CN111209728A - Automatic test question labeling and inputting method - Google Patents
Automatic test question labeling and inputting method Download PDFInfo
- Publication number
- CN111209728A CN111209728A CN202010032609.2A CN202010032609A CN111209728A CN 111209728 A CN111209728 A CN 111209728A CN 202010032609 A CN202010032609 A CN 202010032609A CN 111209728 A CN111209728 A CN 111209728A
- Authority
- CN
- China
- Prior art keywords
- keywords
- test question
- test
- question
- words
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 237
- 238000002372 labelling Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 230000014509 gene expression Effects 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 9
- 238000013179 statistical model Methods 0.000 abstract description 5
- 238000010276 construction Methods 0.000 description 10
- 238000000605 extraction Methods 0.000 description 10
- 238000001914 filtration Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Abstract
The invention relates to an automatic test question labeling and inputting method, which comprises the following steps: automatically converting the word test question document into a corresponding html document and storing the html document; automatically extracting text content of the html document; adopting an n-element grammar model in a statistical model to carry out word segmentation on the text content, and using a hidden Markov model to carry out part-of-speech tagging on the segmented words; extracting the test question features of the words marked with the parts of speech, judging whether the features of the words correspond to the features of preset test question keywords or not, and if so, marking the keywords of the words and marking the positions of the words in the text; segmenting the test questions one by one according to the keyword of the question number; and assembling the test questions in a test question constructing module according to the keywords which are segmented one by one and the positions of the keywords in the text, and storing the assembled test questions to the corresponding positions. The invention effectively improves the accuracy of automatic test question input and solves the problem that pictures or formulas cannot be automatically input.
Description
Technical Field
The invention relates to the field of online examination, in particular to an automatic test question labeling and inputting method.
Background
With the development of network technology, more and more education and training institutions adopt an online examination mode, in order to adapt to scale, scientification and standardization of the examination, the establishment of the test question bank is the core of adapting to the scale, scientification and standardization of the examination, and the first indispensable link for establishing the test question bank is the entry of the test questions.
The existing test question entry method includes entry of test questions and entry based on a regular expression manually, wherein the manual entry usually includes a plurality of text boxes in a specific test question entry system webpage, and corresponding contents need to be entered respectively, such as a question stem, an answer, an option, analysis and the like of a test question, if the test question includes a picture and a formula, the entry needs to be performed by clicking a mode of inserting the picture or a formula button, however, the mode of manually entering the test question is complex, and when the number of the test questions is large, the entry needs a lot of time, and batch entry of the test questions cannot be achieved. The input mode based on the regular expression generally adopts the regular expression to extract each part of content in the test questions, and because the upper and lower structures of the test questions of the same type are similar, the regular expression can be respectively written to extract question stems, answers, options, analysis and the like, so as to realize the input function of the test questions, but the input mode based on the regular expression can extract each part of content of the test questions, but the mode has strict requirements on the test question format in the source word document, different people have different test question writing habits, the test question formats are difficult to unify, once the test questions contain the content consistent with the segmentation rules, the test questions are marked to cause errors in segmenting the test questions, if the test question stems contain A, B, C, D letters, the test question stems can be marked as options of choice questions, and the input method based on the regular expression for inputting the test questions has low accuracy, and the input method for the test questions is low in segmenting the test questions, The practicability is not high, in addition, the method is mainly applied to test questions of a pure text type and cannot be used for extracting and inputting the test questions containing pictures or formulas.
Disclosure of Invention
The invention aims to overcome at least one defect in the prior art, and provides an automatic test question labeling and inputting method which can realize batch input of test questions and improve the accuracy of test question input.
The technical scheme adopted by the invention is as follows:
the method for automatically labeling and inputting the test questions comprises the following steps:
s1, receiving a word test question document, automatically converting the word test question document into a corresponding html document, and storing the html document;
s2, automatically extracting text contents of the html document;
s3, performing word segmentation on the extracted text content, performing part-of-speech tagging on the segmented words, and tagging the positions of the words in the text;
s4, extracting the test question features of the words marked with the parts of speech, judging whether the features of the words correspond to the features of preset test question keywords or not, if so, marking the keywords of the words, and taking the words marked as the keywords as determined keywords;
s5, segmenting the test questions one by one according to the determined keywords, and storing the keywords of each test question;
and S6, assembling the test questions in a test question constructing module according to the keywords which are segmented one by one and the positions of the keywords in the text, and storing the assembled test questions to the corresponding positions according to the keywords and the positions of the keywords in the text.
By converting the word document into the html document for processing, pictures and formulas in the test questions can be completely stored, and the problem that the test question document with the pictures or the formulas cannot be automatically input is solved; the method has the advantages that the statistical model is adopted to carry out word segmentation on the test question text, the segmented words are labeled according to the word types, the word types are used as auxiliary judgment conditions to extract the key words of the test question features, and therefore the accuracy of automatic segmentation of the test questions is improved.
Further, the step S1, while automatically converting the word test question document into the corresponding html document, further includes converting the formula in the document into a picture and recording the corresponding position tag of the picture in the document, and storing the picture and the corresponding position tag thereof and the html document in the same folder.
Further, the step S2 includes extracting a position tag of the picture and marking a corresponding position of the picture in the text.
Further, the step S4 of determining whether the features of the words correspond to the features of the preset test question keywords specifically includes performing test question feature extraction on the words by using a multilayer regular expression, determining whether the words correspond to the preset test question keyword features, if yes, performing keyword labeling on the words, and taking the words labeled as keywords as the determined keywords.
And extracting the test question features of the words through a plurality of layers of regular expressions, judging whether the words correspond to preset test question key word features, and labeling the key words if the words correspond to the preset test question key word features, so that the test question features can be judged well, and the accuracy of the test question key word labeling is improved.
Further, the step S4 includes performing secondary filtering on the terms labeled as keywords.
Further, the determined keywords include one or more of a question number, a choice, an answer, and a resolution.
Further, the step S6 is to divide the test questions one by one according to the determined keywords, specifically, the method uses the question number keywords as the judgment basis, and if answer keywords and/or analysis keywords are included between two question number keywords, the test questions are divided; if there is no answer keyword and/or no parse keyword between one topic number keyword and the next topic number keyword, then the next topic number keyword is marked as a disturbance.
Further, the secondary screening of the labeled keywords is specifically to perform keyword combination on all keywords in a single test question through a random variation algorithm and calculate scores of all keyword combinations, and select a keyword with a combination with the highest score as a determined keyword.
And combining and secondarily screening the marked keywords through a random variation algorithm, calculating the score of the keyword combination, and selecting the combined keyword with the highest score as the determined keyword, so that the most suitable combination can be found out, and the accuracy of test question feature extraction is improved.
Further, the step S6 further includes assembling the determined keywords in different types of test question constructing modules, calculating scores of the assembled test questions in the different types of test question constructing modules, comparing the scores of the same test question in the different types of test question constructing modules, taking the type of the test question constructing module with the highest score as the type of the test question, and labeling the type of the test question.
The keywords with the highest scores are determined to be subjected to test question assembly in the test question constructing modules of different types, the scores of the same test question in the test question constructing modules of different types are compared, the type of the test question constructing module with the highest score is selected as the type of the test question, and the accuracy of automatic labeling of the test question type is improved.
Further, the step S6 further includes searching for a position tag of a picture in the test question, and storing the picture contained in the test question in a corresponding position.
Compared with the prior art, the invention has the beneficial effects that:
(1) the word document is converted into the html document to be processed, pictures and formulas in the test questions can be completely stored, corresponding positions of the pictures and the formulas in the text are marked, the pictures are found through indexes and are inserted into the corresponding positions when the test questions are called, and the test question document with the pictures and the formulas is automatically input.
(2) The test question content is segmented by adopting an n-element grammar model in a statistical model, and the segmented words are labeled by using a hidden Markov model. The part of speech is used as an auxiliary judgment condition to extract the test question feature key words, so that the accuracy of automatic segmentation of the test questions is improved.
(3) The words are subjected to test question feature extraction by adopting a multilayer regular expression, and the word is used as a basis for judging the key words of the test questions on the basis of the part of speech, so that the limiting conditions are wide, the features in the test questions are well reserved, and the test question feature extraction is more flexible compared with the test question feature extraction of a single regular expression.
(4) The key word combinations with the highest scores are selected by combining and secondarily screening the key word features of the single test question which is divided by the random variation algorithm, so that the accuracy of test question feature extraction is improved, the combination with the highest scores of the key words of each test question is assembled in test question construction modules of different types, the type of the test question construction module with the highest scores is selected as the type of the test question, and the accuracy of automatic labeling of the test question types is improved.
Drawings
FIG. 1 is an overall flow chart of an embodiment of the present invention;
fig. 2 is a flowchart of determining keyword labeling according to an embodiment of the present invention, in which a is a flowchart of determining keyword labeling for an issue number, b is a flowchart of determining keyword labeling for an option, c is a flowchart of determining keyword labeling for an answer, and d is a flowchart of determining keyword labeling for analysis;
FIG. 3 is a flow chart of test question assembly according to an embodiment of the present invention.
Detailed Description
The drawings are only for purposes of illustration and are not to be construed as limiting the invention. For a better understanding of the following embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
As shown in fig. 1, this embodiment provides an automatic test question labeling and entering method, which includes:
s1, receiving a word test question document, automatically converting the word test question document into a corresponding html document, and storing the html document;
s2, automatically extracting text contents of the html document;
s3, performing word segmentation on the extracted text content, performing part-of-speech tagging on the segmented words, and tagging the positions of the words in the text;
s4, extracting the test question features of the words marked with the parts of speech, judging whether the features of the words correspond to the features of preset test question keywords or not, if so, marking the keywords of the words, and taking the words marked as the keywords as determined keywords;
s5, segmenting the test questions one by one according to the determined keywords, and storing the keywords of each test question;
and S6, assembling the test questions in a test question constructing module according to the keywords which are segmented one by one and the positions of the keywords in the text, finding the corresponding document of the assembled test questions according to the keywords and the positions of the keywords in the text, and storing the document to the corresponding position.
Specifically, when a test question needs to be recorded, a system reads the content of a word document uploaded by a user through a program and converts the word document into an html document, an html parser is used for obtaining the text content of the html document, then an n-element grammar model in a statistical model is used for carrying out word segmentation on the text content, the corresponding positions of the segmented words in the text are marked and word position indexes are generated, a hidden Markov model is used for carrying out part-of-speech tagging on the segmented words, and the words with part-of-speech tagging are put into a word set; the marked words are sequentially transmitted into a test question feature keyword marking module to perform test question feature extraction on the words marked with the parts of speech, the features of the words are compared with the features of the test question keywords according to preset conditions, whether the words are the test question keywords or not is judged, the specific judgment process is that whether the conditions are met or not is sequentially judged from top to bottom according to the preset conditions, if one condition is not met, the current words are not the corresponding features of the test question keywords, if the conditions are met, the words are subjected to keyword marking and the positions of the words in the text are marked to generate a keyword index, and the words marked as the keywords are used as determined keywords; and finally, segmenting the test questions one by one according to the determined question number keywords, storing the keywords of each test question, assembling each test question in a test question construction module according to the keywords segmented one by one and the positions of the keywords in the text, finding out the corresponding text through the keywords and the position indexes of the keywords contained in the keywords, and storing the text to the specified position. By converting the word document into the html document for processing through the implementation mode, pictures and formulas in the test questions can be completely stored, and the problem that the test question document with the pictures or the formulas cannot be automatically input is solved; the method has the advantages that the statistical model is adopted to carry out word segmentation on the test question text, the segmented words are labeled according to the word types, the word types are used as auxiliary judgment conditions to extract the key words of the test question features, and therefore the accuracy of automatic segmentation of the test questions is improved.
In this embodiment, in step S1, the method for automatically converting a word test question document into a corresponding html document also includes converting a formula in the document into a picture, recording a position tag corresponding to the picture in the document, and storing the picture and the position tag corresponding to the picture in the same folder as the html document.
In this embodiment, the step S2 further includes extracting a position tag of the picture and marking a corresponding position of the picture in the text.
Specifically, the step S1 includes converting the word test question document into a corresponding html document, converting the formula in the document into a picture, recording the corresponding position tag of the picture in the html document, and then placing all the pictures and the corresponding position tags in the same folder stored in the html document, so that the test question document with the pictures and the formula can be recorded in the label without losing content information.
In this embodiment, the step S4 of determining whether the features of the words correspond to the features of the preset test question keywords specifically includes performing test question feature extraction on the words by using a multilayer regular expression, determining whether the words correspond to the preset test question keyword features, if yes, performing keyword labeling on the words, and taking the words labeled as keywords as the determined keywords.
And extracting the test question features of the words through a plurality of layers of regular expressions, judging whether the words correspond to preset test question key word features, and labeling the key words if the words correspond to the preset test question key word features, so that the test question features can be judged well, and the accuracy of the test question key word labeling is improved.
In this embodiment, the step S4 further includes performing secondary filtering on the labeled keyword.
In this embodiment, the determined keywords include one or more of a question number, a choice, an answer, and a resolution.
Specifically, the determined keywords include one or more of a question number, a choice, an answer and an analysis, the step S4 determines whether the characteristics of the words correspond to the characteristics of preset test question keywords, specifically, the marked words are sequentially transmitted to a test question characteristic keyword marking module, the test question characteristic keyword marking module adopts a multilayer regular expression to perform test question characteristic extraction on the words, compares the characteristics of the words with the characteristics of the test question keywords according to preset conditions, and determines whether the words are test question keywords, the preset keyword condition determination flowchart is specifically shown in fig. 2, where a is a judgment flowchart of the question number keywords, b is a judgment flowchart of the choice keywords, c is a judgment flowchart of the answer keywords marking, and d is a judgment flowchart of the analysis keywords marking, the keyword judgment process specifically comprises the steps of sequentially judging whether the words with the parts of speech labeled meet the keyword judgment condition from top to bottom, labeling the words if all the words meet the keyword judgment condition, and judging the keywords of the words with the parts of speech labeled in such a way that the keywords are not corresponding keyword characteristics if one condition does not meet the condition, so that test question characteristics can be better judged, but the condition of wrong labeling still exists in such a way, and therefore, the words labeled as the keywords need to be secondarily screened.
In this embodiment, the step S6 of segmenting the test questions one by one according to the determined keywords specifically uses the question number keywords as a judgment basis, and if answer keywords and/or analysis keywords are included between two question number keywords, the test questions are segmented; if there is no answer keyword and/or no parse keyword between one topic number keyword and the next topic number keyword, then the next topic number keyword is marked as a disturbance.
Specifically, the step S6 is to divide the test questions one by one according to the determined keywords, specifically, the test questions are divided based on the question number keywords, and the two question number keywords must include answer keywords or analysis keywords to divide the test questions, when there is no answer keyword or analysis keyword between one question number keyword and the next question number keyword, the second question number keyword is marked as interference, the interference keyword is ignored to continue to index and find the next question number keyword until the question number keyword meeting the condition is found, and after the question division is completed, the keywords of each test question and the keyword position indexes corresponding to the keywords are stored; through the implementation mode, the condition that the segmentation of the test questions is wrong due to the mistake of labeling the keywords can be avoided.
In this embodiment, the secondary screening of the labeled keywords is specifically to perform keyword combination on all keywords in a single test question through a random variation algorithm and calculate scores of all keyword combinations.
Specifically, a single test question contains a plurality of characteristic keywords, but the keywords obtained through the previous labeling are not necessarily correct, and secondary screening needs to be performed on the characteristic keywords of the single test question, wherein the secondary screening is to combine all the keywords in the single test question through a random variation algorithm, then calculate the scores of all the keyword combinations, and select the combined keyword with the highest score as the determined keyword.
And combining and secondarily screening the marked keywords through a random variation algorithm, calculating the score of the keyword combination, and selecting the combined keyword with the highest score as the determined keyword, so that the most suitable combination can be found out, and the accuracy of test question feature extraction is improved.
In this embodiment, the step S6 further includes selecting a keyword combination with the highest score to assemble the test questions in the test question constructing modules of different types, calculating scores of the assembled test questions in the test question constructing modules of different types, comparing the scores of the same test question in the test question constructing modules of different types, taking the type of the test question constructing module with the highest score as the type of the test question, and labeling the type of the test question.
Specifically, the types of the test question constructing modules include a single-choice question constructing module, a multiple-choice question constructing module, a judgment question constructing module, a short-answer question constructing module and an analysis question constructing module, the keyword combinations with the highest scores are respectively put into the test question constructing modules of different types for test question assembly, as shown in fig. 3, a flow chart of the test question assembling of the test question constructing module is shown, and scores of the same test question in the test question constructing modules of different types are calculated, specifically, in the single-choice question constructing module, the more the conditions of unique question numbers, unique answers, unique option sequences and unique analysis are met, the higher the calculated score is; in the multi-choice question construction module, the more the conditions that the number of the question is unique, the number of the answers are multiple, no characters exist among the answers, the order of the options appears and the only one is analyzed, the higher the calculated score is; in the judgment question construction module, the more the conditions of unique question number, unique answer and unique analysis are met, the higher the calculated score is; in the short answer construction module, the more the conditions of unique question number, unique answer and unique analysis are met, the higher the calculated score is; in the analysis question construction module, the more the conditions of multiple question numbers, unique answer and unique analysis are satisfied, the higher the calculated score is. Selecting a keyword combination with the highest score to assemble test questions in test question constructing modules of different types, selecting a model of the test question constructing module with the highest score as a test question type of the test questions, finally finding corresponding texts through keywords and keyword position indexes contained in the keywords and storing the texts to corresponding positions, correspondingly storing the assembled test questions and the test question types one by one, finding corresponding positions of corresponding picture marks in the test questions, correspondingly storing the pictures contained in the test questions, and facilitating calling and inputting.
The keywords with the highest scores are combined in the test question construction modules of different types to carry out test question assembly and calculate scores, the scores of the same test question in the test question construction modules of different types are compared, the type of the test question construction module with the highest score is selected as the type of the test question, and the accuracy of automatic labeling of the test question types is improved.
In this embodiment, the step S6 further includes searching for a position tag of a picture in the test question, and storing the picture contained in the test question in a corresponding position.
Specifically, after the types of the test questions are determined, the types of the test questions and the test questions are stored in a one-to-one correspondence mode, the position labels of the corresponding pictures in the test questions are searched, the pictures contained in the test questions are stored in the corresponding positions in the test questions, and calling and inputting are facilitated.
Claims (10)
1. An automatic test question labeling and inputting method is characterized by comprising the following steps:
s1, receiving a word test question document, automatically converting the word test question document into a corresponding html document, and storing the html document;
s2, automatically extracting text contents of the html document;
s3, performing word segmentation on the extracted text content, performing part-of-speech tagging on the segmented words, and tagging the positions of the words in the text;
s4, extracting the test question features of the words marked with the parts of speech, judging whether the features of the words correspond to the features of preset test question keywords or not, if so, marking the keywords of the words, and taking the words marked as the keywords as determined keywords;
s5, segmenting the test questions one by one according to the determined keywords, and storing the keywords of each test question;
and S6, assembling the test questions in a test question constructing module according to the keywords which are segmented one by one and the positions of the keywords in the text, and storing the assembled test questions to the corresponding positions according to the keywords and the positions of the keywords in the text.
2. The method for automatically labeling and inputting test questions according to claim 1, wherein in step S1, the method for automatically converting word test question documents into corresponding html documents further comprises converting formulas in the documents into pictures and recording corresponding position tags of the pictures in the documents, and storing the pictures and the corresponding position tags thereof and the html documents in the same folder.
3. The method for automatically labeling and entering test questions according to claim 2, wherein the step S2 further comprises extracting a position tag of the picture and marking a corresponding position of the picture in a text.
4. The method for automatically labeling and entering test questions according to claim 1, wherein the step S4 of judging whether the characteristics of the words correspond to the characteristics of preset test question keywords is to specifically extract the characteristics of the test questions by using a multilayer regular expression, judge whether the words correspond to the characteristics of the preset test question keywords, and label the keywords of the words if the words correspond to the characteristics of the preset test question keywords, and use the words labeled as the keywords as the determined keywords.
5. The method for automatically labeling and entering test questions according to claim 4, wherein the step S4 further comprises performing secondary screening on the terms labeled as keywords.
6. The method as claimed in claim 1, wherein the determined keywords include one or more of title, option, answer and resolution.
7. The method as claimed in claim 6, wherein in step S6, the test questions are segmented one by one according to the determined keywords, specifically, the test questions are segmented based on the question number keywords, and if answer keywords and/or analysis keywords are included between two question number keywords, the test questions are segmented; if there is no answer keyword and/or no parse keyword between one topic number keyword and the next topic number keyword, then the next topic number keyword is marked as a disturbance.
8. The method for automatically labeling and entering test questions according to claim 5, wherein the secondary screening of the labeled keywords is specifically to combine all keywords in a single test question by a random variation algorithm and calculate scores of all keyword combinations, and select a combined keyword with the highest score as the determined keyword.
9. The method as claimed in claim 1 or 8, wherein the step S6 further includes assembling the determined keywords in different types of test question constructing modules, calculating scores of the assembled test questions in the different types of test question constructing modules, comparing the scores of the same test question in the different types of test question constructing modules, regarding the type of the test question constructing module with the highest score as the type of the test question, and labeling the type of the test question.
10. The method for automatically labeling and entering test questions according to claim 2, wherein the step S6 further comprises searching position labels of pictures in the test questions, and storing the pictures contained in the test questions in corresponding positions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010032609.2A CN111209728B (en) | 2020-01-13 | 2020-01-13 | Automatic labeling and inputting method for test questions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010032609.2A CN111209728B (en) | 2020-01-13 | 2020-01-13 | Automatic labeling and inputting method for test questions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111209728A true CN111209728A (en) | 2020-05-29 |
| CN111209728B CN111209728B (en) | 2024-01-30 |
Family
ID=70786103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010032609.2A Active CN111209728B (en) | 2020-01-13 | 2020-01-13 | Automatic labeling and inputting method for test questions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111209728B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680669A (en) * | 2020-08-12 | 2020-09-18 | 江西风向标教育科技有限公司 | Test question segmentation method and system and readable storage medium |
| CN111737949A (en) * | 2020-07-22 | 2020-10-02 | 江西风向标教育科技有限公司 | Topic content extraction method and device, readable storage medium and computer equipment |
| CN111832282A (en) * | 2020-07-16 | 2020-10-27 | 平安科技（深圳）有限公司 | External knowledge fused BERT model fine adjustment method and device and computer equipment |
| CN112052646A (en) * | 2020-08-27 | 2020-12-08 | 安徽聚戎科技信息咨询有限公司 | Text data labeling method |
| CN113065316A (en) * | 2021-03-26 | 2021-07-02 | 洛阳圣昂通网络科技有限公司 | Method for dynamically converting formal thumbnail file into html (hypertext markup language) and inputting question bank, selecting questions from question bank and composing draft and generating thumbnail file |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199871A (en) * | 2014-08-19 | 2014-12-10 | 南京富士通南大软件技术有限公司 | High-speed test question inputting method for intelligent teaching |
| CN106802937A (en) * | 2016-12-30 | 2017-06-06 | 江苏中育优教科技发展有限公司 | The conversion method and system of Word document |
| CN109614594A (en) * | 2018-11-27 | 2019-04-12 | 浙江万朋教育科技股份有限公司 | A method of topic document is resolved into exam pool data |
-
2020
- 2020-01-13 CN CN202010032609.2A patent/CN111209728B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199871A (en) * | 2014-08-19 | 2014-12-10 | 南京富士通南大软件技术有限公司 | High-speed test question inputting method for intelligent teaching |
| CN106802937A (en) * | 2016-12-30 | 2017-06-06 | 江苏中育优教科技发展有限公司 | The conversion method and system of Word document |
| CN109614594A (en) * | 2018-11-27 | 2019-04-12 | 浙江万朋教育科技股份有限公司 | A method of topic document is resolved into exam pool data |
Non-Patent Citations (1)
| Title |
|---|
| 俞婷;符云清;: "基于词法分析和XML技术的多媒体试题批量导入研究" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832282A (en) * | 2020-07-16 | 2020-10-27 | 平安科技（深圳）有限公司 | External knowledge fused BERT model fine adjustment method and device and computer equipment |
| CN111737949A (en) * | 2020-07-22 | 2020-10-02 | 江西风向标教育科技有限公司 | Topic content extraction method and device, readable storage medium and computer equipment |
| CN111737949B (en) * | 2020-07-22 | 2021-07-06 | 江西风向标教育科技有限公司 | Topic content extraction method and device, readable storage medium and computer equipment |
| CN111680669A (en) * | 2020-08-12 | 2020-09-18 | 江西风向标教育科技有限公司 | Test question segmentation method and system and readable storage medium |
| CN112052646A (en) * | 2020-08-27 | 2020-12-08 | 安徽聚戎科技信息咨询有限公司 | Text data labeling method |
| CN112052646B (en) * | 2020-08-27 | 2024-03-29 | 安徽聚戎科技信息咨询有限公司 | Text data labeling method |
| CN113065316A (en) * | 2021-03-26 | 2021-07-02 | 洛阳圣昂通网络科技有限公司 | Method for dynamically converting formal thumbnail file into html (hypertext markup language) and inputting question bank, selecting questions from question bank and composing draft and generating thumbnail file |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111209728B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209728B (en) | Automatic labeling and inputting method for test questions | |
| CN109947836B (en) | English test paper structuring method and device | |
| CN110795543B (en) | Unstructured data extraction method, device and storage medium based on deep learning | |
| CN111144191B (en) | Font identification method, font identification device, electronic equipment and storage medium | |
| CN111274239B (en) | Test paper structuring processing method, device and equipment | |
| CN112115301B (en) | Video annotation method and system based on classroom notes | |
| CN109949637B (en) | Automatic answering method and device for objective questions | |
| CN110276069A (en) | A kind of Chinese braille mistake automatic testing method, system and storage medium | |
| CN113626573B (en) | Sales session objection and response extraction method and system | |
| CN114218379B (en) | Attribution method for question answering incapacity of intelligent question answering system | |
| CN115761753A (en) | Retrieval type knowledge prefix guide visual question-answering method fused with knowledge graph | |
| CN115034218A (en) | Chinese grammar error diagnosis method based on multi-stage training and editing level voting | |
| CN110674722B (en) | Test paper splitting method and system | |
| CN111680669A (en) | Test question segmentation method and system and readable storage medium | |
| CN111666374A (en) | Method for integrating additional knowledge information into deep language model | |
| CN113610068B (en) | Test question disassembling method, system, storage medium and equipment based on test paper image | |
| Oka et al. | Fully automated short answer scoring of the trial tests for common entrance examinations for Japanese university | |
| CN110765107B (en) | Question type identification method and system based on digital coding | |
| JP2017182646A (en) | Information processing device, program and information processing method | |
| CN110390032B (en) | Method and system for reading handwritten composition | |
| US20020138491A1 (en) | Learning automatic data extraction system | |
| Farasyn et al. | Challenges in tagging and parsing spoken dialects of Dutch | |
| CN113553416A (en) | Question answering method, system and readable storage medium based on semantic similarity | |
| CN113342953A (en) | Government affair question and answer method based on multi-model integration | |
| CN113569112A (en) | Tutoring strategy providing method, system, device and medium based on question |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |