Automatic topic generation method

Abstract

The present invention discloses a method for automatically generating questions, the method comprising: step S10, obtaining student information, and obtaining knowledge points to be examined corresponding to the student information; step S20, determining a question type that matches the student information and the knowledge points to be examined according to the student information and the knowledge points to be examined; step S30, generating a question that corresponds to the knowledge points to be examined and is consistent with the question type according to the question type and the knowledge points to be examined. The technical solution can automatically generate questions according to the knowledge points to be examined of the students, and the probability of the generated questions repeating with the existing questions is low, thereby improving the efficiency of question generation and improving the assessment effect of the questions on students.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for automatically deriving and generating a topic. Background Art

[0002] With the development and popularization of computer technology and the Internet, people's work, study and lifestyle have undergone great changes. For example, people are increasingly using computers to acquire knowledge, and computers are also providing people with more and more convenient services. In the field of education, computer technology has also provided convenience for teachers and students.

[0003] At present, for the exercises or test questions that teachers or students encounter on a daily basis, teachers basically search for questions from a question bank based on the teaching requirements of the subject. These questions are prone to being repeated with existing questions, and the high repetition rate is not conducive to the assessment of students. Summary of the invention

[0004] The invention provides a method for automatically deriving and generating a topic.

[0005] The present invention provides a method for automatically generating a topic, the method comprising steps S10-S30:

[0006] Step S10: obtaining student information, and obtaining the knowledge points to be examined corresponding to the student information;

[0007] Step S20: determining, according to the student information and the knowledge points to be tested, a question type that matches the student information and the knowledge points to be tested;

[0008] Step S30: Generate, based on the question type and the knowledge point to be tested, questions corresponding to the knowledge point to be tested and consistent with the question type.

[0009] Preferably, the step S10, obtaining student information and obtaining the knowledge points to be examined corresponding to the student information, includes:

[0010] Acquire student information, wherein the student information includes student characteristic information, student grade information, student ability information and historical test information; wherein the student characteristic information includes any one or more of the student ID, student name, student class and student age;

[0011] According to the student grade information, obtaining subject information matching the student grade information;

[0012] According to the subject information, extract all subject knowledge points in the subject information that match the student information;

[0013] According to the student ability information and historical test information, obtain the mastered knowledge points corresponding to the student information;

[0014] The mastered knowledge points are compared with the corresponding knowledge points of all subjects to obtain the unmastered knowledge points corresponding to the student information as the knowledge points to be examined corresponding to the student information.

[0015] Preferably, determining, based on the student information and the knowledge points to be tested, a question type that matches the student information and the knowledge points to be tested comprises:

[0016] Obtaining the difficulty coefficient corresponding to the knowledge point to be examined;

[0017] According to the student ability information, obtaining a range of difficulty coefficients of questions that are acceptable to the student corresponding to the student information;

[0018] Determine whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range;

[0019] If the difficulty coefficient does not exceed the range, determining the first question type as the question type that matches the student information and the knowledge point to be tested; the first question type includes any one of a composition question and a fill-in-the-blank question;

[0020] If it exceeds the difficulty coefficient range, the second question type is determined to be the question type that matches the student information and the knowledge points to be tested, and the second question type includes any one of true-or-false questions and multiple-choice questions.

[0021] Preferably, the method further comprises:

[0022] Push the generated questions to the student terminal corresponding to the student information, so that the students can take the corresponding test based on the generated questions;

[0023] The test results obtained by taking a test based on the generated questions by the student corresponding to the student information and the feedback information of the student are obtained.

[0024] Preferably, the method further comprises:

[0025] According to the generated question, searching a system question bank to identify whether there is an existing question identical to the question in the system question bank;

[0026] If there is no existing question identical to the question, save the question to the system question;

[0027] If there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.

[0028] Preferably, when there are multiple knowledge points to be examined, generating questions corresponding to the knowledge points to be examined and consistent with the question type according to the question type and the knowledge points to be examined includes steps A1-A6:

[0029] Step A1: obtaining text from a preset text library, and splitting the text to obtain a text summary and a text body content corresponding to the text;

[0030] Step A2: determine whether the text summary includes at least M1 knowledge points to be examined. If yes, proceed to step A3; if no, return to step A1; M1 is a positive integer equal to or greater than 1;

[0031] Step A3, dividing the main body of the text to obtain a plurality of sub-contents, removing the sub-contents that do not include any knowledge point to be examined from the plurality of sub-contents, leaving a plurality of first target sub-contents, each of which includes at least one knowledge point to be examined;

[0032] Step A4, calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text;

[0033] Step A5, screening the plurality of first target sub-contents according to the weight proportions to obtain remaining second target sub-contents;

[0034] Step A6: Generate, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type.

[0035] Preferably, the step A4, calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text, includes:

[0036] The association degree between the multiple first target sub-contents is calculated according to the following formula (1):

[0037]

[0038] In formula (1), g i represents the proportion of the knowledge points to be mastered included in the i-th first target sub-content to all the knowledge points to be mastered; g i+1 represents the proportion of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered; g i-1 Indicates the proportion of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; d i represents the ratio between the storage space occupied by the i-th first target sub-content and the storage space occupied by the text main body content; d i+1represents the ratio between the storage space occupied by the i+1th first target sub-content and the storage space occupied by the text main body content; d i-1 represents the ratio between the storage space occupied by the i-1th first target sub-content and the storage space occupied by the text main body content; n is the total number of first target sub-contents;

[0039] Using formula (2), calculate the proportion of all first target sub-contents including the kth knowledge point to be examined in the main text content s 1k , then:

[0040]

[0041] Wherein, m represents the total number of paragraphs in the main body of the text; H kj represents the number of rows occupied by the first target sub-content including the kth knowledge point to be examined in the jth segment; h j Indicates the total number of rows included in the jth segment; Δδ 1k Indicates 1k The corresponding correction value of the page share is a preset value, and its value range is [0.01, 0.05];

[0042] Using formula (3), calculate the frequency of occurrence of all first target sub-contents including the kth knowledge point to be examined in the main text content s 2k , then:

[0043]

[0044] Among them, P kj G represents the number of occurrences of the kth knowledge point to be examined in the jth paragraph; kj represents the total number of occurrences of each knowledge point to be examined in the jth segment; Δδ 2k Indicates 2k The corresponding occurrence frequency ratio correction value is a preset value, and its value range is [0.01, 0.02];

[0045] According to the F, the s 1k 、 2k The weight ratio w of the kth knowledge point to be examined in the main content of the text is calculated using the following formula (4): k , then:

[0046]

[0047] In formula (4), a represents the 1k The related constant is 0.7, b represents the 2k The related constant is taken as 0.3.

[0048] Preferably, the step A5 of screening the plurality of first target sub-contents according to the weight proportions to obtain the remaining second target sub-contents includes:

[0049] Determine the target knowledge points to be examined whose corresponding weight ratio is equal to or greater than the preset weight ratio threshold;

[0050] Acquire each first target sub-content including the target knowledge point to be examined, and use each first target sub-content including the target knowledge point to be examined as the second target sub-content;

[0051] Step A6: generating, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type, including:

[0052] The following operations are performed for each second target sub-content: the target knowledge points to be examined contained in the current second target sub-content are extracted; and questions corresponding to the extracted target knowledge points to be examined and consistent with the question type are generated based on the current second target sub-content and the extracted target knowledge points to be examined.

[0053] The automatic derivation and generation method of questions of the present invention can generate questions intelligently and automatically according to the knowledge points to be tested of the students, avoid duplication with existing test questions, have a low question duplication rate, can improve the test and assessment effect on students, and has a fast question generating speed, thereby improving the efficiency and accuracy of question generation, and improving the intelligence and objectivity of question generation.

[0054] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the contents pointed out in the written description, claims, and drawings.

[0055] The technical solution of the present invention is further described below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a schematic diagram of the workflow of an implementation method of the automatic derivation and generation method of the topic of the present invention. DETAILED DESCRIPTION

[0058] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0059] The present invention provides a method for automatically deriving and generating questions, aiming to automatically derive and generate corresponding questions according to relevant knowledge points, replacing the traditional question-setting method of manual question-setting.

[0060] like Figure 1 As shown, Figure 1 The figure is a schematic diagram of a workflow of an embodiment of the method for automatically generating a topic according to the present invention. The method for automatically generating a topic according to the present invention can be implemented as steps S10-S30 described below:

[0061] Step S10: Obtain student information, and obtain the knowledge points to be examined corresponding to the student information.

[0062] Step S20: Determine, based on the student information and the knowledge points to be tested, a question type that matches the student information and the knowledge points to be tested.

[0063] Step S30: Generate, based on the question type and the knowledge point to be tested, questions corresponding to the knowledge point to be tested and consistent with the question type.

[0064] In one embodiment, the step S10, obtaining student information and obtaining the knowledge points to be examined corresponding to the student information, can be specifically implemented as follows:

[0065] Acquire student information, wherein the student information includes student characteristic information, student grade information, student ability information and historical test information; wherein the student characteristic information includes any one or more of the student ID, student name, student class and student age;

[0066] According to the student grade information, obtaining subject information matching the student grade information;

[0067] According to the subject information, extract all subject knowledge points in the subject information that match the student information;

[0068] According to the student ability information and historical test information, obtain the mastered knowledge points corresponding to the student information;

[0069] The mastered knowledge points are compared with the corresponding knowledge points of all subjects to obtain the unmastered knowledge points corresponding to the student information as the knowledge points to be examined corresponding to the student information.

[0070] In one embodiment, determining the question type matching the student information and the knowledge point to be tested according to the student information and the knowledge point to be tested can be specifically implemented as follows:

[0071] Obtaining the difficulty coefficient corresponding to the knowledge point to be examined;

[0072] According to the student ability information, obtaining a range of difficulty coefficients of questions that are acceptable to the student corresponding to the student information;

[0073] Determine whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range;

[0074] If the difficulty coefficient does not exceed the range, determining the first question type as the question type that matches the student information and the knowledge point to be tested; the first question type includes any one of a composition question and a fill-in-the-blank question;

[0075] If it exceeds the difficulty coefficient range, the second question type is determined to be the question type that matches the student information and the knowledge points to be tested, and the second question type includes any one of true-or-false questions and multiple-choice questions.

[0076] In one embodiment, the method may further include the following steps:

[0077] Pushing the questions generated in step S30 to the student terminal corresponding to the student information, so that the student can take the corresponding test based on the generated questions;

[0078] The test results obtained by taking a test based on the generated questions by the student corresponding to the student information and the feedback information of the student are obtained.

[0079] In one embodiment, the method may further include the following steps:

[0080] According to the generated question, searching a system question bank to identify whether there is an existing question identical to the question in the system question bank;

[0081] If there is no existing question identical to the question, save the question to the system question;

[0082] If there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.

[0083] The above technical solution can easily and quickly expand the questions in the system question bank and improve the speed of question expansion in the system question bank.

[0084] In one embodiment, when there are multiple knowledge points to be tested (for example, when the knowledge points to be tested are multiple English knowledge points, the English knowledge points may be vocabulary, idioms, grammar, fixed sentence patterns or structures, etc.), at this time, generating questions corresponding to the knowledge points to be tested and consistent with the question type according to the question type and the knowledge points to be tested may include steps A1-A6:

[0085] Step A1: obtaining a text (e.g., an English novel) from a preset text library, and splitting the text to obtain a text summary and a text body content corresponding to the text;

[0086] Step A2: determine whether the text summary includes at least M1 knowledge points to be examined. If yes, proceed to step A3; if no, return to step A1; M1 is a positive integer equal to or greater than 1;

[0087] Step A3, dividing the main body of the text to obtain a plurality of sub-contents, removing the sub-contents that do not include any knowledge point to be examined from the plurality of sub-contents, leaving a plurality of first target sub-contents, each of which includes at least one knowledge point to be examined;

[0088] Step A4, calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text;

[0089] Step A5, screening the plurality of first target sub-contents according to the weight proportions to obtain remaining second target sub-contents;

[0090] Step A6: Generate, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type.

[0091] In one embodiment, the step A4 of calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text includes:

[0092] The association degree between the multiple first target sub-contents is calculated according to the following formula (1):

[0093]

[0094] In formula (1), g i represents the proportion of the knowledge points to be mastered included in the i-th first target sub-content to all the knowledge points to be mastered; g i+1 represents the proportion of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered; g i-1 Indicates the proportion of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; d i represents the ratio between the storage space occupied by the i-th first target sub-content and the storage space occupied by the text main body content; d i+1 represents the ratio between the storage space occupied by the i+1th first target sub-content and the storage space occupied by the text main body content; d i-1represents the ratio between the storage space occupied by the i-1th first target sub-content and the storage space occupied by the text main body content; n is the total number of first target sub-contents;

[0095] Using formula (2), calculate the proportion of all first target sub-contents including the kth knowledge point to be examined in the main text content s 1k , then:

[0096]

[0097] Wherein, m represents the total number of paragraphs in the main body of the text; H kj represents the number of rows occupied by the first target sub-content including the kth knowledge point to be examined in the jth segment; h j Indicates the total number of rows included in the jth segment; Δδ 1k Indicates 1k The corresponding correction value of the page share is a preset value, and its value range is [0.01, 0.05];

[0098] Using formula (3), calculate the frequency of occurrence of all first target sub-contents including the kth knowledge point to be examined in the main text content s 2k , then:

[0099]

[0100] Among them, P kj G represents the number of occurrences of the kth knowledge point to be examined in the jth paragraph; kj represents the total number of occurrences of each knowledge point to be examined in the jth segment; Δδ 2k Indicates 2k The corresponding occurrence frequency ratio correction value is a preset value, and its value range is [0.01, 0.02];

[0101] According to the F, the s 1k 、 2k The weight ratio w of the kth knowledge point to be examined in the main content of the text is calculated using the following formula (4): k , then:

[0102]

[0103] In formula (4), a represents the 1k The related constant is 0.7, b represents the 2k The related constant is taken as 0.3.

[0104] In one embodiment, the step A5 of screening the plurality of first target sub-contents according to the weight proportions to obtain the remaining second target sub-contents includes:

[0105] Determine the target knowledge points to be examined whose corresponding weight ratio is equal to or greater than the preset weight ratio threshold;

[0106] Acquire each first target sub-content including the target knowledge point to be examined, and use each first target sub-content including the target knowledge point to be examined as the second target sub-content;

[0107] Step A6: generating, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type, including:

[0108] The following operations are performed for each second target sub-content: the target knowledge points to be examined contained in the current second target sub-content are extracted; and questions corresponding to the extracted target knowledge points to be examined and consistent with the question type are generated based on the current second target sub-content and the extracted target knowledge points to be examined.

[0109] For example, when the question type is a multiple-choice question and the current second target sub-content is a paragraph of English, which includes three sentences and two knowledge points to be tested, one of which is an English vocabulary and the other is a fixed sentence structure; then, "generating a question corresponding to the extracted target knowledge points to be tested and consistent with the question type according to the current second target sub-content and the extracted target knowledge points to be tested" can be implemented as follows: remove the target knowledge points to be tested in the current second target sub-content and replace them with brackets, and give a corresponding number of optional fill-in items for each bracket to generate a question.

[0110] The automatic derivation and generation method of questions of the present invention can generate questions intelligently and automatically according to the knowledge points to be tested of the students, avoid duplication with existing test questions, have a low question duplication rate, can improve the test and assessment effect on students, and has a fast question generating speed, thereby improving the efficiency and accuracy of question generation, and improving the intelligence and objectivity of question generation.

[0111] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatically generating a topic, characterized in that: The method comprises steps S10-S30: Step S10: obtaining student information, and obtaining the knowledge points to be examined corresponding to the student information; Step S20, determining a question type matching the student information and the knowledge point to be tested according to the student information and the knowledge point to be tested; Step S30, generating questions corresponding to the knowledge points to be tested and consistent with the question type according to the question type and the knowledge points to be tested; Wherein, when there are multiple knowledge points to be examined, generating questions corresponding to the knowledge points to be examined and consistent with the question type according to the question type and the knowledge points to be examined includes steps A1-A6: Step A1: obtaining text from a preset text library, and splitting the text to obtain a text summary and a text body content corresponding to the text; Step A2: determine whether the text summary includes at least M1 knowledge points to be examined. If yes, proceed to step A3; if no, return to step A1; M1 is a positive integer equal to or greater than 1; Step A3, dividing the main body of the text to obtain a plurality of sub-contents, removing the sub-contents that do not include any knowledge point to be examined from the plurality of sub-contents, leaving a plurality of first target sub-contents, each of which includes at least one knowledge point to be examined; Step A4, calculating the weight ratio of the to-be-examined knowledge points included in each first target sub-content in the main body of the text; Step A5, screening the plurality of first target sub-contents according to the weight proportions to obtain remaining second target sub-contents; Step A6: generating, according to the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type; The step A4 of calculating the weight ratio of the knowledge points to be examined included in each first target sub-content in the main body of the text includes: The association degree between the multiple first target sub-contents is calculated according to the following formula (1): In formula (1), g i represents the proportion of the knowledge points to be mastered included in the i-th first target sub-content to all the knowledge points to be mastered; g i+1 represents the proportion of the knowledge points to be mastered included in the i+1th first target sub-content to all the knowledge points to be mastered; g i-1 Indicates the proportion of the knowledge points to be mastered included in the first target sub-content to all the knowledge points to be mastered; d i represents the ratio between the storage space occupied by the i-th first target sub-content and the storage space occupied by the text main body content; d i+1 represents the ratio between the storage space occupied by the i+1th first target sub-content and the storage space occupied by the text main body content; d i-1 represents the ratio between the storage space occupied by the i-1th first target sub-content and the storage space occupied by the text main body content; n is the total number of first target sub-contents; Using formula (2), calculate the proportion of all first target sub-contents including the kth knowledge point to be examined in the main text content s 1k , then: Wherein, m represents the total number of paragraphs in the main body of the text; H kj represents the number of rows occupied by the first target sub-content including the kth knowledge point to be examined in the jth paragraph; h j Indicates the total number of rows included in the jth segment; Δδ 1k Indicates 1k The corresponding correction value of the page share is a preset value, and its value range is [0.01, 0.05]; Using formula (3), calculate the frequency of occurrence of all first target sub-contents including the kth knowledge point to be examined in the main text content s 2k , then: Among them, P kj G represents the number of occurrences of the kth knowledge point to be examined in the jth paragraph; kj represents the total number of occurrences of each knowledge point to be examined in the jth segment; Δδ 2k Indicates 2k The corresponding occurrence frequency ratio correction value is a preset value, and its value range is [0.01, 0.02]; According to the F, the s 1k 、 2k The weight ratio w of the kth knowledge point to be examined in the main content of the text is calculated using the following formula (4): k , then: In formula (4), a represents the 1k The related constant is 0.7, b represents the 2k The related constant is taken as 0.3; The step A5 of screening the plurality of first target sub-contents according to the weight proportions to obtain the remaining second target sub-contents includes: Determine the target knowledge points to be examined whose corresponding weight ratio is equal to or greater than the preset weight ratio threshold; Acquire each first target sub-content including the target knowledge point to be examined, and use each first target sub-content including the target knowledge point to be examined as the second target sub-content; Step A6: generating, based on the second target sub-content, a question that contains the knowledge points to be tested and is consistent with the question type, including: The following operations are performed for each second target sub-content: the target knowledge points to be examined contained in the current second target sub-content are extracted; and questions corresponding to the extracted target knowledge points to be examined and consistent with the question type are generated based on the current second target sub-content and the extracted target knowledge points to be examined.

2. The method for automatically generating a topic according to claim 1, wherein: The step S10, obtaining student information and obtaining the knowledge points to be examined corresponding to the student information, includes: Acquire student information, wherein the student information includes student characteristic information, student grade information, student ability information and historical test information; wherein the student characteristic information includes any one or more of the student ID, student name, student class and student age; According to the student grade information, obtaining subject information matching the student grade information; According to the subject information, extract all subject knowledge points in the subject information that match the student information; According to the student ability information and historical test information, obtain the mastered knowledge points corresponding to the student information; The mastered knowledge points are compared with the corresponding knowledge points of all subjects to obtain the unmastered knowledge points corresponding to the student information as the knowledge points to be examined corresponding to the student information.

3. The method for automatically generating a topic according to claim 2, wherein: The step of determining, based on the student information and the knowledge points to be tested, a question type that matches the student information and the knowledge points to be tested comprises: Obtaining the difficulty coefficient corresponding to the knowledge point to be examined; According to the student ability information, obtaining a range of difficulty coefficients of questions that are acceptable to the student corresponding to the student information; Determine whether the difficulty coefficient corresponding to the knowledge point to be examined exceeds the difficulty coefficient range; If the difficulty coefficient does not exceed the range, determining the first question type as the question type that matches the student information and the knowledge point to be tested; the first question type includes any one of a composition question and a fill-in-the-blank question; If it exceeds the difficulty coefficient range, the second question type is determined to be the question type that matches the student information and the knowledge points to be tested, and the second question type includes any one of true-or-false questions and multiple-choice questions.

4. The method for automatically generating a topic according to claim 1, wherein: The method further comprises: Push the generated questions to the student terminal corresponding to the student information, so that the students can take the corresponding test based on the generated questions; Obtain the test results obtained by the student corresponding to the student information based on the generated questions and the student's feedback information.

5. The method for automatically generating a topic according to claim 1, wherein: The method further comprises: According to the generated question, searching a system question bank to identify whether there is an existing question identical to the question in the system question bank; If there is no existing question identical to the question, save the question to the system question; If there is an existing topic that is the same as the topic, step S30 is re-executed to generate a new topic.

Images