Abnormal test question processing method in test question bank, learning machine and storage medium

Abstract

The invention discloses a method for processing abnormal test questions in a test question bank, a learning machine and a storage medium, and the method comprises the steps: receiving an access request of test question data in the test question bank; screening a corresponding target test question set from a test question bank according to the access request; and performing rich text content recognition on the test questions in the target test question set channel by channel, filtering the recognized abnormal test questions, and feeding back the recognized normal test questions to the access request for display. The abnormal test questions in the test question bank are processed on the basis of rich text content recognition, when the user opens the application, in the process that the user requests the test question bank data, rich text content recognition is executed, the abnormal test questions are found and repaired in time, more and more correct test questions in the test question bank and less and less abnormal questions exist, and the user experience is improved. And the probability of providing the abnormal test questions for the user becomes smaller and smaller, so that the user experience is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of learning machines, and specifically provides a method for processing abnormal questions in a question bank, a learning machine, and a storage medium. Background Art

[0002] With the development of educational informatization, intelligent learning machines, as a kind of intelligent educational auxiliary tool, have received extensive attention and application. The learning applications in learning machines provide the most convenient learning tools for learning.

[0003] Behind the learning machines on the market, there is a vast question bank, which is also the core requirement for users to choose learning machines. Moreover, the data in the question bank needs to be continuously increased and updated to better meet the usage needs of users. Therefore, learning machine service providers need to expand the question bank for the question bank. The existing methods for expanding the question bank include automatic script methods, as well as manual entry and manual review. When using the manual entry and manual review methods to expand the question bank, the quality of the expanded questions is high, but the efficiency is low and the cost is high. When using the automatic script method to expand the question bank, a large number of questions can be expanded in a short time, with extremely high efficiency and extremely low cost, but the quality of the questions cannot be guaranteed. Due to the diverse ways of expanding the question bank, the quality of the questions in the question bank is uneven, and there are inevitably some abnormal questions in the question bank, such as incomplete question stems, incorrect analysis, and incorrect answers. Once these abnormal questions are provided to users, it will greatly affect the learning experience of users, reduce the trust of users in learning machines, lead to emotional excitement of users, and increase the number of customer complaints.

[0004] Therefore, in order to manage the abnormal questions in the question bank, avoid providing abnormal questions to users as much as possible, and improve the user experience and satisfaction, the present invention patent is specifically proposed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a method for processing abnormal questions in a question bank, a learning machine, and a storage medium. By a series of actions or steps, abnormal questions are discovered, and the question bank is informed to quickly repair the abnormal questions, reducing the probability of users encountering abnormal questions and greatly reducing the impact on the user learning experience. The technical solution of the present invention is applicable to various educational products such as, but not limited to, learning machines, mobile phones, and intelligent AIs.

[0006] Specifically, the following technical solutions are adopted:

[0007] In a first aspect, the present invention provides a method for processing abnormal questions in a question bank, including:

[0008] Receiving an access request for question data in the question bank;

[0009] Screen the corresponding target question set from the question bank according to the access request;

[0010] For each question in the target question set, perform rich text content recognition, filter out the abnormal questions, and feed back the passed normal questions to the access request for display.

[0011] As an optional implementation manner of the present invention, in a method for processing abnormal questions in a question bank of the present invention, the performing rich text content recognition on each question in the target question set includes:

[0012] Obtain the rich text content in the question;

[0013] Filter out the target recognition information in the rich text content, and judge whether each target recognition information meets the preset conditions;

[0014] If each target recognition information meets the preset conditions, it is judged as a normal question. If there is target recognition information that does not meet the preset conditions, it is judged as an abnormal question.

[0015] As an optional implementation manner of the present invention, in a method for processing abnormal questions in a question bank of the present invention, the filtering out the target recognition information in the rich text content and judging whether each target recognition information meets the preset conditions includes:

[0016] The filtering out the target recognition information in the rich text content includes picture information, and / or audio information, and / or video information, and / or keyword information;

[0017] Judge whether the picture information, and / or audio information, and / or video information is available, and / or judge whether all keywords in the preset keyword set are covered in the keyword information.

[0018] As an optional implementation manner of the present invention, in a method for processing abnormal questions in a question bank of the present invention, judging whether the picture information, and / or audio information, and / or video information is available includes:

[0019] According to the picture information, and / or audio information, and / or video information, obtain the format of the picture, and / or audio, and / or video, and judge whether the format conforms to the preset format set of the picture, and / or audio, and / or video;

[0020] According to the picture information, and / or audio information, and / or video information, obtain the storage space of the picture, and / or audio, and / or video, and judge whether the storage space conforms to the preset storage space threshold of the picture, and / or audio, and / or video;

[0021] Obtain the image resolution of the picture, and / or audio, and / or video based on the picture information, and / or audio information, and / or video information, and determine whether the image resolution meets the preset image resolution threshold of the picture, and / or audio, and / or video.

[0022] As an alternative embodiment of the present invention, in a method for processing abnormal test questions in a test question bank of the present invention, the filtering process of the identified abnormal test questions includes:

[0023] Record the test question ID of the abnormal test question and report it to the server for summarization of abnormal test questions.

[0024] As an alternative embodiment of the present invention, in a method for processing abnormal test questions in a test question bank of the present invention, after the identified normal test questions are fed back to the access request for display, it includes:

[0025] Obtain the feedback information of the user during the use of the normal test questions, and submit the feedback information and the test question ID to the server for summarization of feedback abnormal test questions;

[0026] The feedback information includes problems with the question of the test question, problems with the answer of the test question, problems with the analysis of the test question, and problems with the multimedia information of the test question.

[0027] As an alternative embodiment of the present invention, a method for processing abnormal test questions in a test question bank of the present invention includes:

[0028] The server sorts out the summarized abnormal test questions, structures them into an array, and sends them to the operation or teaching and research personnel for repair processing;

[0029] Receive the submission request of the abnormal test questions repaired by the operation or teaching and research personnel, perform rich text content recognition on the repaired abnormal test questions, and re-enter the test question bank after passing the recognition, and return to the operation or teaching and research personnel for re-repair processing if the recognition fails.

[0030] As an alternative embodiment of the present invention, a method for processing abnormal test questions in a test question bank of the present invention includes:

[0031] The server monitors the summarized abnormal test questions;

[0032] When a submission request for repairing an abnormal test question from the operation or teaching and research personnel is not received for a certain abnormal test question within the preset time threshold, then delete the abnormal test question from the test question bank;

[0033] Or when feedback information indicating that a certain abnormal test question cannot be repaired is received from the operation or teaching and research personnel, then delete the abnormal test question from the test question bank.

[0034] In a second aspect, the present invention provides a learning machine that adopts the method for processing abnormal questions in the question bank, including:

[0035] An input module that receives an access request for question data in the question bank;

[0036] A question bank module that filters a corresponding target question set from the question bank according to the access request;

[0037] An abnormal question recognition module that performs rich text content recognition on each question in the target question set, filters the recognized abnormal questions, and feeds back the normal questions that pass the recognition to the access request for display.

[0038] In a third aspect, the present invention provides a computer-readable recording medium storing a computer-executable program, which when executed, implements the method for processing abnormal questions in a question bank.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] The method for processing abnormal questions in a question bank of the present invention realizes the processing of abnormal questions in the question bank through rich text content recognition. When the user opens the application, during the process of the user requesting question bank data, rich text content recognition will be performed, abnormal questions will be found, and the abnormal questions will be repaired in a timely manner, making the number of correct questions in the question bank increase and the number of abnormal questions decrease, and the probability of abnormal questions provided to the user also decreases, greatly improving the user experience.

[0041] The method for processing abnormal questions in a question bank of the present invention will display the questions to the user after the questions pass rich text content recognition. At the same time, when the user uses the questions, if it is found that there are problems with the question title, the answer to the question, the analysis of the question, and the multimedia information of the question, then the question is an abnormal question, and the user can give feedback on the abnormal question. The server records and summarizes the abnormal questions feedback by the user for repair processing.

[0042] The method for processing abnormal questions in a question bank of the present invention realizes the governance scheme for abnormal questions in the question bank through an algorithm based on rich text content recognition and feedback. When the user opens the application, during the process of the user requesting question bank data, the algorithm of rich text content recognition and feedback will be executed, abnormal questions will be found, and the abnormal questions will be repaired in a timely manner, making the accuracy rate of the question bank higher and higher, the number of abnormal questions less and less, and the number of abnormal questions provided to the user also less and less, greatly improving the user experience.

[0043] The present invention also provides a learning machine that adopts the method for processing abnormal test questions in the test question bank, and designs an algorithm based on rich text content recognition and feedback to implement a content wrong-question governance solution. This solution can be used in a variety of educational products such as, but not limited to, learning machines, mobile phones, and intelligent AIs. This strategy is the most advanced implementation strategy on the market and is of great significance for future strategies to improve user experience by implementing a content wrong-question governance solution based on rich text content recognition and feedback. This solution has the advantages of simple implementation, stability, and good user experience. This solution can also be extended for use in other similar scenarios. Brief Description of the Drawings

[0044] Figure 1 Flowchart of a method for processing abnormal test questions in the test question bank according to Embodiment 1 of the present invention;

[0045] Figure 2 Schematic structural diagram of an electronic device according to Embodiment 2 of the present invention;

[0046] Figure 3 Schematic diagram of a computer-readable recording medium according to Embodiment 2 of the present invention. Detailed Description of the Embodiments

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention.

[0048] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the present invention claimed, but is merely representative of some embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0049] It should be noted that, without conflict, the embodiments in the present invention and the features and technical solutions in the embodiments may be combined with each other.

[0050] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0051] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper" and "lower" is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is habitually placed during use, or the orientation or positional relationship commonly understood by those skilled in the art. Such terms are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the present invention. In addition, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0052] Embodiment 1

[0053] See Figure 1 As shown, a method for processing abnormal test questions in a test question bank of this embodiment includes:

[0054] Receiving an access request for test question data in the test question bank;

[0055] Screening a corresponding target test question set from the test question bank according to the access request;

[0056] For each test question in the target test question set, perform rich text content recognition, filter out the identified abnormal test questions, and feedback the recognized normal test questions to the access request for display.

[0057] This embodiment realizes the processing of abnormal test questions in the test question bank based on rich text content recognition. When the user opens the application and requests test question bank data, rich text content recognition will be performed, abnormal test questions will be found, and the abnormal test questions will be repaired in a timely manner, so that the number of correct test questions in the test question bank is increasing, the number of abnormal questions is decreasing, and the probability of abnormal test questions provided to the user is also decreasing, greatly improving the user experience.

[0058] The rich text content recognition in this embodiment is to recognize the rich text content in the test questions. The rich text content is a text format that contains rich formats and styles. The test questions not only contain text format content, but also contain picture format content, and even include audio format content, video format content, etc.

[0059] Furthermore, in a method for processing abnormal test questions in a test question bank of this embodiment, the step of performing rich text content recognition on each test question in the target test question set includes:

[0060] Obtaining the rich text content in the test question;

[0061] Filtering out the target recognition information in the rich text content and determining whether each target recognition information meets the preset conditions;

[0062] If all the target recognition information meets the preset conditions, it is determined as a normal test question. If there is target recognition information that does not meet the preset conditions, it is determined as an abnormal test question.

[0063] In this embodiment, through the preset conditions, the target recognition information is identified from the rich text content, and it is determined whether the target recognition information meets the preset conditions, so as to determine the abnormal test questions. The target recognition information in this embodiment is the information in the rich text content that is relatively easy to be recognized. In this way, it is beneficial to simply and quickly recognize the target recognition information and make a timely judgment on whether it is an abnormal test question.

[0064] Specifically, in a method for processing abnormal test questions in a test question database of this embodiment, the filtering out of the target recognition information in the rich text content and determining whether each target recognition information meets the preset conditions includes:

[0065] The filtering out of the target recognition information in the rich text content includes picture information, and / or audio information, and / or video information, and / or keyword information;

[0066] Determine whether the picture information, and / or audio information, and / or video information is available, and / or determine whether all the keywords in the preset keyword set are covered in the keyword information.

[0067] Since the picture information, and / or audio information, and / or video information in the rich text content can be easily recognized, the picture information, and / or audio information, and / or video information is selected as the target recognition information for judgment. Moreover, once the test question contains picture information, and / or audio information, and / or video information, the picture information, and / or audio information, and / or video information must be available to ensure that the test question is a normal test question and the user can use it normally; if the picture information, and / or audio information, and / or video information is not available, it means that the test question is an abnormal test question and the user cannot use it after obtaining it.

[0068] Therefore, in a method for processing abnormal test questions in a test question database of this embodiment, in order to determine whether the picture information, and / or audio information, and / or video information is available, it specifically includes:

[0069] Obtain the format of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the format conforms to the preset format set of the picture, and / or audio, and / or video;

[0070] Obtain the storage space of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the storage space conforms to the preset storage space threshold of the picture, and / or audio, and / or video;

[0071] Obtain the image resolution of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the image resolution meets the preset image resolution threshold of the picture, and / or audio, and / or video.

[0072] Therefore, in this embodiment, when it is recognized that the rich text content of the test question contains picture information, and / or audio information, and / or video information, by judging whether the format of the picture information, and / or audio information, and / or video information is correct, whether the storage space occupied by the file meets the requirements (both too large or too small storage space do not meet the requirements), and whether the image resolution reaches the minimum usage requirement, only when the picture information, and / or audio information, and / or video information all meet the requirements, the picture information, and / or audio information, and / or video information can be used.

[0073] In addition, when the rich text content of this embodiment contains or only contains text content, by identifying the keyword information in the text content, judge whether all the keywords in the preset keyword set are covered in the keyword information, so as to judge whether it is an abnormal test question.

[0074] Specifically, the keyword information of this embodiment can be determined according to the basic structural format of the test question. For example, the keyword information can include the test question number, "answer", "analysis", etc. Only when the keyword information covers all the keywords in the preset keyword set, is it a complete test question. Otherwise, the test question is incomplete and should be determined as an abnormal test question to avoid being displayed to the user.

[0075] In a method for processing abnormal test questions in a test question bank of this embodiment, the filtering process of the identified abnormal test questions includes: recording the test question ID of the abnormal test question and reporting it to the server for summarizing the abnormal test questions. This embodiment records and summarizes the test question IDs of the abnormal test questions for the purpose of repairing the abnormal test questions.

[0076] As an alternative implementation of this embodiment, in a method for processing abnormal test questions in a test question bank of this embodiment, after the recognized normal test questions are fed back to the access request for display, it includes:

[0077] Obtain the feedback information of the user during the use of the normal test questions, submit the feedback information and the test question ID to the server for summarizing the feedback abnormal test questions;

[0078] The feedback information includes that there are problems with the title of the test question, the answer of the test question, the analysis of the test question, and the multimedia information of the test question.

[0079] After the test questions are recognized through rich text content in this embodiment, the test questions will be presented to the user. At the same time, when the user uses the test questions and finds that there are problems with the questions, answers, analysis, or multimedia information of the test questions, then the test questions are abnormal test questions, and the user can give feedback on the abnormal test questions. The server records and summarizes the abnormal test questions feedback by the user for repair processing.

[0080] Further, a method for processing abnormal test questions in a test question bank of this embodiment includes:

[0081] The server sorts out the summarized abnormal test questions, structures them into an array, and sends them to operation or teaching and research personnel for repair processing;

[0082] Receive the submission request for repairing and processing abnormal test questions from operation or teaching and research personnel, perform rich text content recognition on the abnormal test questions for repair processing, and re-enter the test question bank after passing the recognition, and return to operation or teaching and research personnel for re-repair processing if the recognition fails.

[0083] The server of this embodiment sorts out the test question IDs of the summarized abnormal test questions, structures them into an array, and sends them to a DingTalk group or a WeChat group through an automated script to notify operation or teaching and research to pay attention in time. Operation and teaching and research see the test question IDs of the abnormal test questions, preview the abnormal test questions through a shortcut, reproduce the problems encountered by the user, and repair the reproduced abnormal test questions in time.

[0084] A method for processing abnormal test questions in a test question bank of this embodiment includes:

[0085] The server monitors the summarized abnormal test questions;

[0086] When a submission request for repairing and processing an abnormal test question from operation or teaching and research personnel is not received for a certain abnormal test question within a preset time threshold, then the abnormal test question is deleted from the test question bank;

[0087] Or when feedback information indicating that a certain abnormal test question cannot be repaired and processed is received from operation or teaching and research personnel, then the abnormal test question is deleted from the test question bank.

[0088] A method for processing abnormal test questions in a test question bank of this embodiment deletes the abnormal test questions that cannot be repaired and processed from the test question bank to prevent the abnormal test questions from being presented to the user and affecting the user experience.

[0089] In this embodiment, an algorithm based on rich text content recognition and feedback is used to implement the abnormal question governance solution in the question bank. When the user opens the application and requests question bank data, the algorithm for rich text content recognition and feedback will be executed to detect abnormal questions and repair them in a timely manner, making the accuracy rate of the question bank higher and higher, the number of abnormal questions fewer and fewer, and the number of abnormal questions provided to the user also fewer and fewer, greatly improving the user experience.

[0090] This embodiment also provides a learning machine that adopts the method for processing abnormal questions in the question bank, including:

[0091] An input module that receives access requests for question data in the question bank;

[0092] A question bank module that filters a corresponding target question set from the question bank according to the access request;

[0093] An abnormal question recognition module that performs rich text content recognition on each question in the target question set, filters out the recognized abnormal questions, and feeds back the recognized normal questions to the access request for display.

[0094] In the learning machine of this embodiment, the abnormal question recognition module implements the processing of abnormal questions in the question bank through rich text content recognition. When the user opens the application and requests question bank data through the input module, the abnormal question recognition module will perform rich text content recognition, detect abnormal questions, and repair them in a timely manner, making the number of correct questions in the question bank more and more, the number of abnormal questions fewer and fewer, and the probability of abnormal questions provided to the user also smaller and smaller, greatly improving the user experience.

[0095] The rich text content recognition in this embodiment is to recognize the rich text content in the questions. The rich text content is a text format that contains rich formats and styles. The questions not only contain text format content, but also contain picture format content, and even include audio format content, video format content, etc.

[0096] Further, in a learning machine that adopts the method for processing abnormal questions in the question bank of this embodiment, the abnormal question recognition module performing rich text content recognition on each question in the target question set includes:

[0097] Obtain the rich text content in the question;

[0098] Filter out the target recognition information in the rich text content and determine whether each target recognition information meets the preset conditions;

[0099] If each target recognition information meets the preset conditions, it is determined as a normal question. If there is target recognition information that does not meet the preset conditions, it is determined as an abnormal question.

[0100] In this embodiment, through preset conditions, target recognition information is recognized from rich text content, and it is determined whether the target recognition information meets the preset conditions, so as to determine abnormal test questions. The target recognition information in this embodiment is the information in the rich text content that is relatively easy to recognize. In this way, it is beneficial to simply and quickly recognize the target recognition information and make a timely judgment on whether it is an abnormal test question.

[0101] Specifically, the abnormal test question recognition module in this embodiment filters out the target recognition information in the rich text content, and determining whether each target recognition information meets the preset conditions includes:

[0102] The abnormal test question recognition module filters out the target recognition information in the rich text content including picture information, and / or audio information, and / or video information, and / or keyword information;

[0103] Determine whether the picture information, and / or audio information, and / or video information is available, and / or determine whether all keywords in the preset keyword set are covered in the keyword information.

[0104] Since the picture information, and / or audio information, and / or video information in the rich text content can be easily recognized, picture information, and / or audio information, and / or video information is selected as the target recognition information for judgment. Moreover, once a test question contains picture information, and / or audio information, and / or video information, the picture information, and / or audio information, and / or video information must be available to ensure that the test question is a normal test question and the user can use it normally; if the picture information, and / or audio information, and / or video information is unavailable, it means that the test question is an abnormal test question and the user cannot use it after obtaining it.

[0105] Therefore, in order to determine whether the picture information, and / or audio information, and / or video information is available, the abnormal test question recognition module in this embodiment specifically includes:

[0106] Obtain the format of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the format conforms to the preset format set of the picture, and / or audio, and / or video;

[0107] Obtain the storage space of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the storage space conforms to the preset storage space threshold of the picture, and / or audio, and / or video;

[0108] Obtain the image resolution of the picture, and / or audio, and / or video based on the picture information, and / or audio information, and / or video information, and determine whether the image resolution meets the preset image resolution threshold of the picture, and / or audio, and / or video.

[0109] Therefore, when the abnormal question recognition module of this embodiment recognizes that the rich text content of the question contains picture information, and / or audio information, and / or video information, by judging whether the formats of the picture information, and / or audio information, and / or video information are correct, whether the storage space occupied by the file meets the requirements (both too large or too small storage space do not meet the requirements), and whether the image resolution reaches the minimum usage requirements. Only when the picture information, and / or audio information, and / or video information all meet the requirements, the picture information, and / or audio information, and / or video information can be used.

[0110] In addition, when the rich text content of this embodiment contains or only contains text content, by identifying the keyword information in the text content, judge whether all the keywords in the preset keyword set are covered in the keyword information, so as to judge whether it is an abnormal question.

[0111] Specifically, the keyword information of this embodiment can be determined according to the basic structure format of the question. For example, the keyword information can include the question number, "Answer", "Analysis", etc. Only when the keyword information covers all the keywords in the preset keyword set, is it a complete question. Otherwise, the question is incomplete and should be determined as an abnormal question to avoid being displayed to the user.

[0112] A learning machine adopting the abnormal question processing method in the question bank of this embodiment, the abnormal question recognition module filters the recognized abnormal questions, including: recording the question ID of the abnormal question and reporting it to the server for summarizing the abnormal questions. This embodiment records and summarizes the question IDs of the abnormal questions for the purpose of repairing the abnormal questions.

[0113] As an optional implementation manner of this embodiment, a learning machine adopting the abnormal question processing method in the question bank of this embodiment includes a feedback module. After the recognized normal questions are fed back to the access request for display, it includes:

[0114] The feedback module obtains the feedback information of the user during the use of the normal questions, submits the feedback information and the question ID to the server for summarizing the feedback abnormal questions;

[0115] The said feedback information includes that there are problems with the question of the question, the answer of the question, the analysis of the question, and the multimedia information of the question.

[0116] In this embodiment, after the test questions are recognized through rich text content, the test questions will be presented to the user. At the same time, when the user is using the test questions and finds that there are problems with the title of the test questions, the answers to the test questions, the analysis of the test questions, and the multimedia information of the test questions, then the test questions are abnormal test questions, and the user can feedback through the feedback module for the abnormal test questions. The server records and summarizes the abnormal test questions feedback by the user for repair processing.

[0117] Further, a learning machine adopting the method for processing abnormal test questions in the test question bank of this embodiment includes:

[0118] The server sorts out the summarized abnormal test questions, structures them into an array, and sends them to the operation or teaching and research personnel for repair processing;

[0119] Receives the submission request for the abnormal test questions repaired by the operation or teaching and research personnel, performs rich text content recognition on the abnormal test questions repaired, and re-enters the test question bank after passing the recognition, and returns to the operation or teaching and research personnel for re-repair processing if the recognition fails.

[0120] The server of this embodiment sorts out the test question IDs of the summarized abnormal test questions, structures them into an array, and sends them to the DingTalk group or WeChat group through an automated script to notify the operation or teaching and research to pay attention in time. The operation and teaching and research see the test question IDs of the abnormal test questions, preview the abnormal test questions through the shortcut, reproduce the problems encountered by the user, and repair the reproduced abnormal test questions in time.

[0121] A learning machine adopting the method for processing abnormal test questions in the test question bank of this embodiment includes:

[0122] The server monitors the summarized abnormal test questions;

[0123] When a submission request for repairing an abnormal test question is not received from the operation or teaching and research personnel within the preset time threshold for a certain abnormal test question, then the abnormal test question is deleted from the test question bank;

[0124] Or when receiving the feedback information that a certain abnormal test question cannot be repaired from the operation or teaching and research personnel, then the abnormal test question is deleted from the test question bank.

[0125] A learning machine adopting the method for processing abnormal test questions in the test question bank of this embodiment deletes the abnormal test questions that cannot be repaired from the test question bank to avoid the abnormal test questions being presented to the user and affecting the user experience.

[0126] In this embodiment, a learning machine that adopts the method for processing abnormal test questions in the test question bank implements a governance solution for abnormal test questions in the test question bank through an algorithm based on rich text content recognition and feedback. When the user opens the application, during the process of the user requesting test question bank data, the algorithm for rich text content recognition and feedback will be executed to detect abnormal test questions and repair them in a timely manner, making the accuracy rate of the test question bank higher and higher, the number of abnormal test questions fewer and fewer, and the number of abnormal test questions provided to the user also fewer and fewer, greatly improving the user experience.

[0127] Reference Figure 1 As shown, when the user uses the learning machine to access an application, the application opens the page and starts to request exercise data from the server. At this stage, the program executes the algorithm for rich text content recognition and feedback to screen and mark the exercises. The specific steps are as follows:

[0128] Step 1: After obtaining the rich text content of the question, filter through the script whether the pictures, keywords, etc. in the question stem meet the expectations. If not, record the question ID and report it to the server for summarization.

[0129] Step 2: If no abnormality is reproduced in Step 1, it will be normally displayed to the user. During the user's use, if the user encounters abnormalities such as wrong answers, wrong analyses, or wrong video content in the questions, click the feedback on the page and submit it to the server for summarization.

[0130] Step 3: The background system sorts out the summarized abnormal question IDs and structures them into an array, and sends them to the DingTalk group or WeChat group through an automated script to notify the operation or teaching and research staff to pay attention in a timely manner.

[0131] Step 4: The operation and teaching and research staff see the abnormal question IDs and preview the wrong questions on the learning machine through the shortcut to reproduce the problems encountered by the user, and repair the reproduced wrong questions in a timely manner.

[0132] Step 5: Delete the part of the wrong questions that cannot be repaired from the test question bank.

[0133] Through the above 5 steps in the algorithm, this embodiment accurately identifies and repairs the abnormal test questions in the test question bank. In the long run, the number of abnormal test questions in the test question bank will become fewer and fewer, and all the test questions commonly used by users will become normal test questions.

[0134] After the above process is completed, when the user uses the learning machine application to do exercises, the probability of encountering wrong questions will be very small, or even none. This solution greatly reduces software customer complaints, improves the user learning experience, and also wins a good reputation from users.

[0135] This embodiment also provides a learning machine that adopts the method for handling abnormal test questions in the test question library, and designs an algorithm based on rich text content recognition and feedback to implement a content wrong-question governance solution. This solution can be used in a variety of educational products such as, but not limited to, learning machines, mobile phones, and intelligent AIs. This strategy is the most advanced implementation strategy on the market and is of great significance for future strategies to improve user experience by implementing a content wrong-question governance solution based on rich text content recognition and feedback. This solution has the advantages of simple implementation, stability, and good user experience. This solution can also be extended for use in other similar scenarios.

[0136] Embodiment 2

[0137] The following describes an embodiment of the electronic device of the present invention. This electronic device can be regarded as a specific physical implementation manner of the above method and device embodiments of the present invention. For the details described in the embodiment of the electronic device of the present invention, they should be regarded as a supplement to the above method or device embodiments; for the details not disclosed in the embodiment of the electronic device of the present invention, they can be implemented with reference to the above method or device embodiments.

[0138] Figure 2 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device includes a processor and a memory. The memory is used to store computer-executable programs. When the computer program is executed by the processor, the processor executes a method for handling abnormal test questions in a test question library according to Embodiment 1.

[0139] As Figure 2 shown, the electronic device is presented in the form of a general-purpose computing device. The processor can be one or multiple and work cooperatively. The present invention does not exclude distributed processing, that is, the processors can be dispersed in different physical devices. The electronic device of the present invention is not limited to a single entity, but can also be the sum of multiple physical devices.

[0140] The memory stores computer-executable programs, usually machine-readable codes. The computer-readable program can be executed by the processor so that the electronic device can execute the method of the present invention, or at least some steps of the method.

[0141] The memory includes volatile memory, such as a random access storage unit (RAM) and / or a cache storage unit, and can also be non-volatile memory, such as a read-only storage unit (ROM).

[0142] Optionally, in this embodiment, the electronic device further includes an I / O interface, which is used for data exchange between the electronic device and external devices. The I / O interface may represent one or more of several types of bus structures, including a memory unit bus or a memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of the multiple bus structures.

[0143] It should be understood that Figure 2 the displayed electronic device is only an example of the present invention, and the electronic device of the present invention may further include elements or components not shown in the above examples. For example, some electronic devices also include a display unit such as a display screen, and some electronic devices also include human-computer interaction elements such as buttons, keyboards, etc. As long as the electronic device can execute the computer-readable program in the memory to implement at least part of the steps of the method or method of the present invention, it can be considered as the electronic device covered by the present invention.

[0144] Figure 3 is a schematic diagram of a computer-readable recording medium according to an embodiment of the present invention. As Figure 3 shown, a computer-executable program is stored in the computer-readable recording medium. When the computer-executable program is executed, it implements a method for processing abnormal test questions in a test question bank according to Embodiment 1 of the present invention. The computer-readable recording medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable recording medium may also be any readable medium other than the readable recording medium, and this readable medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable recording medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination of the above.

[0145] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone 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 the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0146] From the above description of the embodiments, those skilled in the art can easily understand that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. included in the system. The present invention can also be implemented by computer software for performing the method of the present invention, such as control software executed by a microprocessor, an electronic control unit, a client, a server, etc. However, it should be noted that the computer software for performing the method of the present invention is not limited to being executed in one or a specific number of hardware entities, and it can also be implemented in a distributed manner by unspecified specific hardware. For computer software, the software product can be stored in a computer-readable recording medium (which can be a CD-ROM, a USB flash drive, a removable disk, etc.), or it can be distributed and stored on a network, as long as it can enable an electronic device to execute the method according to the present invention.

[0147] The above embodiments are only used to illustrate the present invention and do not limit the technical solutions described in the present invention. Although this specification has described the present invention in detail with reference to the above respective embodiments, the present invention is not limited to the above specific embodiments. Therefore, any modification or equivalent replacement to the present invention; and all technical solutions and their improvements that do not depart from the spirit and scope of the invention are covered by the scope of the claims of the present invention.

Claims

1. A method for processing abnormal test questions in a test question database, characterized in that: include: Receive a request to access test question data in a test question database; According to the access request, a corresponding target test question set is selected from the test question bank; Rich text content recognition is performed on each question in the target question set, abnormal questions that are identified are filtered, and normal questions that pass the identification are fed back to the access request for display.

2. A method for processing abnormal test questions in a test question database according to claim 1, characterized in that: The identifying of rich text content for each test question in the target test question set includes: Get the rich text content in the test questions; Filter out target identification information in rich text content, and determine whether each target identification information meets preset conditions; If all target recognition information meets the preset conditions, it is judged as a normal test question. If there is target recognition information that does not meet the preset conditions, it is judged as an abnormal test question.

3. A method for processing abnormal test questions in a test question database according to claim 2, characterized in that: The filtering out the target identification information in the rich text content and judging whether each target identification information meets the preset conditions includes: The target identification information filtered out from the rich text content includes picture information, and / or audio information, and / or video information, and / or keyword information; Determine whether the picture information, and / or audio information, and / or video information is available, and / or determine whether the keyword information covers all keywords in a preset keyword set.

4. A method for processing abnormal test questions in a test question database according to claim 3, characterized in that: Determining whether the picture information, and / or audio information, and / or video information is available includes: Obtaining the format of the picture, audio, and / or video according to the picture information, audio information, and / or video information, and determining whether the format conforms to a preset format set of the picture, audio, and / or video; Obtaining storage space for the picture, audio, and / or video according to the picture information, audio information, and / or video information, and determining whether the storage space meets a preset storage space threshold for the picture, audio, and / or video; Obtain the image resolution of the picture, and / or audio, and / or video according to the picture information, and / or audio information, and / or video information, and determine whether the image resolution meets the preset image resolution threshold of the picture, and / or audio, and / or video.

5. A method for processing abnormal test questions in a test question database according to any one of claims 1 to 4, characterized in that: The filtering process of the identified abnormal test questions includes: The test question IDs of abnormal test questions are recorded and reported to the server for summary of abnormal test questions.

6. A method for processing abnormal test questions in a test question database according to claim 5, characterized in that: The step of feeding back the recognized normal test questions to the access request for display includes: Obtain user feedback during normal test questions, submit the feedback information and test question ID to the server, and summarize the feedback on abnormal test questions; The feedback information includes problems with the test questions, problems with the answers to the test questions, problems with the analysis of the test questions, and problems with the multimedia information of the test questions.

7. A method for processing abnormal test questions in a test question database according to claim 6, characterized in that: include: The server organizes the abnormal test questions and structures them into an array, and sends them to the operation or teaching and research personnel for repair. Receive requests for abnormal test questions to be repaired by operations or teaching and research personnel, perform rich text content recognition on the repaired abnormal test questions, re-enter the test question database if the recognition passes, and return to the operations or teaching and research personnel for re-repair if the recognition fails.

8. A method for processing abnormal test questions in a test question database according to claim 7, characterized in that: include: The server monitors the aggregated abnormal test questions; When an abnormal question does not receive a request from an operation or teaching and research staff to repair the abnormal question within a preset time threshold, the abnormal question will be deleted from the question bank; Or when feedback is received from operations or teaching and research personnel that a certain abnormal test question cannot be repaired, the abnormal test question will be deleted from the test question bank.

9. A learning machine using the method for processing abnormal test questions in a test question database as claimed in any one of claims 1 to 8, characterized in that: include: An input module receives a request to access the test data in the test question database; A test question bank module, which selects a corresponding target test question set from the test question bank according to the access request; The abnormal question identification module performs rich text content identification on each question in the target question set, filters the identified abnormal questions, and feeds back the normal questions that have passed the identification to the access request for display.

10. A computer-readable recording medium storing a computer-executable program, characterized in that: When the computer executable program is executed, a method for handling abnormal test questions in a test question bank as described in any one of claims 1 to 8 is implemented.

Images