect problem data, so that the target user can practice the target Go incorrect problem again.

[0029] In one possible implementation, the first determining unit is specifically used for:

[0030] The target Go incorrect question data is input into a pre-built Go knowledge point identification model to predict the target Go knowledge point to which the target incorrect question data belongs.

[0031] In one possible implementation, the device further includes:

[0032] The second acquisition unit is used to acquire sample Go practice problem data;

[0033] The training unit is used to train the initial Go knowledge point recognition model using the sample Go practice problem data and the target loss constraint function, so as to obtain the Go knowledge point recognition model.

[0034] In one possible implementation, the initial Go knowledge point identification model is an end-to-end model consisting of an encoder and a decoder.

[0035] In one possible implementation, the device further includes:

[0036] The third acquisition unit is used to acquire verification Go practice problem data;

[0037] The input unit is used to input the verification Go practice question data into the Go examination knowledge point recognition model to obtain the Go examination knowledge point prediction result corresponding to the verification Go practice question data.

[0038] The updating unit is used to update the Go knowledge point recognition model when the prediction result of the Go knowledge point of the verification Go practice question data is inconsistent with the annotation result of the Go knowledge point of the verification Go practice question data.

[0039] In one possible implementation, the second determining unit includes:

[0040] The first determining subunit is used to determine the position of the target Go incorrect question data in the remaining question bank data based on the target Go knowledge points to be examined.

[0041] The second determining subunit is used to determine the display node corresponding to the target Go incorrect question data in the new remaining question data based on the position of the target Go incorrect question data in the remaining question data and the preset learning path in the Go question bank.

[0042] In one possible implementation, the display node corresponding to the target Go incorrect question data in the new remaining question bank data includes the time order and / or position order of the target Go incorrect question data in the new remaining question bank data.

[0043] This application embodiment also provides a Go error correction practice device, including: a processor, a memory, and a system bus;

[0044] The processor and the memory are connected via the system bus;

[0045] The memory is used to store one or more programs, the one or more programs including instructions, which, when executed by the processor, cause the processor to perform any of the above-described methods for practicing Go mistakes.

[0046] This application also provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform any of the above-described methods for practicing Go mistakes.

[0047] This application also provides a computer program product, which, when run on a terminal device, causes the terminal device to execute any of the above-described methods for practicing Go mistakes.

[0048] This application provides a method, apparatus, storage medium, and device for practicing Go (Weiqi) incorrect answers. First, it acquires target Go incorrect answer data from a target user. Then, based on the target Go incorrect answer data, it determines the target Go knowledge point to which the incorrect answer data belongs. Next, based on the preset learning path in the Go question bank, the target Go knowledge point, and the remaining question bank data, it determines the display node corresponding to the target Go incorrect answer data. Finally, based on the display node corresponding to the target Go incorrect answer data, it displays the target Go incorrect answer data to the target user, allowing the target user to practice the incorrect Go answer again. As can be seen, because this application can re-include the target Go incorrect answer data from the target user into the remaining question bank, and construct a time or location node to re-display the incorrect answer to the target user based on its position in the new remaining question bank, it can actively display the target Go incorrect answer during subsequent practice, allowing the target user to actively practice once or multiple times, thereby improving the target user's learning quality. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 A flowchart illustrating a method for practicing incorrect Go problems provided in this application embodiment;

[0051] Figure 2 This is a schematic diagram illustrating the composition of a Go (Weiqi) error-correction practice device provided in an embodiment of this application. Detailed Implementation

[0052] Currently, when practicing Go, users typically practice using question banks on Go-related knowledge points provided by electronic learning devices such as learning machines and tablets. Furthermore, to facilitate review of incorrect Go questions, these electronic learning devices usually include a Go error database (such as an error notebook), which automatically records incorrect questions or allows users to manually enter them.

[0053] However, in actual use, users rarely actively review the incorrect questions in their error bank or notebook. They usually believe that they have mastered the questions they got wrong after reviewing the solution or answer once. Only when there is intervention from a third party (such as a teacher or parent) will users actively complete the Go questions they previously answered incorrectly in the error bank or notebook. After a user answers a question correctly, they usually automatically or manually remove the relevant questions from the error bank or notebook. However, one correction is not enough to determine whether the user has mastered the knowledge tested by the relevant questions. To confirm that the user has mastered the knowledge tested by the relevant questions, it is necessary to correct and review them periodically. Users' unwillingness or need for external intervention is taking advantage of the user's learning and will not achieve the goal of eliminating their weaknesses and improving their Go skills.

[0054] To address the aforementioned shortcomings, this application provides a method for practicing incorrect Go questions. First, it acquires data on incorrectly answered Go questions from a target user. Then, based on this data, it determines the target Go knowledge point to which the incorrect questions pertain. Next, based on the preset learning path in the Go question bank, the target Go knowledge point, and the remaining question bank data, it determines the corresponding display node for the incorrect Go questions. Finally, based on the display node corresponding to the incorrect Go questions, it displays the incorrect Go questions to the target user, allowing them to practice the incorrect questions again.

[0055] As can be seen, since the embodiments of this application can re-include the target Go questions that the target user answered incorrectly into the remaining question bank, and construct the time or location node to display them to the target user again based on the position of the incorrect questions in the new remaining question bank, the target Go questions can be actively displayed to the target user in subsequent practice, allowing the target user to actively practice once or multiple times, thereby improving the learning quality of the target user.

[0056] 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.

[0057] First Embodiment

[0058] See Figure 1 This is a flowchart illustrating a method for practicing Go mistakes according to this embodiment. The method includes the following steps:

[0059] S101: Obtain the target Go problem data that the target user answered incorrectly.

[0060] In this embodiment, any Go question answered incorrectly by a target user while practicing Go can be defined as the target Go question data. This embodiment does not limit the language type of the target Go question data. For example, the target Go question data can be Chinese data or English data, etc. Furthermore, this embodiment does not limit the length of the target Go question data. For example, the target Go question data can be sentence text data or paragraph text, etc.

[0061] In this application, the specific content of the target user's incorrectly answered Go questions is not limited. It can be the question stem data of questions that the target user did not answer according to the standard or answered incorrectly when practicing Go questions in the Go question bank. The target user's practice in the Go question bank refers to practicing questions related to specific knowledge points in Go, and the specific content of the question bank is not limited.

[0062] S102: Based on the target Go incorrect question data, determine the target Go knowledge points to which the target incorrect question data belongs.

[0063] In this embodiment, after obtaining the target user's incorrect Go question data through step S101, the target Go knowledge point to which the incorrect question data belongs can be determined based on the target Go question data, so as to execute the subsequent step S103.

[0064] Specifically, one possible implementation is that after obtaining the target user's incorrect answer to a Go question, the target Go question data can be input into a pre-built Go knowledge point recognition model to predict the target Go knowledge point to which the incorrect answer data belongs.

[0065] It should be noted that the specific structure and detection process of the Go knowledge point recognition model can be set according to the actual situation, and this embodiment does not limit it.

[0066] Next, this embodiment will introduce the construction process of the Go examination knowledge point recognition model. One optional implementation method is that the construction process of the Go examination knowledge point recognition model may specifically include: firstly, obtaining sample Go practice question data, and then using the sample Go practice question data and the target loss constraint function to train the initial Go examination knowledge point recognition model to obtain the Go examination knowledge point recognition model.

[0067] Specifically, in this implementation, a significant amount of preparatory work is required to construct the Go knowledge point recognition model. First, a large amount of practice questions related to Go knowledge points needs to be collected as sample Go practice questions to form the model training data. For example, a large amount of Go practice questions can be collected beforehand, such as practice questions related to knowledge points for each amateur dan level (1-8 dan) from low to high, or practice questions related to knowledge points for each professional dan level (1-dan, 2-dan, ..., 8-dan, 9-dan) from low to high. These can serve as sample Go practice questions to form the model training data, and the corresponding knowledge point annotations for these sample Go practice questions are manually labeled. Next, the initial Go knowledge point recognition model can be trained based on these sample Go practice questions, the corresponding knowledge point annotations, and the target loss constraint function, thereby generating the Go knowledge point recognition model.

[0068] One possible implementation is that the initial Go knowledge point identification model can be (but is not limited to) an end-to-end model consisting of an encoder and a decoder.

[0069] Specifically, during model training, a sample set of Go practice questions can be extracted from the training data as the model input, and the corresponding knowledge point recognition results can be used as the output. Multiple rounds of model training are performed, and the knowledge point recognition results obtained in each round of training are compared with the corresponding manually labeled results. The model parameters are updated based on the differences between the two until the preset conditions are met, such as the target loss function being very small and basically unchanged. Then, the update of the model parameters is stopped, the training of the Go knowledge point recognition model is completed, and a well-trained Go knowledge point recognition model is generated.

[0070] Based on this, after training and generating a Go knowledge point recognition model using sample Go practice question data, the generated Go knowledge point recognition model can be further validated using verification Go practice question data. The specific validation process may include the following steps (1)-(3):

[0071] Step (1): Obtain verification Go practice problem data.

[0072] In this embodiment, in order to verify the Go knowledge point recognition model, it is first necessary to obtain verification Go practice question data. The verification Go practice question data refers to Go practice question data that can be used to perform the Go knowledge point recognition model. After obtaining these verification Go practice question data and the Go knowledge point tags corresponding to each verification Go practice question data, the subsequent steps (2) can be performed.

[0073] Step (2): Input the verification Go practice question data into the Go examination knowledge point recognition model to obtain the prediction results of the Go examination knowledge points corresponding to the verification Go practice question data.

[0074] After obtaining the verification Go practice question data through step (1), the verification Go practice question data can be further input into the Go examination knowledge point recognition model to obtain the Go examination knowledge point prediction result corresponding to the verification Go practice question data, which can then be used to execute the subsequent step (3).

[0075] Step (3): When the prediction results of the Go examination knowledge points of the verification Go practice question data are inconsistent with the annotation results of the Go examination knowledge points of the verification Go practice question data, the verification Go practice question data is used again as the sample Go practice question data to update the Go examination knowledge point recognition model.

[0076] After obtaining the prediction result of the Go examination knowledge points corresponding to the verification Go practice question data through step (2), if the prediction result is inconsistent with the Go examination knowledge point labeling result (such as manually labeled Go examination knowledge point labels) to which the verification Go practice question data belongs, the verification Go practice question data can be used again as sample Go practice question data to update the parameters of the Go examination knowledge point recognition model.

[0077] Through the above embodiments, the Go examination knowledge point recognition model can be effectively verified using verification Go practice question data. When the predicted Go examination knowledge point results of the verification Go practice question data are inconsistent with the actual Go examination knowledge point recognition results corresponding to the verification Go practice question data (such as manually labeled Go examination knowledge point labels), the Go examination knowledge point recognition model can be adjusted and updated in a timely manner, thereby helping to improve the recognition accuracy and precision of the Go examination knowledge point recognition model.

[0078] S103: Based on the preset learning path in the Go question bank, the target Go knowledge points to be tested, and the remaining question bank data in the Go question bank, determine the display node corresponding to the target Go wrong question data.

[0079] In this embodiment, after determining the target Go knowledge point to which the target wrong question data belongs through step S102, the display node corresponding to the target Go wrong question data can be further determined based on the preset learning path in the Go question bank, the target Go knowledge point, and the remaining question bank data in the Go question bank (referring to the set of unanswered questions in the Go question bank where the wrong question data answered by the target user is located), so as to execute the subsequent step S104.

[0080] The preset learning paths in a Go problem bank refer to the patterns or methods used to present the problems. A typical Go problem bank contains a large number of problems, which can be presented in order of knowledge points from beginner to advanced, or in a random order, or all knowledge points can be covered in a single response. Furthermore, the preset learning paths in the Go problem bank can be system defaults, user-defined paths, or paths based on existing memorization methods (such as the Ebbinghaus forgetting curve).

[0081] Specifically, one possible implementation is that, after determining the target Go knowledge point to which the target wrong question data belongs, the position of the target Go wrong question data in the remaining question bank data can be determined first based on the target Go knowledge point. Then, based on the position of the target Go wrong question data in the remaining question bank data and the preset learning path in the Go question bank, the display node corresponding to the target Go wrong question data in the new remaining question bank data can be determined (including but not limited to the time order and / or position order of the target Go wrong question data in the new remaining question bank data).

[0082] The display node corresponding to the target Go incorrect question data in the new remaining question bank data refers to the chronological and / or positional order in which the target Go incorrect question data is displayed after merging the target Go incorrect question data and the remaining question bank data into a new remaining question bank data. There can be only one display node (i.e., displayed only once) or multiple display nodes (i.e., displayed multiple times), with no limit on the specific number. The chronological order in which the target Go incorrect question data is displayed in the new remaining question bank data can include the normal chronological display order of each question in the remaining question bank and the specific chronological position of the target Go incorrect question data. The positional order in which the target Go incorrect question data is displayed in the new remaining question bank data can be the position of the knowledge point being tested in the target Go game.

[0083] It should be noted that each question in the Go question bank tests several different knowledge points. Questions testing the same type of knowledge point, the same knowledge point, or the same level of knowledge are usually grouped together. Therefore, determining the position of the target Go incorrect question data within the remaining question bank data refers to using a preset similarity calculation method (such as text similarity or image similarity calculation) to determine which questions in the remaining question bank data belong to the same type of question, the same knowledge point, or the same level of knowledge point as the target Go incorrect question. Then, based on the location of similar questions, the appropriate insertion position can be determined.

[0084] S104: Based on the display node corresponding to the target Go incorrect problem data, display the target Go incorrect problem data to the target user so that the target user can practice the target Go incorrect problems again.

[0085] In this embodiment, after determining the display node corresponding to the target Go incorrect problem data (including but not limited to the time order and / or position order of the target Go incorrect problem data in the new remaining problem bank data) through step S103, the target Go incorrect problem data can be actively displayed to the target user again (multiple times at a time) according to the display node corresponding to the target Go incorrect problem data, in the corresponding time order and / or position order, so that the target user can practice the target Go incorrect problem again (multiple times at a time), thereby improving the target user's learning quality of Go.

[0086] In summary, this embodiment provides a method for practicing Go incorrect questions. First, it acquires data on incorrectly answered Go questions from a target user. Then, based on this data, it determines the target Go knowledge point to which the incorrect question belongs. Next, based on the preset learning path in the Go question bank, the target Go knowledge point, and the remaining question bank data, it determines the display node corresponding to the incorrect question. Finally, based on the display node, it displays the incorrect Go question to the target user, allowing them to practice the incorrect question again. As can be seen, this embodiment can re-include incorrectly answered Go questions from the target user into the remaining question bank and construct a time or location node to re-display the incorrect question to the target user based on its position in the new remaining question bank. This allows the incorrect question to be actively displayed during subsequent practice sessions, enabling the target user to actively practice once or multiple times, thereby improving the learning quality of the target user.

[0087] Second Embodiment

[0088] This embodiment will introduce a Go error correction practice device; please refer to the above method embodiment for related content.

[0089] See Figure 2 This is a schematic diagram of the composition of a Go error correction practice device provided in this embodiment. The device 200 includes:

[0090] The first acquisition unit 201 is used to acquire target Go incorrect questions data that the target user answered incorrectly.

[0091] The first determining unit 202 is used to determine the target Go knowledge point to which the target wrong question data belongs based on the target wrong question data;

[0092] The second determining unit 203 is used to determine the display node corresponding to the target Go incorrect question data based on the preset learning path in the Go question bank, the target Go knowledge points to be examined, and the remaining question bank data in the Go question bank.

[0093] The display unit 204 is used to display the target Go incorrect problem data to the target user according to the display node corresponding to the target Go incorrect problem data, so that the target user can practice the target Go incorrect problem again.

[0094] In one implementation of this embodiment, the first determining unit 202 is specifically used for:

[0095] The target Go incorrect question data is input into a pre-built Go knowledge point identification model to predict the target Go knowledge point to which the target incorrect question data belongs.

[0096] In one implementation of this embodiment, the apparatus further includes:

[0097] The second acquisition unit is used to acquire sample Go practice problem data;

[0098] The training unit is used to train the initial Go knowledge point recognition model using the sample Go practice problem data and the target loss constraint function, so as to obtain the Go knowledge point recognition model.

[0099] In one implementation of this embodiment, the initial Go knowledge point recognition model is an end-to-end model consisting of an encoder and a decoder.

[0100] In one implementation of this embodiment, the apparatus further includes:

[0101] The third acquisition unit is used to acquire verification Go practice problem data;

[0102] The input unit is used to input the verification Go practice question data into the Go examination knowledge point recognition model to obtain the Go examination knowledge point prediction result corresponding to the verification Go practice question data.

[0103] The updating unit is used to update the Go knowledge point recognition model when the prediction result of the Go knowledge point of the verification Go practice question data is inconsistent with the annotation result of the Go knowledge point of the verification Go practice question data.

[0104] In one implementation of this embodiment, the second determining unit 203 includes:

[0105] The first determining subunit is used to determine the position of the target Go incorrect question data in the remaining question bank data based on the target Go knowledge points to be examined.

[0106] The second determining subunit is used to determine the display node corresponding to the target Go incorrect question data in the new remaining question data based on the position of the target Go incorrect question data in the remaining question data and the preset learning path in the Go question bank.

[0107] In one implementation of this embodiment, the display node corresponding to the target Go incorrect question data in the new remaining question bank data includes the time order and / or position order of the target Go incorrect question data in the new remaining question bank data.

[0108] Furthermore, this application embodiment also provides a Go error correction practice device, including: a processor, a memory, and a system bus;

[0109] The processor and the memory are connected via the system bus;

[0110] The memory is used to store one or more programs, the one or more programs including instructions, which, when executed by the processor, cause the processor to perform any of the above-described implementations of the Go error-solving practice method.

[0111] Furthermore, embodiments of this application also provide a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to execute any of the above-described methods for practicing Go incorrect problems.

[0112] Furthermore, this application also provides a computer program product, which, when run on a terminal device, causes the terminal device to execute any of the above-described methods for practicing Go mistakes.

[0113] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0114] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0115] It should also be noted that, in this document, relational terms such as "first" and "second" are used only 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. Furthermore, 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 limitations, 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.

[0116] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for practicing incorrect Go problems, characterized in that, include: Obtain data on incorrect answers to target Go questions by target users; Based on the target Go error data, determine the target Go knowledge points to which the target Go error data belongs; Based on the target Go knowledge points, a preset similarity calculation method is used to determine which questions in the target Go incorrect questions data and the remaining question bank data belong to the same type of questions, the same knowledge points, or the same knowledge level. Then, based on the location of similar questions, a reasonable insertion position is determined as the position of the target Go incorrect questions data in the remaining question bank data. Based on the position of the target Go incorrect question data in the remaining question bank data and the preset learning path in the Go question bank, the display node corresponding to the target Go incorrect question data in the new remaining question bank data is determined; the display node corresponding to the target Go incorrect question data in the new remaining question bank data includes the positional order of the target Go incorrect question data in the new remaining question bank data; Based on the display node corresponding to the target Go incorrect problem data, the target Go incorrect problem data is displayed to the target user so that the target user can practice the target Go incorrect problem again.

2. The method according to claim 1, characterized in that, The step of determining the target Go knowledge point to which the target Go error data belongs based on the target Go error data includes: The target Go incorrect question data is input into a pre-built Go knowledge point identification model to predict the target Go knowledge point to which the target incorrect question data belongs.

3. The method according to claim 2, characterized in that, The Go knowledge point identification model is constructed as follows: Obtain sample Go practice problem data; Using the sample Go practice problem data and the target loss constraint function, the initial Go knowledge point recognition model is trained to obtain the Go knowledge point recognition model.

4. The method according to claim 3, characterized in that, The initial Go knowledge point identification model is an end-to-end model consisting of an encoder and a decoder.

5. The method according to claim 3, characterized in that, The method further includes: Obtain verification Go practice problem data; The verification Go practice question data is input into the Go knowledge point recognition model to obtain the Go knowledge point prediction result corresponding to the verification Go practice question data. When the prediction result of the Go examination knowledge points of the verification Go practice question data is inconsistent with the annotation result of the Go examination knowledge points of the verification Go practice question data, the verification Go practice question data is used again as the sample Go practice question data to update the Go examination knowledge point recognition model.

6. A Go (Weiqi) error correction practice device, characterized in that, include: The first acquisition unit is used to acquire target Go problem data that the target user answered incorrectly. The first determining unit is used to determine the target Go knowledge point to which the target Go incorrect question data belongs based on the target Go incorrect question data; The second determining unit is used to determine the display node corresponding to the target Go incorrect question data based on the preset learning path in the Go question bank, the target Go knowledge points to be examined, and the remaining question bank data in the Go question bank. The display unit is used to display the target Go incorrect problem data to the target user according to the display node corresponding to the target Go incorrect problem data, so that the target user can practice the target Go incorrect problem again; The second determining unit includes: The first determining subunit is used to determine, based on the target Go knowledge points being examined, which questions in the target Go incorrect question data and the remaining question bank data belong to the same type of question, the same knowledge point, or the same knowledge level of knowledge points, through a preset similarity calculation method, and then determine a reasonable insertion position based on the location of similar questions, as the position of the target Go incorrect question data in the remaining question bank data; The second determining subunit is used to determine the display node corresponding to the target Go incorrect question data in the new remaining question data based on the position of the target Go incorrect question data in the remaining question data and the preset learning path in the Go question bank; the display node corresponding to the target Go incorrect question data in the new remaining question data includes the position order of the target Go incorrect question data in the new remaining question data.

7. A Go (Weiqi) error correction practice device, characterized in that, include: Processor, memory, system bus; The processor and the memory are connected via the system bus; The memory is used to store one or more programs, the one or more programs including instructions that, when executed by the processor, cause the processor to perform the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the method described in any one of claims 1-5.

Images