CN107491536B - Test question checking method, test question checking device and electronic equipment - Google Patents
Test question checking method, test question checking device and electronic equipment Download PDFInfo
- Publication number
- CN107491536B CN107491536B CN201710725966.5A CN201710725966A CN107491536B CN 107491536 B CN107491536 B CN 107491536B CN 201710725966 A CN201710725966 A CN 201710725966A CN 107491536 B CN107491536 B CN 107491536B
- Authority
- CN
- China
- Prior art keywords
- test question
- test
- checked
- question
- attribute
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Abstract
The invention discloses a test question checking method, a test question checking device and electronic equipment, wherein the test question checking method comprises the following steps: acquiring test question contents and test question attributes of test questions to be checked; semantic matching is carried out on the test question content and test question keywords in a preset identification library, wherein each test question keyword has a corresponding test question attribute; if the target test question key words exist, detecting whether the test question attributes of the test questions to be verified are matched with the test question attributes corresponding to the target test question key words, wherein the target test question key words are the test question key words which are matched with the test question content semanteme successfully; and if the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords, storing the test questions to be verified to a test question library. The scheme of the invention saves the verification cost of the test question attribute and improves the verification efficiency of the test question attribute.
Description
Technical Field
The invention relates to the technical field of online question banks, in particular to a test question checking method, a test question checking device and electronic equipment.
Background
With the development of information and electronic technology, various online learning websites and application programs have been developed rapidly recently. The online question bank is a common learning product and is mainly used for online search learning and system intelligent paper output of students. Each topic in the online topic library has its topic attribute, which is mainly information of the subject, grade, etc. If the information is wrong, the students may receive wrong test questions in the process of using the online question bank, for example, if the students in lower grades take the test questions in higher grades, the students in lower grades may be in super class; if students in higher grades take test questions in lower grades, the current learning content of the students cannot be effectively trained due to the fact that the content of the test questions is too simple.
At present, the general practice in the industry is to manually label and check attributes of each test question by editing, generally, after one test question is obtained by editing, manually label the subject, grade and other test question attributes of the test question by means of understanding the contents of the test question by editing, and then perform proofreading by proofreaders. Because the process is completely the subjective operation of people, not only higher labor cost is needed, but also omission or errors are easy to occur, and the attribute labeling of the test questions is wrong.
Disclosure of Invention
In view of this, the invention provides a test question checking method, a test question checking device and an electronic device, aiming at saving the cost of checking the attribute of a test question and improving the efficiency of checking the attribute of the test question.
The first aspect of the present invention provides a test question checking method, including:
acquiring test question contents and test question attributes of test questions to be checked;
semantic matching is carried out on the test question content and test question keywords in a preset identification library, wherein each test question keyword has a corresponding test question attribute;
if the target test question key words exist, detecting whether the test question attributes of the test questions to be verified are matched with the test question attributes corresponding to the target test question key words, wherein the target test question key words are the test question key words which are matched with the test question content semanteme successfully;
and if the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords, storing the test questions to be verified to a test question library.
A second aspect of the present invention provides a test question checking apparatus, including:
the first information acquisition unit is used for acquiring the test question content and the test question attribute of the test question to be checked;
the semantic matching unit is used for performing semantic matching on the test question content acquired by the information acquisition unit and test question keywords in a preset identification library, wherein each test question keyword has a corresponding test question attribute;
the attribute matching unit is used for detecting whether the test question attribute of the test question to be checked, which is acquired by the information acquisition unit, is matched with the test question attribute corresponding to the target test question keyword when the semantic matching unit determines that the target test question keyword exists, wherein the target test question keyword is the test question keyword which is matched with the test question content in a semantic mode;
and the warehousing unit is used for storing the test questions to be verified to a test question library when the attribute matching unit determines that the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords.
A third aspect of the invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above when executing the computer program.
A fourth aspect of the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method as described above.
As can be seen from the above, in the present invention, firstly, the test question content and the test question attribute of the test question to be checked are obtained, and then the test question content is semantically matched with the test question keywords in the preset identification library, wherein each test question keyword has a corresponding test question attribute, and when the target test question keyword exists, whether the test question attribute is matched with the test question attribute corresponding to the target test question keyword, wherein the target test question keyword is a test question keyword which is semantically successfully matched with the test question content, and if the test question attribute is successfully matched with the test question attribute corresponding to the target test question keyword, the test question to be checked is stored in the test question library. The invention automatically checks whether the attribute of the test question is correct or not through the preset identification library, thereby reducing the labor cost for checking the attribute of the test question, improving the efficiency for checking the attribute of the test question and reducing the possibility that the test question in the test question library has wrong attribute of the test question.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation of a test question checking method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another implementation of the test question checking method according to the embodiment of the present invention;
FIG. 3 is a schematic diagram of a specific implementation flow of step S102 or step S202 in the embodiment shown in FIG. 1 or FIG. 2;
FIG. 4 is a schematic structural diagram of a test question checking apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device provided in an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Example one
Fig. 1 shows an implementation process of a test question checking method provided in an embodiment of the present invention, which is detailed as follows:
in step S101, test question content and test question attributes of a test question to be checked are obtained;
in the embodiment of the invention, the test question content and the test question attribute of the test question to be checked can be obtained firstly. The test questions to be verified may be obtained from a preset test question library to be verified, or the test questions to be verified sent by the user may be received, which is not limited herein. The test question content of the test question to be checked comprises but is not limited to a question stem part and an answer part; the test question attributes of the test questions to be tested include the subject to which the test questions belong and the grade to which the test questions belong, and may also include the test places to which the test questions belong, the information of the test question publisher, and the like, which is not limited herein.
In step S102, semantically matching the test question content with the test question keywords in a preset recognition library;
in the embodiment of the invention, the test question content can be semantically matched with the test question keywords in the preset identification library, wherein each test question keyword has a corresponding test question attribute. When the recognition library is initialized, a developer can arrange the common test question keywords and the corresponding test question attributes according to a textbook or a teaching material and manually input the common test question keywords and the corresponding test question attributes into the recognition library, and of course, the recognition library can also be initialized in other ways, which is not limited herein. For example, if a "quadratic function" is stored in the recognition library and a knowledge point of the "quadratic function" belonging to the first three mathematics subjects can be specified from the teaching material, the test question attribute corresponding to the "quadratic function" is "first three" and "math". Furthermore, when the test questions are made by the test person, in order to check the ability of the students to randomly change and disperse thinking, the knowledge points on the teaching materials are usually not directly made on the question stem, but are adjusted to a certain extent, so that the test questions are more diversified. Thus, it is likely that some subjects are not expressed in the same way as characters on the teaching materials, but the actual meanings of the subjects are still consistent with the teaching materials. In consideration of this, in step S102, the test question content may be semantically matched with the test question keywords in the preset recognition library to obtain a more accurate matching result.
In step S103, if there is a target test question keyword, detecting whether a test question attribute of the test question to be checked matches with a test question attribute corresponding to the target test question keyword;
in the embodiment of the invention, if a target test question keyword exists, whether the test question attribute of the test question to be detected is matched with the test question attribute corresponding to the target test question keyword is continuously detected, wherein the target test question keyword is the test question keyword which is matched with the test question content semantically successfully. That is, whether the test question attribute of the test question to be checked is consistent with the test question attribute corresponding to the target test question keyword is checked, and if so, the matching is considered to be successful; if not, the matching is considered unsuccessful.
In step S104, if the test question attributes of the test question to be verified are successfully matched with the test question attributes corresponding to the target test question keywords, storing the test question to be verified in a test question library;
in the embodiment of the present invention, if the test question attribute of the test question to be verified detected in step S103 is successfully matched with the test question attribute corresponding to the target entity keyword, the test question attribute of the test question to be verified is considered to be verified correctly, and the test question to be verified can be stored in the test question library for the student user to check.
Therefore, through the embodiment of the invention, the test question content of the test question to be verified is matched with the test question key words in the identification library, after the target test question key words are successfully obtained through matching, the test question attribute of the test question to be verified is matched with the test question attribute corresponding to the target test question key words, and after the target test question key words are successfully matched again, the test question to be verified is put in a warehouse, so that the verification efficiency of the test question attribute of the test question to be verified can be greatly improved through the two matching processes, manual operation is not needed in the two matching processes, and the labor cost is saved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two
Fig. 2 shows an implementation flow of another test question checking method provided by the embodiment of the present invention when a target test question keyword does not exist, or when the test question attribute of the test question to be checked is not successfully matched with the test question attribute corresponding to the target entity keyword:
in step S201, test question content and test question attributes of a test question to be checked are obtained;
in step S202, semantically matching the test question content with the test question keywords in a preset recognition library;
in the embodiment of the present invention, the implementation manners of the step S201 and the step S202 are the same as or similar to the implementation manners of the step S101 and the step S102, which are not repeated herein.
In step S203, if the target test question keyword does not exist, sending the test question to be checked to an audit client;
in the embodiment of the invention, when the test question key words matched with the test question contents of the test questions to be verified are not found in the preset identification library, namely when the identification library does not have the target test question key words corresponding to the test questions to be verified, the test questions to be verified cannot be automatically verified through the identification library, and the test questions to be verified can be sent to the verification client, wherein the verification client is the client on which the account number of a verifier is logged. And after the test questions to be checked are sent to the checking client, waiting for the auditors to manually check the test questions to be checked.
In step S204, if there is a target test question keyword, detecting whether the test question attribute of the test question to be checked matches the test question attribute corresponding to the target test question keyword;
in the embodiment of the invention, if a target test question keyword exists, whether the test question attribute of the test question to be detected is matched with the test question attribute corresponding to the target test question keyword is continuously detected, wherein the target test question keyword is the test question keyword which is matched with the test question content semantically successfully. That is, it is checked whether the test question attribute of the test question to be checked is consistent with the test question attribute corresponding to the target test question keyword, if so, the matching is considered to be successful, and the step S205 is entered; if not, the matching is considered to be unsuccessful, and the process proceeds to step S206.
In step S205, the test questions to be checked are stored in the question bank;
in the embodiment of the present invention, if the test question attribute of the test question to be verified detected in step S204 is successfully matched with the test question attribute corresponding to the target entity keyword, the test question attribute of the test question to be verified is considered to be verified correctly, and the test question to be verified can be stored in the test question library for the student user to check.
In step S206, the examination questions to be checked are sent to the auditing client;
in the embodiment of the present invention, if it is detected that the test question attribute of the target test question keyword obtained in step S204 is not successfully matched with the test question attribute of the test question to be checked, that is, if the test question attribute of the target test question keyword is not consistent with the test question attribute of the test question to be checked, the test question to be checked is sent to the checking client, so that the auditor can perform manual checking through the checking client. The auditing client in this step may be a client that logs in the same account of the auditor as the auditing client in step S203, or may be a client that logs in a different account of the auditor as the auditing client in step S203, and this is not limited here.
In step S207, if the checked test questions sent by the audit client are received, the checked test questions are saved in the test question library;
in the embodiment of the present invention, in step S203 or step S206, an operation of sending the test questions to be verified to the auditing client because the test questions to be verified cannot be verified by the recognition library occurs. Therefore, after the step S203 or the step S206, if the checked test questions sent by the checking client are received, the checked test questions are stored in the test question library, where the checked test questions are obtained by the checking client checking the test questions to be checked based on the input checking operation. In step S203 and step S206, the auditing client receives the test questions to be verified; after receiving the test questions to be verified at the verification client, the auditor can perform manual verification operation on the test questions to be verified: if the attribute of the test question to be verified is correct and can be matched with the content of the test question, determining that the test question to be verified is correct, and directly determining the test question to be verified as the verified test question; and if the attribute of the test question to be verified is incorrect, modifying the attribute of the test question to be verified so that the attribute of the test question to be verified can be matched with the content of the test question, and determining the test question to be verified after the attribute of the test question is modified as the verified test question. Of course, the auditor may also find that there is an error in the test question content during the verification process, and then the auditor may also modify the test question content of the test question to be verified, which is not limited herein. And then, the auditing client sends the checked test questions to enable the checked test questions to be saved in the test question bank.
Optionally, in order to enable the identification library to be updated in time, when receiving the checked test questions sent by the auditing client, the test question checking method further includes:
obtaining the test question content and the test question attribute of the checked test question;
and updating the identification library according to the test question content and the test question attribute of the checked test question.
When the checked test questions sent by the checking client are received, the check of the test questions to be checked through the checking client can be performed only when the identification library cannot accurately check the test questions to be checked, and therefore, the fact that the checked test questions sent by the checking client are received means that the identification library is insufficient, the test question key words containing the test questions to be checked may not be included, and the test question attributes of the target test question key words corresponding to the test questions to be checked may not be matched with the test questions to be checked. In order to update the identification library in time, after the checked test questions sent by the checking client are obtained, the test question contents and the test question attributes of the checked test questions can be continuously obtained, and the identification library is updated according to the test question contents and the test question attributes of the checked test questions. For example, if the test question content of the test question to be checked is developed around the quadratic function, but the recognition library does not have the test question keyword of the quadratic function, the test question to be checked is sent to the checking client for manual checking; assuming that the content of the test question is unchanged and still the test question is developed around the quadratic function in the checked test question sent by the auditing client, and the attribute of the test question is determined as 'first three' and 'math', the 'quadratic function' can be added into the recognition library as a key word of the test question, and simultaneously the attribute 'first three' and 'math' of the test question corresponding to the 'quadratic function' is added.
Therefore, through the embodiment of the invention, in the two matching processes, once the condition that the matching cannot be successfully performed occurs, the test questions to be verified are sent to the verification client side, and the verification personnel further performs verification, so that the automatic verification and the manual verification can be well combined, on one hand, the large-scale manual verification is avoided, and on the other hand, the verification accuracy is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
EXAMPLE III
On the basis of the two embodiments, fig. 3 shows a flowchart of the specific implementation of step S102 in the first embodiment and step S202 in the second embodiment, which is detailed as follows:
in step S301, extracting a keyword to be verified according to the test question content;
in the embodiment of the invention, after the test question content of the test question to be verified is obtained, the keyword to be verified can be extracted according to the test question content of the test question to be verified. Here, the number of the keywords to be verified is not limited, and thus, more than two keywords to be verified may be extracted. The keyword to be verified may be extracted from not only the question stem part of the test question to be verified, but also the answer part of the test question to be verified, and this is not limited here.
In step S302, semantic similarity between each keyword to be checked and the test question keyword is calculated respectively;
in the embodiment of the invention, the semantic similarity between each keyword to be verified and each test question keyword in the recognition library is respectively calculated according to the obtained keywords to be verified. The semantic distance between the keyword to be verified and the test question keyword may be calculated according to a classification system as the semantic similarity, or the semantic similarity between the keyword to be verified and the test question keyword may be calculated after statistics is performed by using a large-scale corpus, which is not limited herein.
In step S303, if the semantic similarity between the keyword to be verified and the test question keyword is not less than the preset semantic similarity threshold, determining the test question keyword whose semantic similarity with the keyword to be verified is not less than the preset semantic similarity threshold as a target test question keyword successfully matched with the keyword to be verified;
in the embodiment of the invention, when the calculated semantic similarity between the keyword to be checked and a test question keyword is not less than the preset semantic similarity threshold, the test question keyword can be determined as the target test question keyword. Once the target test question key words matched with any key word to be verified are found, the calculation of the semantic similarity of the key words can be finished, and the next target test question key words matched with the next key word to be verified are continuously searched.
Optionally, after the step S302, the test question checking method further includes:
calculating a keyword matching ratio according to the number of the target test question keywords and the number of all keywords to be checked of the test questions to be checked;
at this time, if the target test question keyword exists, detecting whether the test question attribute of the test question to be checked is matched with the test question attribute corresponding to the target test question keyword, which can be embodied as:
and if the keyword matching ratio exceeds a preset ratio threshold, detecting whether the test question attribute of the test question to be checked is matched with the test question attribute corresponding to the target test question keyword.
In the method, not all keywords to be checked of the test questions to be checked can find the target test question keywords matched with the keywords, and only a few keywords to be checked in the keywords to be checked of the test questions to be checked can match the target test question keywords. For example, 10 keywords to be checked are extracted from one test question to be checked, but only 2 keywords to be checked are matched with the target test question keywords, and obviously, this condition still needs to be sent to the checking client side to be checked by the auditor for manual checking. Thus, here, a ratio of the number of target test question keywords to the number of all the to-be-verified keywords of the test question to be verified may be calculated as a keyword matching ratio. Only when the keyword matching ratio exceeds a preset ratio threshold, the keyword matching is considered to be meaningful, and whether the test question attribute of the test question to be checked is matched with the test question attribute corresponding to the target test question keyword can be continuously detected; and if the matching ratio of the keywords does not exceed a preset ratio threshold, sending the test questions to be checked to an auditing client. Further, in the process of matching the test question attributes, if the test question attributes among different target test question keywords are found to be inconsistent, the test question attributes of the target test question keywords with the largest proportion are selected to be matched with the test question attributes of the test questions to be verified. For example, if the test question attributes of 7 target test question keywords are "first three" and "physical" and the test question attributes of the remaining 3 target test question keywords are "first three" and "mathematical" among the 10 target test question keywords of the test question to be checked, the test question attributes of the target test question keywords occupying the most proportion are considered; in this example, if the ratio is "first three" or "physical" most, then the "first three" or "physical" is matched with the test question attributes of the test questions to be checked, and it is detected whether the matching is successful, and of course, the ratio of the test question attributes of the target test question keywords having the most ratio needs to be greater than the preset attribute ratio threshold. And if the proportion of the test question attributes of the target entity key words with the largest proportion cannot reach the preset attribute proportion threshold, sending the test questions to be verified to the verification client, and manually verifying the test questions by a verifier. For example, if the test question attribute of 4 target test question keywords is "first three" and "physical" among 10 target test question keywords of the test question to be checked, the test question attribute of 3 target test question keywords is "first three" and "math", the test question attribute of the remaining 3 target test question keywords is "first three" and "chemical", and the preset attribute ratio threshold is 80%, the test question attribute of the target test question keyword with the most proportion is obtained as "first three" and "physical" through calculation, and the proportion condition is 40%, because the proportion does not exceed the preset attribute ratio threshold, at this time, the test question to be checked still needs to be sent to the auditing client.
Therefore, the method and the device further improve the accuracy of the matching result obtained in the two matching operations, and enable the verification process of the test question attribute to be more intelligent.
Example four
Fig. 4 is a block diagram showing a configuration of a test question checking apparatus according to an embodiment of the present invention, and only a part related to the embodiment of the present invention is shown for convenience of description. This examination question verifying unit 4 includes: a first information acquisition unit 41, a semantic matching unit 42, an attribute matching unit 43, and a warehousing unit 44.
The first information obtaining unit 41 is configured to obtain test question content and test question attributes of a test question to be checked;
a semantic matching unit 42, configured to perform semantic matching on the test question content acquired by the information acquiring unit 41 and the test question keywords in a preset identification library, where each test question keyword has a corresponding test question attribute;
an attribute matching unit 43, configured to, when the semantic matching unit 42 determines that a target test question keyword exists, detect whether the test question attribute of the test question to be checked, which is acquired by the information acquisition unit, matches the test question attribute corresponding to the target test question keyword, where the target test question keyword is a test question keyword that is successfully semantically matched with the test question content;
and a storage unit 44, configured to store the test question to be verified in the test question library when the attribute matching unit 43 determines that the test question attribute of the test question to be verified is successfully matched with the test question attribute corresponding to the target test question keyword.
Optionally, the test question verification apparatus 4 further includes:
a sending unit, configured to send the test question to be checked to an audit client when the target test question keyword does not exist, or when a test question attribute of the test question to be checked is not successfully matched with a test question attribute corresponding to the target test question keyword, where the audit client is a client on which an account of an auditor is logged;
the warehousing unit 44 is further configured to, if a checked test question sent by the checking client is received, store the checked test question in a test question warehouse, where the checked test question is obtained by checking the test question to be checked by the checking client based on an input checking operation.
Optionally, the test question verification apparatus 4 further includes:
a second information obtaining unit, configured to obtain test question content and test question attributes of the checked test questions;
and the updating unit is used for updating the identification library according to the test question content and the test question attribute of the checked test question acquired by the second information acquisition unit.
Optionally, the semantic matching unit 42 includes:
a keyword to be verified extraction subunit, configured to extract a keyword to be verified according to the test question content;
the semantic similarity calculation operator unit is used for calculating the semantic similarity between each keyword to be checked and the test question keywords respectively;
and the target test question keyword determining subunit is used for determining the test question keywords of which the semantic similarity with the keywords to be verified is not less than a preset semantic similarity threshold as the target test question keywords successfully matched with the keywords to be verified if the semantic similarity between the keywords to be verified and the test question keywords is not less than the preset semantic similarity threshold.
Optionally, the test question verification apparatus 4 further includes:
a keyword matching ratio calculating unit for calculating a keyword matching ratio according to the number of the target test question keywords and the number of all the keywords to be checked of the test questions to be checked
The attribute matching unit is specifically configured to detect whether the test question attribute of the test question to be checked matches the test question attribute corresponding to the target test question keyword if the keyword matching ratio exceeds a preset ratio threshold.
Therefore, through the embodiment of the invention, the test question checking device matches the test question content of the test question to be checked with the test question key words in the identification library, after the target test question key words are successfully obtained through matching, the test question attribute of the test question to be checked is matched with the test question attribute corresponding to the target test question key words, and after the target test question key words are successfully matched again, the test question to be checked is put in a warehouse. Furthermore, in the two matching processes, once the condition that the matching cannot be successfully carried out occurs, the test question checking device can also send the test questions to be checked to the checking client side, and further checking is carried out by a checking personnel, so that the automatic checking and the manual checking can be well combined, on one hand, the large-scale manual checking is avoided, and on the other hand, the checking accuracy is improved. Moreover, by calculating the semantic similarity between the keywords to be verified and the test question keywords, the accuracy of the matching result obtained in the process of matching twice is improved, and the verification process of the test question attributes is more intelligent.
EXAMPLE five
Fig. 5 is a schematic diagram of an electronic device provided in an embodiment of the present invention. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52, such as a test question checking program, stored in the memory 51 and executable on the processor 50. The processor 50 implements the steps of the various method embodiments described above, such as steps S101 to S104 shown in fig. 1, when executing the computer program 52. Alternatively, the processor 50 executes the computer program 52 to realize the functions of the modules/units in the device embodiments, such as the functions of the units 41 to 44 shown in fig. 4.
Illustratively, the computer program 52 may be divided into one or more units, which are stored in the memory 51 and executed by the processor 50 to implement the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 52 in the electronic device 5. For example, the computer program 52 may be divided into a first information obtaining unit, a semantic matching unit, an attribute matching unit, and a storage unit, and the specific functions of the units are as follows:
the first information acquisition unit is used for acquiring the test question content and the test question attribute of the test question to be checked;
the semantic matching unit is used for performing semantic matching on the test question content acquired by the information acquisition unit and test question keywords in a preset identification library, wherein each test question keyword has a corresponding test question attribute;
the attribute matching unit is used for detecting whether the test question attribute of the test question to be checked, which is acquired by the information acquisition unit, is matched with the test question attribute corresponding to the target test question keyword when the semantic matching unit determines that the target test question keyword exists, wherein the target test question keyword is the test question keyword which is matched with the test question content in a semantic mode;
and the storage unit is used for storing the test questions to be verified to the test question library when the attribute matching unit determines that the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords.
The electronic device 5 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The electronic device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that fig. 5 is merely an example of the electronic device 5, and does not constitute a limitation of the electronic device 5, and may include more or less components than those shown, or combine certain components, or different components, for example, the electronic device 5 may further include an input-output device, a network access device, a bus, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 51 may be an internal storage unit of the electronic device 5, such as a hard disk or a memory of the electronic device 5. The memory 51 may be an external storage device of the electronic device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 5. Further, the memory 51 may include both an internal storage unit and an external storage device of the electronic device 5. The memory 51 is used for storing the computer program and other programs and data required by the electronic device 5. The above-mentioned memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the apparatus may be divided into different functional units or modules to implement all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/electronic device are merely illustrative, and for example, the division of the above modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units described above, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the embodiments of the method when the computer program is executed by a processor. . The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable medium described above may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media excludes electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (9)
1. A test question checking method is characterized by comprising the following steps:
acquiring test question contents and test question attributes of test questions to be checked;
semantic matching is carried out on the key words to be checked of the test question content and the test question key words in a preset identification library, wherein each test question key word has a corresponding test question attribute;
if the target test question keywords exist, calculating a keyword matching ratio according to the number of the target test question keywords and the number of all keywords to be checked of the test questions to be checked;
if the keyword matching ratio exceeds a preset ratio threshold, detecting whether the test question attribute of the test question to be checked is matched with the test question attribute corresponding to the target test question keyword, wherein the target test question keyword is the test question keyword which is matched with the test question content semantically successfully; if the matching ratio of the keywords does not exceed a preset ratio threshold, sending the test questions to be checked to an auditing client, wherein the auditing client is a client logged with an account number of an auditor;
and if the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords, storing the test questions to be verified to a test question library.
2. The test question checking method according to claim 1, wherein the semantic matching is performed on the key words to be checked of the test question content and the test question key words in a preset recognition library, and then further comprising:
if the target test question key words do not exist, or if the test question attributes of the test questions to be verified are not successfully matched with the test question attributes corresponding to the target test question key words, sending the test questions to be verified to a verification client;
and if the checked test questions sent by the checking client are received, storing the checked test questions to a test question library, wherein the checked test questions are obtained after the checking client checks the test questions to be checked based on the input checking operation.
3. The test question checking method according to claim 2, wherein if the checked test question sent by the audit client is received, the test question checking method further comprises:
obtaining the test question content and the test question attribute of the checked test question;
and updating the identification library according to the test question content and the test question attribute of the checked test question.
4. The test question checking method according to any one of claims 1 to 3, wherein said semantically matching key words to be checked of said test question contents with the test question key words in a preset recognition library comprises:
extracting keywords to be checked according to the test question content;
respectively calculating the semantic similarity between each keyword to be checked and the test question keyword;
and if the semantic similarity between the keywords to be verified and the test question keywords is not less than a preset semantic similarity threshold, determining the test question keywords with the semantic similarity between the keywords to be verified and the test question keywords not less than the preset semantic similarity threshold as the target test question keywords successfully matched with the keywords to be verified.
5. A test question inspection apparatus, comprising:
the first information acquisition unit is used for acquiring the test question content and the test question attribute of the test question to be checked;
the semantic matching unit is used for performing semantic matching on the key words to be checked of the test question content acquired by the first information acquisition unit and the test question key words in a preset identification library, wherein each test question key word has a corresponding test question attribute;
the attribute matching unit is used for detecting whether the test question attribute of the test question to be checked, which is acquired by the first information acquisition unit, is matched with the test question attribute corresponding to the target test question keyword when the semantic matching unit determines that the target test question keyword exists, wherein the target test question keyword is the test question keyword which is matched with the test question content in a semantic mode;
the storage unit is used for storing the test questions to be verified to a test question library when the attribute matching unit determines that the test question attributes of the test questions to be verified are successfully matched with the test question attributes corresponding to the target test question keywords;
a keyword matching ratio calculating unit, configured to calculate a keyword matching ratio according to the number of the target test question keywords and the number of all to-be-verified keywords of the to-be-verified test questions;
the attribute matching unit is specifically configured to detect whether the test question attribute of the test question to be checked matches the test question attribute corresponding to the target test question keyword if the keyword matching ratio exceeds a preset ratio threshold; and if the matching ratio of the keywords does not exceed a preset ratio threshold, sending the test questions to be checked to an auditing client, wherein the auditing client is a client logged with an account number of an auditor.
6. The test question inspection apparatus of claim 5, further comprising:
the sending unit is used for sending the to-be-checked test questions to an auditing client when the target test question key words do not exist or the test question attributes of the to-be-checked test questions are not successfully matched with the test question attributes corresponding to the target test question key words, wherein the auditing client is a client logged with an account number of an auditor;
the warehousing unit is further used for storing the checked test questions to a test question library if the checked test questions sent by the checking client are received, wherein the checked test questions are obtained after the checking client checks the test questions to be checked based on the input checking operation.
7. The test question verifying apparatus of claim 6, wherein the test question verifying apparatus further comprises:
the second information acquisition unit is used for acquiring the test question content and the test question attribute of the checked test question;
and the updating unit is used for updating the identification library according to the test question content and the test question attribute of the checked test question acquired by the second information acquisition unit.
8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 4 are implemented when the computer program is executed by the processor.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710725966.5A CN107491536B (en) | 2017-08-22 | 2017-08-22 | Test question checking method, test question checking device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710725966.5A CN107491536B (en) | 2017-08-22 | 2017-08-22 | Test question checking method, test question checking device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107491536A CN107491536A (en) | 2017-12-19 |
| CN107491536B true CN107491536B (en) | 2020-07-07 |
Family
ID=60646526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710725966.5A Active CN107491536B (en) | 2017-08-22 | 2017-08-22 | Test question checking method, test question checking device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107491536B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182839A (en) * | 2018-01-26 | 2018-06-19 | 安徽爱学堂教育科技有限公司 | Test method and device based on problem database system |
| CN109446522B (en) * | 2018-10-22 | 2023-09-19 | 北京布局未来教育科技有限公司 | Automatic test question classification system and method |
| CN110135692A (en) * | 2019-04-12 | 2019-08-16 | 平安普惠企业管理有限公司 | Intelligence grading control method, device, computer equipment and storage medium |
| CN111627275B (en) * | 2020-04-23 | 2022-05-31 | 完美世界控股集团有限公司 | Processing method and device for language representation information test, storage medium and terminal |
| CN112507073A (en) * | 2020-12-07 | 2021-03-16 | 云南电网有限责任公司普洱供电局 | Content verification method of power distribution network operation file and related equipment |
| CN113361265A (en) * | 2021-07-08 | 2021-09-07 | 北京乐学帮网络技术有限公司 | Data quality inspection method, data quality inspection device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8514646B1 (en) * | 2012-05-09 | 2013-08-20 | Storart Technology Co. Ltd. | Method for improving performance when flash memory storage device works in wide temperature range |
| CN104346467A (en) * | 2014-11-14 | 2015-02-11 | 北京百度网讯科技有限公司 | Geographic information checking method, relevant device and corresponding database |
| CN104750754A (en) * | 2013-12-31 | 2015-07-01 | 北龙中网（北京）科技有限责任公司 | Website industry classification method and server |
| CN106095898A (en) * | 2016-06-07 | 2016-11-09 | 武汉斗鱼网络科技有限公司 | A kind of video title management method and device |
| CN106681850A (en) * | 2016-12-06 | 2017-05-17 | 北京中交兴路信息科技有限公司 | Vehicle model calibration method and device |
-
2017
- 2017-08-22 CN CN201710725966.5A patent/CN107491536B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8514646B1 (en) * | 2012-05-09 | 2013-08-20 | Storart Technology Co. Ltd. | Method for improving performance when flash memory storage device works in wide temperature range |
| CN104750754A (en) * | 2013-12-31 | 2015-07-01 | 北龙中网（北京）科技有限责任公司 | Website industry classification method and server |
| CN104346467A (en) * | 2014-11-14 | 2015-02-11 | 北京百度网讯科技有限公司 | Geographic information checking method, relevant device and corresponding database |
| CN106095898A (en) * | 2016-06-07 | 2016-11-09 | 武汉斗鱼网络科技有限公司 | A kind of video title management method and device |
| CN106681850A (en) * | 2016-12-06 | 2017-05-17 | 北京中交兴路信息科技有限公司 | Vehicle model calibration method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107491536A (en) | 2017-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491536B (en) | Test question checking method, test question checking device and electronic equipment | |
| CN107256650B (en) | Exercise pushing method and system and terminal equipment | |
| CN109829155B (en) | Keyword determination method, automatic scoring method, device, equipment and medium | |
| CN109271401B (en) | Topic searching and correcting method and device, electronic equipment and storage medium | |
| CN109815487B (en) | Text quality inspection method, electronic device, computer equipment and storage medium | |
| CN109800320B (en) | Image processing method, device and computer readable storage medium | |
| CN106940788B (en) | Intelligent scoring method and device, computer equipment and computer readable medium | |
| CN109492222B (en) | Intention identification method and device based on concept tree and computer equipment | |
| CN107423278B (en) | Evaluation element identification method, device and system | |
| CN107016132B (en) | Online question bank quality improving method and system and terminal equipment | |
| CN110569335B (en) | Triple verification method and device based on artificial intelligence and storage medium | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN111723870B (en) | Artificial intelligence-based data set acquisition method, apparatus, device and medium | |
| CN110263328B (en) | Discipline capability type labeling method and device, storage medium and terminal equipment | |
| CN113220875A (en) | Internet information classification method and system based on industry label and electronic equipment | |
| CN104036015A (en) | Electronic terminal question classification method and device, and solution provision method, system and device based on electronic terminal question classification device and method | |
| CN110929519B (en) | Entity attribute extraction method and device | |
| CN114049686A (en) | Signature recognition model training method and device and electronic equipment | |
| CN114492370A (en) | Webpage identification method and device, electronic equipment and medium | |
| CN110059180B (en) | Article author identity recognition and evaluation model training method and device and storage medium | |
| CN107071553A (en) | A kind of method, device and computer-readable recording medium for changing video speech | |
| CN110717029A (en) | Information processing method and system | |
| US11763589B1 (en) | Detection of blanks in documents | |
| CN113268977B (en) | Text error correction method and device based on language model, terminal equipment and medium | |
| CN115098596B (en) | Government affair related data carding method, government affair related data carding device, government affair related data carding equipment and readable storage medium |
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 |