A data correction method, device and system
By identifying and expanding the data correction methods, the problems of low efficiency and low accuracy of manual correction in the existing technology are solved, and fast and accurate data correction is achieved, improving the correction efficiency and flexibility.
Patent Information
- Application Number
- CN202010874493.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-08-26
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-08-26
AI Technical Summary
The existing data correction methods rely on manual operations, are inefficient and prone to misapproval, resulting in rigid correction results and low accuracy.
By identifying the types of questions and standard answers of the data to be corrected, the extended process is carried out to generate auxiliary correction results, and revise them based on the revised information to achieve rapid and accurate corrections.
It improves the efficiency and accuracy of correction, improves the flexibility and accuracy of correction results, and reduces manual errors.
Smart Images

Figure CN111950240B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of learning and education, and more specifically, to a data correction method, device and system. Background Art
[0002] At present, the existing data correction method is usually a manual correction method. When the data is corrected by the manual correction method, each data needs to be manually checked and corrected, which wastes a lot of time, has low correction efficiency, and is prone to errors in manual correction. It can be seen that the existing data correction method is manual correction, the correction results are rigid, the correction efficiency is low, and the accuracy is low. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a data correction method, device and system, which can identify extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving the correction efficiency.
[0004] A first aspect of an embodiment of the present application provides a data correction method, comprising:
[0005] Identify and process the data to be corrected to obtain the question type and standard answer of the data to be corrected;
[0006] Determine answer data in the data to be corrected according to the question type, and perform expansion processing on the answer data to obtain an expanded answer;
[0007] Generate auxiliary correction results according to the standard answer and the extended answer;
[0008] According to the acquired revision information for the auxiliary revision result, the auxiliary revision result is revised to obtain the revision result of the data to be revised.
[0009] In the above implementation process, when correcting data, the data to be corrected is first identified and processed to obtain the question type and standard answer of the data to be corrected; then, according to the question type, the answer data in the data to be corrected is determined, and the answer data is expanded to obtain the expanded answer; and according to the standard answer and the expanded answer, an auxiliary correction result is generated; finally, according to the obtained revision information for the auxiliary correction result, the auxiliary correction result is revised to obtain the correction result of the data to be corrected, thereby achieving the technical effect of quickly and accurately correcting the data to be corrected. At the same time, revising the auxiliary correction result through the revision information can improve the flexibility and accuracy of the correction result, which is conducive to improving the correction efficiency.
[0010] Furthermore, the identification processing of the data to be corrected to obtain the question type and standard answer of the data to be corrected includes:
[0011] Perform identification processing on the data to be corrected to obtain identification data;
[0012] Matching the topic information corresponding to the identification data from a preset topic database;
[0013] The question type and standard answer of the data to be corrected are obtained according to the question information.
[0014] In the above implementation process, the data to be corrected is first identified to obtain identification data, and then the corresponding question type and standard answer are matched according to the preset question database, thereby achieving the technical effect of quickly and accurately locating the question type and standard answer.
[0015] Furthermore, the identification processing of the data to be corrected to obtain identification data includes:
[0016] Determine the data type of the data to be revised;
[0017] The data to be corrected is identified according to the data type to obtain identification data.
[0018] In the above implementation process, in actual use, the data to be corrected is pictures, text, voice, video and other data. Therefore, when identifying the data to be corrected, the data type of the data to be corrected is first determined, and then the data to be corrected is identified according to the data type (for example, picture type is processed by picture recognition, text type is processed by text recognition, etc.), and the identified data is obtained, and the data type has strong compatibility and applicability.
[0019] Furthermore, the step of obtaining the question type and standard answer of the data to be corrected according to the question information includes:
[0020] Extracting the title identifier in the data to be corrected from the identification data;
[0021] According to the question identifier, the question type and standard answer of the data to be corrected are determined.
[0022] In the above implementation process, after obtaining the recognition data, the corresponding question identifier can be extracted from the recognition data, the data processing is simple, and the question type and the standard answer can be quickly determined based on the question identifier.
[0023] Further, determining the answer data in the data to be corrected according to the question type includes:
[0024] Determining the positional relationship between the answer part and the question stem part in the data to be corrected according to the question type;
[0025] According to the positional relationship between the answer part and the question stem part, identifying the position of the answer part in the data to be corrected;
[0026] The answer data is extracted from the data to be corrected according to the position of the answer part.
[0027] In the above implementation process, when extracting answer data, by determining the positional relationship between the answer and the question stem according to the question type, it is helpful to accurately determine the position of the answer data, thereby improving the accuracy of answer extraction.
[0028] Furthermore, the step of performing expansion processing on the answer data to obtain an expanded answer includes:
[0029] Extracting keywords from the answer data;
[0030] Matching synonyms corresponding to the keywords in a preset extended database;
[0031] The answer data is expanded according to the synonyms to obtain an expanded answer.
[0032] In the above implementation process, expanding the answer data is equivalent to replacing words with the same meaning in the answer data. First, the keywords that need to be expanded are determined, and then the corresponding synonyms of the keywords are determined according to the preset expansion database. Finally, the answer data is expanded through synonyms to obtain the expanded answers, which further improves the compatibility and accuracy of data correction. The correction results are highly flexible, which is conducive to improving the correction efficiency.
[0033] A second aspect of an embodiment of the present application provides a data correction device, the data correction device comprising:
[0034] An identification module is used to identify the data to be corrected and obtain the question type and standard answer of the data to be corrected;
[0035] An extraction module, used for determining answer data in the data to be corrected according to the question type;
[0036] An expansion module, used to perform expansion processing on the answer data to obtain an expanded answer;
[0037] A correction module, used for generating auxiliary correction results according to the standard answer and the extended answer;
[0038] The revision module is used to revise the auxiliary revision result according to the obtained revision information for the auxiliary revision result to obtain the revision result of the data to be revised.
[0039] In the above implementation process, when correcting data, the recognition module first identifies the data to be corrected to obtain the question type and standard answer of the data to be corrected; then the extraction module determines the answer data in the data to be corrected according to the question type, and the expansion module expands the answer data to obtain the expanded answer; further, the correction module generates an auxiliary correction result based on the standard answer and the expanded answer, so as to achieve the correct recognition and correction of the expanded answer. Finally, the revision module revises the auxiliary correction result according to the obtained revision information for the auxiliary correction result, and obtains the correction result of the data to be corrected, thereby achieving the technical effect of quickly and accurately correcting the data to be corrected. At the same time, revising the auxiliary correction result through the revision information can improve the flexibility and accuracy of the correction result, which is conducive to improving the correction efficiency.
[0040] Furthermore, the identification module includes:
[0041] The first submodule is used to perform recognition processing on the data to be corrected to obtain recognition data;
[0042] A second submodule is used to match the topic information corresponding to the identification data from a preset topic database;
[0043] The third submodule is used to obtain the question type and standard answer of the data to be corrected according to the question information.
[0044] In the above implementation process, when identifying and processing the data to be corrected, the first sub-module needs to first identify and process the data to be corrected to obtain the identification data, and then the second sub-module matches the corresponding question type and standard answer, thereby achieving the technical effect of quickly and accurately locating the question type and standard answer.
[0045] A third aspect of the embodiments of the present application provides a data correction system, the data correction system comprising a first terminal, a second terminal and a data correction device, wherein:
[0046] The first terminal is used to send the data to be corrected to the data correction device;
[0047] The data correction device is used to identify the data to be corrected to obtain the question type and standard answer of the data to be corrected; and according to the question type, determine the answer data in the data to be corrected, and perform expansion processing on the answer data to obtain an expanded answer; and generate an auxiliary correction result according to the standard answer and the expanded answer; and send the auxiliary correction result to the second terminal;
[0048] The second terminal is used to receive the auxiliary correction result and the revision information made by the user for the auxiliary correction result; and send the revision information to the data correction device;
[0049] The data correction device is further used to receive the revision information, and revise the auxiliary correction result according to the revision information to obtain the correction result of the data to be corrected; and send the correction result to the first terminal;
[0050] The first terminal is used to receive and output the correction result.
[0051] In the above implementation process, when performing data correction, the first terminal first sends the data to be corrected to the data correction device. Then, when receiving the data to be corrected, the data correction device first identifies and processes the data to be corrected to obtain the question type and standard answer of the data to be corrected; and according to the question type, determines the answer data in the data to be corrected, and performs expansion processing on the answer data to obtain the expanded answer; and generates an auxiliary correction result according to the standard answer and the expanded answer, and finally, according to the obtained revision information for the auxiliary correction result, revise the auxiliary correction result to obtain the correction result of the data to be corrected, and then send the auxiliary correction result to the second terminal. The second terminal can output and display the auxiliary correction result, and receive the revision information made by the user for the auxiliary correction result. Finally, the data correction device can receive the revision information sent by the second terminal, and revise the auxiliary correction result according to the revision information, generate the correction result of the data to be corrected, and feed back the correction result to the first terminal in a timely manner. This can achieve the technical effect of quickly and accurately correcting the correction data. At the same time, by revising the auxiliary correction results through revision information, the flexibility and accuracy of the correction results can be improved, which is conducive to improving the correction efficiency.
[0052] A fourth aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the data correction method described in any one of the first aspects of the embodiments of the present application.
[0053] A fifth aspect of an embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the data correction method described in any one of the first aspects of the embodiment of the present application is executed. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0055] Figure 1 A flowchart of a data correction method provided in Example 1 of the present application;
[0056] Figure 2 A flowchart of a data correction method provided in Embodiment 2 of the present application;
[0057] Figure 3 A schematic diagram of the structure of a data correction device provided in Embodiment 3 of the present application;
[0058] Figure 4 A schematic diagram of the structure of a data correction device provided in Embodiment 4 of the present application;
[0059] Figure 5 A schematic diagram of the system architecture of a data correction system provided in Embodiment 5 of the present application;
[0060] Figure 6 This is an information interaction flow chart of a data correction system provided in Example 6 of the present application;
[0061] Figure 7 This is an information interaction flow chart of a data correction system applied to text data provided in Example 6 of the present application.
[0062] Icons: 410 - student terminal; 420 - teacher terminal; 430 - data correction device. DETAILED DESCRIPTION
[0063] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0064] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0065] Example 1
[0066] Please see Figure 1 , Figure 1A flow chart of a data correction method is provided for an embodiment of the present application. The data correction method includes:
[0067] S101, identifying and processing the data to be corrected to obtain the question type and standard answer of the data to be corrected.
[0068] In the embodiment of the present application, the execution subject of the method can be a computing device such as a computer, a server (a single server or a server cluster), and no limitation is made in this embodiment.
[0069] In the embodiment of the present application, the execution subject of the method can also be a smart device such as a smart phone and a tablet, and there is no limitation on this in the present embodiment.
[0070] In the embodiment of the present application, the identification processing of the data to be revised includes data type analysis and data content identification of the data to be revised.
[0071] In the embodiment of the present application, after receiving the data to be corrected, the data type of the data to be corrected can be determined first, and then the data to be corrected can be identified and processed using a corresponding identification method according to the data type, thereby obtaining the question type and standard answer of the data to be corrected.
[0072] In the embodiment of the present application, the data type of the data to be corrected can be text type, voice type, picture type, video type, etc., and of course it can also be a combination of the above multiple data types, which is not limited by the embodiment of the present application.
[0073] In the embodiment of the present application, assignments of different data types have different question types. For example, for picture-type data to be graded, the question types may include but are not limited to fill-in-the-blank questions, multiple-choice questions, essay questions, true-or-false questions, etc.; for audio-type data to be graded, the question types may include but are not limited to reading questions, pronunciation questions, etc.; for video-type data to be graded, the question types may include but are not limited to lip-sync questions, action questions, etc., which are not limited in the embodiment of the present application.
[0074] After step S101, the following steps are also included:
[0075] S102. According to the question type, the answer data in the data to be corrected is determined, and the answer data is expanded to obtain an expanded answer.
[0076] In the embodiments of the present application, after determining the question type, the positional relationship between the answer data and the question stem of the homework can be determined according to the question type, and then the corresponding answer data can be extracted according to the positional relationship between the answer data and the question stem of the homework. For example, for the data to be corrected of the picture type, its question type can be fill-in-the-blank questions, multiple-choice questions, short-answer questions, application questions, true or false questions, etc. For fill-in-the-blank questions, the answer data is embedded in the question stem; for multiple-choice questions and true or false questions, the answer data is within specific answer boxes (such as parentheses, horizontal lines, square brackets, etc.); for short-answer questions and application questions, the area of the answer data is independent of the area of the question stem.
[0077] In the embodiments of the present application, after obtaining the answer data, the answer data also needs to be expanded. In practical applications, the same meaning can be expressed by different words. Therefore, the answer data of different people has the same meaning, but the words or sentence patterns used in the answers are different. Therefore, by expanding the answer data, different forms of answer expressions can be compatible, which is beneficial to improving the flexibility and accuracy of the correction results, and thus beneficial to improving the data correction efficiency.
[0078] It should be noted that in order to improve the flexibility and accuracy of homework correction, the synonymous expansion is not limited to the number of words and characters. For example, "male" can be expanded to "male gender"; "buy" can be expanded to "purchase"; "=" can be expanded to "equal to"; "plus sign" can be expanded to "+", etc., which will not be elaborated here.
[0079] In addition, in some specific scenarios, the synonymous expansion is not limited to the type of characters. For example, "right" can be expanded to "√", expanded to "correct", or expanded to "yes", or expanded to "Y", or even expanded to "OK".
[0080] Of course, for the sake of accuracy, the foregoing methods also need to be pre-stored in advance and the applicable scenarios need to be set, which will not be elaborated here.
[0081] Furthermore, in actual operation, some error marking words can also be set, such as some negative words, such as "not", "didn't", "haven't", etc. When the words representing the correct answer appear in the answer data, it is also necessary to determine whether there are error marking words in the context of these words. For example, the standard answer is "yes", and the answer data is "no". When determining the word "not" in the answer data, it can be determined that the question is incorrect.
[0082] S103. Generate an auxiliary correction result according to the standard answer and the expanded answer.
[0083] In the embodiments of the present application, for example, when the standard answer is 0.5, if the answer data in the answer data is , then the answer data is synonymously expanded, and the answer data in the expanded answer is Or 0.5 or 50%, then when generating the auxiliary correction results, it can be corrected according to its expanded answers, and it can be compatible with different answer expressions, which is conducive to improving the flexibility and accuracy of the correction results, and thus conducive to improving the efficiency of data correction.
[0084] In an embodiment of the present application, when the executor of the present method is a server for assisting in correcting homework, after receiving the data to be corrected submitted by the first terminal (such as a student terminal, a trainee terminal, etc., which may be a student mobile phone, a student computer or a student PAD, etc.), and generating an auxiliary correction result based on the data to be corrected, the auxiliary correction result can be sent to the corresponding second terminal (such as a teacher terminal, a teaching terminal, which may be a teacher mobile phone, a teacher computer or a teacher PAD, etc.), and then after receiving the auxiliary correction result, the second terminal can output the auxiliary correction result by marking and enhancing the display, so that users using the second terminal (such as teaching teachers, tutors, class teachers, etc.) can directly focus on the answer area and the result area, and can confirm or revise the auxiliary correction result through the second terminal (such as supplementing the correction result, modifying the correction result, etc.), and then generate revision information, and then the second terminal will send the revision information to the server.
[0085] In the embodiment of the present application, executing step S103 is helpful to improve the flexibility and accuracy of the correction result, thereby helping to improve the data correction efficiency.
[0086] After step S103, the following steps are also included:
[0087] S104: According to the acquired revision information for the auxiliary revision result, the auxiliary revision result is revised to obtain the revision result of the data to be revised.
[0088] In the embodiment of the present application, the auxiliary correction result obtained by implementing the above steps S101 to S103 is obtained by correcting the data to be corrected according to the standard answer. At this time, the auxiliary correction result can be output and manually reviewed. If there is a correction problem in the auxiliary correction result, the corresponding revision information can be input to revise the auxiliary correction result to obtain the final correction result. The auxiliary correction result obtained by the automatic correction operation can be reviewed in time, and errors can be corrected in time. It has high flexibility and is conducive to improving the accuracy and efficiency of data correction.
[0089] As an optional implementation, after obtaining the auxiliary correction result, confirmation information for the auxiliary correction result may be received, indicating that the auxiliary correction result meets the manual review standard, and the auxiliary correction result is then determined as the correction result of the data to be corrected.
[0090] It can be seen that the implementation Figure 1 The described data correction method can identify extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving the correction efficiency.
[0091] Example 2
[0092] Please see Figure 2 , Figure 2 The following is a flow chart of a data correction method provided in an embodiment of the present application. Figure 2 As shown, the data correction method includes:
[0093] S201, performing recognition processing on the data to be corrected to obtain recognition data.
[0094] As an optional implementation, the data to be corrected is subjected to identification processing to obtain identification data, including:
[0095] Determine the data type of the data to be revised;
[0096] The data to be corrected is identified and processed according to the data type to obtain identification data.
[0097] In the above implementation, the identification process of the data to be revised includes analyzing the data type and identifying the data content of the data to be revised.
[0098] In the above implementation, the data type of the data to be corrected may be text type, voice type, picture type, video type, etc., or a mixed type of any of the above types, which is not limited in this embodiment of the application.
[0099] In the above implementation, for the text type data to be revised, the text information in the data to be revised can be directly extracted, and the text information can be converted into a recognizable data format to obtain recognition data, and the data to be revised can be recognized to obtain recognition data.
[0100] In the above implementation, for the image type data to be corrected, the image recognition algorithm can be used to identify the data to be corrected, and the OCR (optical character recognition) text recognition technology can also be used to recognize the characters in the data to be corrected, thereby obtaining the recognized data.
[0101] In the above implementation, for the voice type data to be corrected, a voice recognition technology may be used to perform recognition processing on the data to be corrected to obtain recognition data.
[0102] In the above implementation, for the video type of data to be corrected, the video recognition technology can be used to perform recognition processing on the data to be corrected to obtain recognition data.
[0103] After step S201, the following steps are also included:
[0104] S202: Match the topic information corresponding to the identification data from a preset topic database.
[0105] In the embodiment of the present application, the question identifier includes the question number, answer feature word, question order, question keywords, etc., which are not limited to the embodiment of the present application.
[0106] In the embodiment of the present application, the topic information corresponding to the identification data can be determined from a preset topic database according to the topic identifier.
[0107] S203, obtaining the question type and standard answer of the data to be corrected according to the question information.
[0108] In the embodiment of the present application, assignments of different data types have different question types. For picture-type data to be graded, the question types may include but are not limited to fill-in-the-blank questions, multiple-choice questions, essay questions, true-or-false questions, etc., which are not limited in the embodiment of the present application.
[0109] In the embodiment of the present application, the question type and standard answer of the data to be corrected can be matched from a preset question database according to the question information.
[0110] As an optional implementation, obtaining the question type and standard answer of the data to be corrected according to the question information may include the following steps:
[0111] Extracting the title identifier in the data to be corrected from the recognition data;
[0112] According to the question ID, determine the question type and standard answer of the data to be corrected.
[0113] In the embodiment of the present application, by implementing the above steps S201 to S203, the data to be corrected can be identified and processed to obtain the question type and standard answer of the data to be corrected.
[0114] S204. Determine the positional relationship between the answer part and the question stem part in the data to be corrected according to the question type.
[0115] In the embodiment of the present application, for example, for the data to be corrected of the picture type, the question type can be fill-in-the-blank questions, multiple-choice questions, essay questions, application questions, true-or-false questions, etc. For fill-in-the-blank questions, the answer part is embedded in the stem part; for multiple-choice questions and true-or-false questions, the answer part is in a specific answer box (such as brackets, horizontal lines, square brackets, underscores, spaces, etc.); for essay questions and application questions, the answer part is independent of the stem part, and the answer part is located below the stem part, and of course it can also be in other positions, such as the right side, left side, top, etc.
[0116] S205. Identify the position of the answer part in the data to be corrected according to the positional relationship between the answer part and the question stem part.
[0117] In the above examples, for fill-in-the-blank questions, the answer part is located in the question stem; for multiple-choice questions and true-or-false questions, the answer part is located in a specific answer box; for essay questions and application questions, the answer part is located below the question stem.
[0118] Of course, when determining the answer part, you can also determine whether there are marking symbols pointing to other locations in the answer part (or answer box), such as arrows, downward or upward angle brackets, etc. If so, the part pointed by the arrow or the content contained in the angle brackets can also be used as the answer part. I will not go into details about this.
[0119] For example, in fill-in-the-blank questions, if the reserved answer box is not large enough to accommodate the student's answer data, the student can write the remaining text in other locations and connect the two parts of the answer according to the symbols agreed in advance. I will not go into details about this.
[0120] S206. Extracting answer data from the data to be corrected according to the position of the answer part.
[0121] In the above example, when extracting answer data from the data to be corrected according to the position of the answer part, for fill-in-the-blank questions, first identify the stem part, then determine the handwritten area of the stem part, and then perform text recognition processing on the handwritten area to obtain the answer data; for multiple-choice questions and true-or-false questions, first determine the specific answer box area, and then perform text recognition processing on the specific answer box area to obtain the answer data; for question-and-answer questions and application questions, first determine the position of the stem part, and then determine the handwritten area below the stem part, and finally perform text recognition processing on the handwritten area to obtain the answer data.
[0122] In the embodiment of the present application, the above steps S204 to S205 are implemented to determine the answer data in the data to be corrected according to the question type.
[0123] S207. Extract keywords from the answer data.
[0124] As an optional implementation, the answer data may be processed according to preset common keyword extraction rules to obtain keyword information.
[0125] As an optional implementation, the words in the answer data may be divided first to obtain multiple words, and all of the multiple words are used as keywords.
[0126] After step S207, the following steps are also included:
[0127] S208: Match synonyms corresponding to the keywords in a preset extended database.
[0128] S209. Expand the answer data according to synonyms to obtain expanded answers.
[0129] In the embodiment of the present application, for example, when the keyword is 0.5, the synonyms corresponding to the keyword can be matched according to the preset extended database: 50%, then the answer data is synonymously expanded, and the expanded answers include Or 0.5 or 50%, then when generating the auxiliary correction results, when the standard answer is 0.5, it can be corrected according to its expanded answer, which is compatible with different answer expressions, which is conducive to improving the flexibility and accuracy of the correction results, and thus helps to improve the efficiency of data correction.
[0130] In the embodiment of the present application, the above steps S207 to S209 are implemented to expand the answer data and obtain an expanded answer.
[0131] S210. Generate auxiliary correction results based on the standard answers and the extended answers.
[0132] S211 . According to the acquired revision information for the auxiliary revision result, the auxiliary revision result is revised to obtain the revision result of the data to be revised.
[0133] It can be seen that the implementation Figure 2 The described data correction method can identify extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving the correction efficiency.
[0134] Example 3
[0135] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a data correction device provided in an embodiment of the present application. Figure 3 As shown, the data correction device comprises:
[0136] The identification module 310 is used to identify the data to be corrected and obtain the question type and standard answer of the data to be corrected.
[0137] The extraction module 320 is used to determine the answer data in the data to be corrected according to the question type.
[0138] The expansion module 330 is used to expand the answer data to obtain an expanded answer.
[0139] The correction module 340 is used to generate auxiliary correction results according to the standard answers and the expanded answers.
[0140] The revision module 350 is used to revise the auxiliary revision result according to the revision information obtained for the auxiliary revision result, and obtain the revision result of the data to be revised.
[0141] In this embodiment, the explanation of the data correction device can refer to the description in Embodiment 1 or Embodiment 2, and will not be further elaborated in this embodiment.
[0142] In some possible implementations, the recognition module 310 may be a combination of a camera and a processing unit, and the extraction module 320, the expansion module 330, the correction module 340, the revision module 350, etc. may all be processing units, such as a CPU, a processor, etc., without limitation.
[0143] The extraction module 320 and the expansion module 330 can be the same module as long as they can achieve the above functions. Of course, they can also be divided into more small modules, and there is no limitation on this.
[0144] It can be seen that the data correction device described in this embodiment can identify the extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving the correction efficiency.
[0145] Example 4
[0146] Please also read Figure 4 , Figure 4 : is a schematic diagram of the structure of a data correction device provided in an embodiment of the present application. Figure 4 The data correction device shown is composed of Figure 3 The data correction device shown in FIG. Figure 4 As shown, the identification module 310 includes:
[0147] The first submodule 311 is used to perform recognition processing on the data to be corrected to obtain recognition data;
[0148] The second submodule 312 is used to match the topic information corresponding to the identification data from the preset topic database;
[0149] The third submodule 313 is used to obtain the question type and standard answer of the data to be corrected according to the question information.
[0150] As an optional implementation, the first submodule 311 includes:
[0151] A type determination unit, used to determine the data type of the data to be revised;
[0152] The recognition unit is used to recognize the data to be corrected according to the data type to obtain recognition data.
[0153] As an optional implementation, the third submodule 313 includes:
[0154] The extraction unit is used to extract the title identification in the data to be corrected from the recognition data.
[0155] Determine the unit and, based on the question ID, determine the question type and standard answer for the data to be graded.
[0156] As an optional implementation, the extraction module 320 includes:
[0157] The fourth submodule 321 is used to determine the position relationship between the answer part and the question stem part in the data to be corrected according to the question type;
[0158] The fifth submodule 322 is used to identify the position of the answer part in the data to be corrected according to the positional relationship between the answer part and the question stem part;
[0159] The sixth submodule 323 is used to extract the answer data from the data to be corrected according to the position of the answer part.
[0160] As an optional implementation, the expansion module 330 includes:
[0161] The seventh submodule 331 is used to extract keywords from the answer data;
[0162] An eighth submodule 332 is used to match synonyms corresponding to the keywords in a preset extended database;
[0163] The ninth submodule 333 is used to expand the answer data according to synonyms to obtain an expanded answer.
[0164] In this embodiment, the explanation of the data correction device can refer to the description in Embodiment 1 or Embodiment 2, and will not be further elaborated in this embodiment.
[0165] It can be seen that the data correction device described in this embodiment can identify the extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving the correction efficiency.
[0166] Example 5
[0167] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a data correction system provided in an embodiment of the present application. Figure 5 As shown, the data correction system includes a first terminal, a second terminal and a data correction device. Taking the first terminal as a student terminal 410 and the second terminal as a teacher terminal 420 as an example, the data correction system is introduced in detail, wherein the student terminal 410 is used to send the data to be corrected to the data correction device 430.
[0168] In the embodiment of the present application, the student terminal 410, the teacher terminal 420 and the data correction device 430 can be connected to each other through the Internet, which is not limited to the embodiment of the present application.
[0169] In the embodiment of the present application, a data correction device 430 can be communicated with multiple student terminals 410 and multiple teacher terminals 420 at the same time, a teacher terminal 420 can be communicated with multiple student terminals 410 at the same time, and multiple student terminals 410 can be communicated with each other.
[0170] In the embodiment of the present application, the student terminal 410, i.e., the student client, may specifically be a smart phone, a tablet computer, an intelligent learning machine, a computer, etc., which is not limited in the embodiment of the present application.
[0171] In the embodiment of the present application, the student terminal 410 has the functions of watching class videos, viewing questions, taking classes online, taking photos or inputting homework, submitting homework, viewing grades, etc. At the same time, it can also communicate with other students' student terminals 410 through the online communication function and can view the homework status of other students. This embodiment of the present application is not limited to this.
[0172] In the embodiment of the present application, the student terminal 410 can directly send the data to be corrected to the data correction device 430, or first send the data correction device 430 to the teacher terminal 420, and then forward it to the data correction device 430 by the teacher terminal 420. This embodiment of the present application is not limited to this.
[0173] The data correction device 430 is used to identify and process the data to be corrected, obtain the question type and standard answer of the data to be corrected; and determine the answer data in the data to be corrected according to the question type, and expand the answer data to obtain the expanded answer; and generate auxiliary correction results according to the standard answer and the expanded answer; and send the auxiliary correction results to the teacher terminal 420.
[0174] In the embodiment of the present application, the data correction device 430 may be a computing device such as a server or a computer, which is not limited in the embodiment of the present application.
[0175] In the embodiment of the present application, the data correction device 430 has the function of sending and receiving information, and can also determine the corresponding standard answer from the preset question database based on the question information (such as question number, answer feature word, order, etc.), and can also feed back the obtained auxiliary correction results to the teacher terminal 420.
[0176] The teacher terminal 420 is used to receive the auxiliary correction result and the revision information made by the user for the auxiliary correction result; and send the revision information to the data correction device 430.
[0177] In the embodiment of the present application, the teacher terminal 420 can be a smart phone, a tablet computer, an intelligent learning machine, a computer, etc., which is not limited to the embodiment of the present application.
[0178] In the embodiment of the present application, the teacher terminal 420 can also receive the data to be corrected sent by the student terminal 410 and forward the data to be corrected to the data correction device 430 , and can receive the auxiliary correction result fed back by the data correction device 430 .
[0179] The data correction device 430 is further used to receive revision information, and revise the auxiliary correction result according to the revision information to obtain the correction result of the data to be corrected; and send the correction result to the student terminal 410.
[0180] In an embodiment of the present application, the teacher terminal 420 can output the auxiliary correction result and receive confirmation information and modification information input by the teacher for the auxiliary correction result. Then, the data correction device 430 can process the auxiliary correction result according to the confirmation information and modification information, and then obtain the final correction result, and send the correction result to the student terminal 410.
[0181] The student terminal 410 is used to receive and output the correction results.
[0182] In the embodiment of the present application, students can view the corresponding correction results through the student terminal 410, and can also perform pre-learning feedback, course learning, data viewing, homework review, academic feedback, excellent homework learning, communication with other students, learning data sharing and other operations through the student terminal 410, which is not limited to the embodiment of the present application.
[0183] In this embodiment, the explanation of the data correction system can refer to the description in Embodiment 1 or Embodiment 2, and will not be further elaborated in this embodiment.
[0184] It can be seen that the data correction system described in this embodiment can identify extended answers and quickly correct the data to be corrected. The correction results are highly flexible and accurate, which is conducive to improving correction efficiency.
[0185] Example 6
[0186] Please also see Figure 6 , Figure 6 This is an information interaction flow chart of a data correction system provided in an embodiment of the present application. Figure 6 The data correction system includes a first terminal, a second terminal and a data correction device. Taking the first terminal as a student terminal 410 and the second terminal as a teacher terminal 420 as an example, the workflow of the data correction system is described in detail.
[0187] S501 , the student terminal 410 sends the data to be corrected to the data correction device 430 .
[0188] As an optional implementation, the student terminal 410 may first send the data to be corrected to the teacher terminal 420 , and then the teacher terminal 420 may aggregate the data to be corrected and forward it to the data correcting device 430 .
[0189] S502 , the data correction device 430 identifies and processes the data to be corrected, and obtains the question type and standard answer of the data to be corrected.
[0190] S503: The data correction device 430 determines the answer data in the data to be corrected according to the question type.
[0191] S504: The data correction device 430 performs expansion processing on the answer data to obtain an expanded answer.
[0192] S505. The data correction device 430 generates auxiliary correction results according to the standard answer and the expanded answer.
[0193] S506 , the data correction device 430 sends the auxiliary correction result to the teacher terminal 420 .
[0194] S507 . The teacher terminal 420 receives the auxiliary correction result, and receives the revision information made by the user in response to the auxiliary correction result.
[0195] S508 , the teacher terminal 420 sends the revision information to the data correction device 430 .
[0196] S509 , the data correction device 430 receives the revision information, and performs revision processing on the auxiliary correction result according to the revision information to obtain the correction result of the data to be corrected.
[0197] S510 , the data correction device 430 sends the correction result to the student terminal 410 .
[0198] S511, the student terminal 410 receives and outputs the correction results.
[0199] In the embodiment of the present application, the data to be corrected may be text data, voice data, picture data, video data, etc., or a combination of the above data, which is not limited in the embodiment of the present application.
[0200] If the data to be revised is text data, please refer to Figure 7 , Figure 7 This is a flow chart of information interaction of a data correction system applied to text data provided by an embodiment of the present application. Figure 7 As shown, the data correction system includes a student terminal 410 , a teacher terminal 420 and a data correction device 430 .
[0201] S601 , the student terminal 410 sends text data to the teacher terminal 420 .
[0202] S602 , the teacher terminal 420 forwards the text data to the data correction device 430 .
[0203] As an optional implementation, the student terminal 410 may directly send the data to be corrected to the data correcting device 430 .
[0204] S603, the data correction device 430 receives the text data, and performs data type analysis and text recognition processing on the text data to obtain the question type and standard answer of the text data.
[0205] S604. The data correction device 430 determines the positional relationship between the answer part and the question stem part in the text data according to the question type.
[0206] S605. The data correction device 430 identifies the position of the answer part in the text data according to the positional relationship between the answer part and the question stem part.
[0207] S606. The data correction device 430 performs text area segmentation processing on the text data according to the position of the answer part, extracts the answer area from the text data, and performs text recognition processing on the answer area to obtain answer data.
[0208] S607: The data correction device 430 performs expansion processing on the answer data to obtain an expanded answer.
[0209] S608. The data correction device 430 generates auxiliary correction results according to the standard answer and the expanded answer.
[0210] S609 , the data correction device 430 sends the auxiliary correction result to the teacher terminal 420 .
[0211] S610. The teacher terminal 420 receives the auxiliary correction result, and receives the revision information made by the user in response to the auxiliary correction result.
[0212] S611 , the teacher terminal 420 sends the revision information to the data correction device 430 .
[0213] S612: The data correction device 430 receives the revision information, and performs revision processing on the auxiliary correction result according to the revision information to obtain the correction result of the text data.
[0214] S613 , the data correction device 430 sends the correction result to the student terminal 410 .
[0215] S614. The student terminal 410 receives and outputs the correction results.
[0216] In this embodiment, the explanation of the data correction system can refer to the description in Embodiment 1 or Embodiment 2, and will not be further elaborated in this embodiment.
[0217] It can be seen that the data correction system described in this embodiment can identify extended answers and quickly correct text data. The correction results are highly flexible and accurate, which is conducive to improving correction efficiency.
[0218] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute any one of the data correction methods in Embodiment 1 or Embodiment 2 of the present application.
[0219] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, any data correction method in Embodiment 1 or Embodiment 2 of the present application is executed.
[0220] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0221] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0222] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0223] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0224] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0225] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A data correction method, characterized in that: include: Identify and process the data to be corrected to obtain the question type and standard answer of the data to be corrected; Determine answer data in the data to be corrected according to the question type, and perform expansion processing on the answer data to obtain an expanded answer; Generate auxiliary correction results according to the standard answer and the extended answer; According to the acquired revision information for the auxiliary revision result, the auxiliary revision result is revised to obtain the revision result of the data to be revised; The step of performing expansion processing on the answer data to obtain an expanded answer includes: Extracting keywords from the answer data; Matching synonyms corresponding to the keywords in a preset extended database; The answer data is expanded according to the synonyms to obtain an expanded answer.
2. The data correction method according to claim 1, characterized in that: The identification processing of the data to be corrected to obtain the question type and standard answer of the data to be corrected includes: Perform identification processing on the data to be corrected to obtain identification data; Matching the topic information corresponding to the identification data from a preset topic database; The question type and standard answer of the data to be corrected are obtained according to the question information.
3. The data correction method according to claim 2, characterized in that: The step of performing identification processing on the data to be corrected to obtain identification data includes: Determine the data type of the data to be revised; The data to be corrected is identified according to the data type to obtain identification data.
4. The data correction method according to claim 2, characterized in that: The step of obtaining the question type and standard answer of the data to be corrected according to the question information includes: Extracting the title identifier in the data to be corrected from the identification data; According to the question identifier, the question type and standard answer of the data to be corrected are determined.
5. The data correction method according to claim 1, characterized in that: Determining the answer data in the data to be corrected according to the question type includes: Determining the positional relationship between the answer part and the question stem part in the data to be corrected according to the question type; According to the positional relationship between the answer part and the question stem part, identifying the position of the answer part in the data to be corrected; The answer data is extracted from the data to be corrected according to the position of the answer part.
6. A data correction device, characterized in that: The data correction device comprises: An identification module is used to identify the data to be corrected and obtain the question type and standard answer of the data to be corrected; An extraction module, used for determining answer data in the data to be corrected according to the question type; An expansion module, used to perform expansion processing on the answer data to obtain an expanded answer; A correction module, used for generating auxiliary correction results according to the standard answer and the extended answer; A revision module, configured to revise the auxiliary revision result according to the revision information obtained for the auxiliary revision result, so as to obtain the revision result of the data to be revised; Wherein, the expansion module includes: The seventh submodule is used to extract keywords from the answer data; An eighth submodule is used to match synonyms corresponding to the keywords in a preset extended database; The ninth submodule is used to expand the answer data according to synonyms to obtain expanded answers.
7. A data correction system, characterized in that: The data correction system comprises a first terminal, a second terminal and a data correction device, wherein: The first terminal is used to send the data to be corrected to the data correction device; The data correction device is used to identify the data to be corrected to obtain the question type and standard answer of the data to be corrected; and according to the question type, determine the answer data in the data to be corrected, and perform expansion processing on the answer data to obtain an expanded answer; and generate an auxiliary correction result according to the standard answer and the expanded answer; and send the auxiliary correction result to the second terminal; The second terminal is used to receive the auxiliary correction result and receive the revision information made by the user for the auxiliary correction result; and send the revision information to the data correction device; The data correction device is further used to receive the revision information, and revise the auxiliary correction result according to the revision information to obtain the correction result of the data to be corrected; and send the correction result to the first terminal; The first terminal is used to receive and output the correction result; The data correction device is specifically used to extract keywords from the answer data; match synonyms corresponding to the keywords according to a preset expansion database; and perform expansion processing on the answer data according to the synonyms to obtain an expanded answer.
8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the data correction method according to any one of claims 1 to 5.
9. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the data correction method according to any one of claims 1 to 5 is executed.
