A question bank construction method, system, storage medium and electronic device

Abstract

The present invention provides a method, system, storage medium and electronic device for building a question bank, belonging to the technical field of question bank building. The method obtains a current question bank, determines a theme in the current question bank, divides the theme into several question elements, and the question elements include fixed items and re-created variable items, wherein the theme at least includes a question and a correct answer; determines the question type of the theme, derives the re-created variable items in the theme, and after combining them with the fixed items, obtains a first target question with the same question type as the theme; determines the structure of the target question type, merges the re-created variable items or the derived re-created variable items with the structure of the target question type, and obtains a second target question different from the theme question type; adds the first target question and the second target question to the current question bank to complete the question bank construction. Specifically, the automatic question supplementation method can effectively solve the problem of time-consuming and labor-intensive manual question setting.

Description

Technical Field

[0001] The present invention belongs to the technical field of question bank construction, and in particular relates to a question bank construction method, system, storage medium and electronic equipment. Background Art

[0002] In order to build a question bank, it is usually necessary to continuously add test questions. Newly formulated test questions must be compared with the test questions in the question bank for similarity. If a certain degree of similarity is reached, they must be either modified or abandoned. This causes the maintenance cost to continue to rise after the question bank is built to a certain extent. In addition, used test questions must be frozen for a period of time or abandoned. If the question bank is used frequently, the question bank cannot keep up with the speed of replenishment, causing the question bank capacity to quickly bottom out, seriously endangering the quality of the question bank. Manually replenishing questions is time-consuming and labor-intensive. Summary of the invention

[0003] Based on this, an embodiment of the present invention provides a question bank construction method, system, storage medium and electronic device to solve the above problems.

[0004] A first aspect of an embodiment of the present invention provides a method for constructing a question bank, the method comprising:

[0005] Obtain the current question bank, determine the motif in the current question bank, divide the motif into several question elements, the question element includes fixed items and recreated variable items, wherein the motif includes at least a question and a correct answer. Specifically, if the motif is a question containing an expression, determine the target punctuation mark in the motif, and divide the motif according to the target punctuation mark, wherein the content before the first target punctuation mark and between adjacent punctuation marks is the question element;

[0006] If the motif is a question that does not contain an expression, identifying target punctuation marks and preset characters in the motif, wherein the target punctuation marks and preset characters in the motif are fixed items;

[0007] Obtaining text content between fixed items, and determining whether the text content is a phrase;

[0008] If it is determined that the text content is a phrase, the corresponding phrase is determined as the first re-created variable item;

[0009] If it is determined that the text content is not a phrase, the corresponding text content is determined as a second re-created variable item;

[0010] Analyzing the text content of the second re-created variable item, dividing the text content of the second re-created variable item into a plurality of phrases, and determining the corresponding phrases as the third re-created variable item;

[0011] Determine the question type of the motif, derive the recreated variable items in the motif, and combine them with the fixed items to obtain a first target question with the same question type as the motif;

[0012] Determine the structure of the target question type, and merge the recreated variable item or the derived recreated variable item with the structure of the target question type to obtain a second target question that is different from the mother question type;

[0013] Add the first target question and the second target question to the current question bank to complete the question bank construction.

[0014] Furthermore, after the step of analyzing the text content of the second re-created variable item, dividing the text content of the second re-created variable item into a plurality of phrases, and determining the corresponding phrases as the third re-created variable item, the following steps are included:

[0015] Determining the difficulty level of each first re-creation variable item and the third re-creation variable item according to the target element, wherein the target element is the knowledge point of the question;

[0016] The first re-creation variable item and the third re-creation variable item with a higher difficulty level are selected as the objects for subsequent target question generation.

[0017] Furthermore, the step of determining the difficulty level of each first re-creation variable item and the third re-creation variable item according to the target element includes:

[0018] Obtain each of the target elements in the theme, and determine whether the number of the target elements is unique;

[0019] If it is determined that the number of the target elements is unique, the first re-creation variable item and the third re-creation variable item corresponding to the unique target element are determined as the highest difficulty level;

[0020] If it is determined that the number of the target elements is not unique, determining the semantics of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif;

[0021] Respectively obtain the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements, and derive the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif in turn according to the semantics, and respectively count the number of derived results of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif;

[0022] According to the number of derived results, the corresponding first re-creation variable item and the third re-creation variable item are ranked in difficulty level, wherein the re-creation variable item with the least number of derived results is determined as the highest difficulty level.

[0023] Furthermore, the step of sorting the difficulty levels of the corresponding first re-creation variable items and the third re-creation variable items according to the number of derived results includes:

[0024] Determine whether the first re-created variable items and the third re-created variable items have the same number of derived results;

[0025] If it is determined that the first re-created variable items and the third re-created variable items have the same number of derivative results, the answer status of the first re-created variable items and the third re-created variable items of the main topic is obtained respectively, and the difficulty level of the corresponding re-created variable item is determined based on the answer status.

[0026] Furthermore, in the step of respectively obtaining the answer status of each first re-created variable item and the third re-created variable item of the theme and determining the difficulty level of the corresponding re-created variable item based on the answer status, the user's correct answer rate when asking questions for the corresponding first re-created variable item and the third re-created variable item in the theme of the same question type is counted, wherein the higher the correct answer rate, the lower the difficulty level of the re-created variable item.

[0027] Furthermore, the question types of the first target question and the second target question both include true-or-false questions, multiple-choice questions and fill-in-the-blank questions, wherein when the question type of the first target question is any one of true-or-false questions, multiple-choice questions and fill-in-the-blank questions, the question type of the second target question is the remaining question types.

[0028] A second aspect of an embodiment of the present invention provides a question bank construction system, which is used to implement a question bank construction method provided in the first aspect of an embodiment of the present invention, and the system includes:

[0029] A division module is used to obtain the current question bank, determine the motif in the current question bank, divide the motif into several question elements, and the question elements include fixed items and recreated variable items, wherein the motif includes at least a question and a correct answer;

[0030] A first target topic generating module is used to determine the topic type of the motif, derive the recreated variable items in the motif, and combine them with the fixed items to obtain a first target topic with the same topic type as the motif;

[0031] A second target question generation module is used to determine the structure of the target question type, and merge the re-created variable item or the derived re-created variable item with the structure of the target question type to obtain a second target question different from the mother question type;

[0032] An adding module is used to add the first target question and the second target question to the current question bank to complete the question bank construction.

[0033] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the question bank construction method provided in the first aspect.

[0034] A fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the program, the question bank construction method provided in the first aspect is implemented.

[0035] The question bank construction method, system, storage medium and electronic device provided in the embodiments of the present invention obtain the current question bank, determine the main theme in the current question bank, divide the main theme to obtain a number of question elements, the question elements include fixed items and re-created variable items, wherein the main theme at least includes a question and a correct answer; determine the question type of the main theme, derive the re-created variable items in the main theme, and after combining them with the fixed items, obtain a first target question with the same question type as the main theme; determine the structure of the target question type, merge the re-created variable items or the derived re-created variable items with the structure of the target question type, and obtain a second target question different from the main theme; add the first target question and the second target question to the current question bank to complete the question bank construction. Specifically, the automatic question supplement method can effectively solve the problem of time-consuming and labor-intensive manual question setting. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a method for constructing a question bank provided in the first embodiment of the present invention;

[0037] Figure 2 A structural block diagram of a question bank construction system provided in Embodiment 2 of the present invention;

[0038] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0039] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0040] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the description of the present invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0042] Embodiment 1

[0043] Please refer to Figure 1 , Figure 1 which shows a question bank construction method provided in Embodiment 1 of the present invention. The question bank construction method specifically includes steps S01 to S04.

[0044] Step S01: Obtain the current question bank, determine the master questions in the current question bank, divide the master questions to obtain a number of question elements. The question elements include fixed items and recreated variable items. Among them, the master questions include at least questions and correct answers.

[0045] Specifically, the fixed items refer to the fixed or unchanging content or parts in the master questions, and the recreated variable items refer to the variable content or parts in the master questions. It should be noted that when the master question is a question containing an expression, determine the target punctuation mark in the master question, and divide the master question according to the target punctuation mark. Among them, the content before the first target punctuation mark and between adjacent punctuation marks is the question element;

[0046] When the master question is a question without an expression, identify the target punctuation mark and the preset characters in the master question. Among them, the target punctuation mark and the preset characters in the master question are fixed items. Exemplarily, the target punctuation mark can be a comma, a semicolon or a period, etc., but not limited thereto; the preset characters can be "is", "is for", etc., but not limited thereto;

[0047] Obtain the text content between the fixed items and determine whether the text content is a phrase;

[0048] If it is determined that the text content is a phrase, then determine the corresponding phrase as the first recreated variable item;

[0049] If it is determined that the text content is not a phrase, then determine the corresponding text content as the second recreated variable item;

[0050] Analyze the text content of the second recreated variable item, split the text content of the second recreated variable item into several phrases, and determine the corresponding phrases as the third recreated variable items.

[0051] When the master question is a question containing an expression, for example, the master question is "Given an ellipse The left and right foci of (a>b>0) are F1 and F2 respectively. If there is a point P such that ∠F1PF2 is a right angle, then the range of the eccentricity of the ellipse is __________. ", is a fill-in-the-blank question. The topic is divided. Since the content before the first target punctuation mark and between adjacent punctuation marks is the topic element, then the topic elements in the topic are "the known ellipse (a>b>0) has left and right foci F1 and F2 respectively", "if there is a point P", "so that ∠F1PF2 is a right angle", and "the range of the eccentricity of the ellipse is __________". In this embodiment, fixed terms can be determined manually and variable terms can be created again, where the fixed terms can be "known ellipse (a>b>0)’s left and right foci are F1 and F2 respectively” and “the range of the eccentricity of the ellipse is __________”. The variable term that can be created can be a combination of “if there exists a point P” and “such that ∠F1PF2 is a right angle”.

[0052] When the theme is a question that does not contain an expression and is a judgment question, for example, the theme is "A is a scenic spot in B". The statement in this theme is correct. The theme is divided, and the obtained question elements are "A", "is", "the scenic spot in B" and ".". Since the target punctuation marks and preset characters in the theme are fixed items, the fixed items in the theme are "is" and ".". The text content between the fixed items is obtained, including the text content before the first fixed item, that is, "A" and "the scenic spot in B". Among them, "A" is a phrase, then "A" is determined as the first re-created variable item, and "the scenic spot in B" is not a phrase, then "the scenic spot in B" is determined as the second re-created variable item.

[0053] Further, the text content "the scenic spots within the territory of B" is analyzed to obtain the smallest unit of the phrase, including "B", "within the territory" and "scenic spots", which is determined as the third re-created variable item.

[0054] In addition, the difficulty level of each first re-creation variable item and third re-creation variable item is determined based on the target element, where the target element is the knowledge point of the question. It can be understood that the difficulty level refers to the difficulty of the question when a first re-creation variable item or a third re-creation variable item is used as the test point of the question. Among them, the knowledge point is also the test point, and the knowledge points of different subjects are different. For example, in history questions, the knowledge points are mainly time, place, people, etc., and in geography questions, the knowledge points are mainly knowledge points in physical geography and human geography. Specifically including:

[0055] Obtain each target element in the theme and determine whether the number of target elements is unique;

[0056] If it is determined that the number of target elements is unique, the first re-creation variable item and the third re-creation variable item corresponding to the unique target element are determined as the highest difficulty level;

[0057] If it is determined that the number of target elements is not unique, the semantics of the first re-creation variable item and the third re-creation variable item corresponding to each target element in the motif are determined;

[0058] The first re-creation variable item and the third re-creation variable item corresponding to each target element are obtained respectively, and the first re-creation variable item and the third re-creation variable item corresponding to each target element in the theme are derived in turn according to the semantics, and the number of derived results of the first re-creation variable item and the third re-creation variable item corresponding to each target element in the theme are counted respectively. It can be understood that taking the theme "A is a scenic spot in the territory of B" as an example, according to the semantics, "A", "B", "in the territory" and "scenic spot" are derived in turn, wherein semantic recognition can be performed using an existing convolutional neural network (CNN). Specifically, according to the semantics , derive the noun "A". For example, when "A" is a mountain, other mountains similar to the mountain can be derived. According to the semantics, derive the noun "scenic spot". For example, the derived results are "tourist resort", "sightseeing resort", "scenic area", etc. It should be noted that, in general, the derived results of "scenic spot" are more than the derived results of "A", because the word "scenic spot" has a larger space for development. Therefore, the difficulty level of the first re-created variable "A" is higher than that of the third re-created variable "scenic spot";

[0059] According to the number of derived results, the corresponding first re-creation variable item and the third re-creation variable item are ranked in difficulty level, wherein the re-creation variable item with the least number of derived results is determined as the highest difficulty level;

[0060] The first re-creation variable item and the third re-creation variable item with a higher difficulty level are selected as the objects for subsequent target question generation.

[0061] It should be noted that the step of sorting the difficulty levels of the corresponding first re-creation variable items and the third re-creation variable items according to the number of derived results includes:

[0062] Determine whether the first re-creation variable items and the third re-creation variable items have the same number of derived results. For example, the first re-creation variable item "A" and the third re-creation variable item "B" may have the same number of derived results under the semantics of the above-mentioned motif, wherein the number of derived results that differ within a certain range may also be regarded as the same number of derived results. In addition, the comparison of the number of derived results is performed in all re-creation variable items including the first re-creation variable item and the third re-creation variable item.

[0063] If it is determined that the first re-created variable items and the third re-created variable items have the same number of derivative results, the answer situations of the main topic regarding the first re-created variable items and the third re-created variable items are obtained respectively, and the difficulty level of the corresponding re-created variable items is determined according to the answer situations. Specifically, the user's correct answer rate is counted when questions are asked for the corresponding first re-created variable items and the third re-created variable items in the main topic of the same question type, wherein the higher the correct answer rate, the lower the difficulty level of the re-created variable item.

[0064] Step S02, determining the question type of the theme, deriving the recreated variable items in the theme, and combining them with the fixed items to obtain a first target question of the same question type as the theme.

[0065] In this embodiment, the question types of the first target question and the second target question include true-or-false questions, multiple-choice questions and fill-in-the-blank questions. Among them, when the question type of the first target question is any one of true-or-false questions, multiple-choice questions and fill-in-the-blank questions, the question type of the second target question is the remaining question types. It can be understood that when the first target question is a true-or-false question, the second target question can be a multiple-choice question or a fill-in-the-blank question.

[0066] For example, continue with the “known ellipse (a>b>0) has left and right foci F1 and F2 respectively. If there is a point P such that ∠F1PF2 is a right angle, then the range of the eccentricity of the ellipse is __________. "For example, create a variable term of "If there is a point P such that ∠F1PF2 is a right angle", and the derived result can be "If there is a point P such that ", the derived result is a synonymous expression for the re-creation of the variable term, and the derived result can also be "if there exists a point P such that ", the result of this derivation is that the difficulty of creating variable items increases, and the knowledge of triangles is increased. The overall type of fill-in-the-blank questions remains unchanged, but other types of questions can also be added.

[0067] In addition, continuing with the judgment question "A is a scenic spot in B" as an example, for example, when "A" is a mountain, other mountains similar to the mountain can be derived, such as "A1", "A2", etc., which are combined with the fixed items "is" and ".", we can get the first target questions of "A1 is a scenic spot in B" and "A2 is a scenic spot in B", which are both judgment questions.

[0068] Step S03, determining the structure of the target question type, integrating the recreated variable items or the derived recreated variable items with the structure of the target question type, and obtaining a second target question that is different from the mother question type.

[0069] It should be noted that since the theme in the above example is a true-or-false question, the second target question is a multiple-choice question and a fill-in-the-blank question. The structure of the multiple-choice question and the fill-in-the-blank question can be set manually, or the subject-predicate-object structure of the theme can be adjusted according to semantic analysis to form the corresponding second target question.

[0070] Specifically, the structure of the multiple-choice question can be "Those belonging to B include: A", where B refers to the second re-created variable item "the scenic spots within the territory of B", and A is the option of the multiple-choice question, which can be "A" and its derivative results; the structure of the fill-in-the-blank question can be "A is a scenic spot within the territory of C.", where C can be "B" and its derivative results, so as to complete the conversion of the question type.

[0071] Step S04, adding the first target question and the second target question to the current question bank to complete the question bank construction.

[0072] In summary, the question bank construction method in the above-mentioned embodiment of the present invention obtains the current question bank, determines the theme in the current question bank, divides the theme into several question elements, and the question elements include fixed items and re-created variable items, wherein the theme at least includes a question and a correct answer; determines the question type of the theme, derives the re-created variable items in the theme, and obtains a first target question of the same question type as the theme after combining them with the fixed items; determines the structure of the target question type, merges the re-created variable items or the derived re-created variable items with the structure of the target question type, and obtains a second target question that is different from the theme question type; adds the first target question and the second target question to the current question bank to complete the question bank construction. Specifically, the automatic question supplementation method can effectively solve the problem of time-consuming and labor-intensive manual question setting.

[0073] Embodiment 2

[0074] See also Figure 2 , Figure 2 2 is a structural block diagram of a question bank construction system 200 provided in the second embodiment of the present invention. The question bank construction system 200 specifically includes: a division module 21, a first target question generation module 22, a second target question generation module 23 and an adding module 24, wherein:

[0075] The division module 21 is used to obtain the current question bank, determine the motif in the current question bank, divide the motif into a plurality of question elements, the question elements include fixed items and recreated variable items, wherein the motif includes at least a question and a correct answer;

[0076] A first target topic generating module 22 is used to determine the topic type of the motif, derive the recreated variable items in the motif, and combine them with the fixed items to obtain a first target topic with the same topic type as the motif;

[0077] A second target topic generating module 23 is used to determine the structure of the target topic type, and merge the re-created variable items or the derived re-created variable items with the structure of the target topic type to obtain a second target topic different from the mother topic type;

[0078] Adding module 24 is used to add the first target question and the second target question to the current question bank to complete the question bank construction. The question types of the first target question and the second target question include true-or-false questions, multiple-choice questions and fill-in-the-blank questions. Among them, when the question type of the first target question is any one of true-or-false questions, multiple-choice questions and fill-in-the-blank questions, the question type of the second target question is the remaining question types.

[0079] Further, in some optional embodiments of the present invention, the division module 21 includes:

[0080] A first division unit is used for determining target punctuation marks in the motif when the motif is a question containing an expression, and dividing the motif according to the target punctuation marks, wherein the content before the first target punctuation mark and between adjacent punctuation marks is the topic element;

[0081] a recognition unit, for recognizing target punctuation marks and preset characters in the motif if the motif is a question without an expression, wherein the target punctuation marks and preset characters in the motif are fixed items;

[0082] A first judging unit, configured to obtain text content between fixed items and judge whether the text content is a phrase;

[0083] A first determination unit, configured to determine the corresponding phrase as a first re-created variable item if the text content is determined to be a phrase;

[0084] a second determining unit, configured to determine the corresponding text content as a second re-created variable item if it is determined that the text content is not a phrase;

[0085] The third determination unit is used to analyze the text content of the second re-creation variable item, split the text content of the second re-creation variable item into a plurality of phrases, and determine the corresponding phrases as the third re-creation variable item.

[0086] Furthermore, in some optional embodiments of the present invention, the division module 21 further includes:

[0087] a fourth determination unit, configured to determine the difficulty level of each of the first re-creation variable item and the third re-creation variable item according to a target element, wherein the target element is a knowledge point of the question;

[0088] The selection unit is used to select the first re-creation variable item and the third re-creation variable item with a high difficulty level as an object for subsequent target question generation.

[0089] Further, in some optional embodiments of the present invention, the fourth determining unit includes:

[0090] A first judging subunit is used to obtain each of the target elements in the motif and judge whether the number of the target elements is unique;

[0091] A first determining subunit is configured to determine the first re-creation variable item and the third re-creation variable item corresponding to the unique target element as the highest difficulty level if it is determined that the number of the target element is unique;

[0092] A second determining subunit is configured to determine the semantics of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif if it is determined that the number of the target elements is not unique;

[0093] a derivation subunit, for respectively obtaining the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements, and deriving the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif in turn according to the semantics, and respectively counting the number of derived results of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif;

[0094] A sorting subunit is used to sort the difficulty levels of the corresponding first re-creation variable items and the third re-creation variable items according to the number of derived results, wherein the variable item with the least number of derived results is determined as the highest difficulty level, and specifically, to determine whether the first re-creation variable items and the third re-creation variable items have the same number of derived results;

[0095] If it is determined that the first re-created variable items and the third re-created variable items have the same number of derivative results, the answer situations of the first re-created variable items and the third re-created variable items of the main topic are obtained respectively, and the difficulty level of the corresponding re-created variable items is determined according to the answer situations, wherein the user's correct answer rate is counted when questions are asked for the corresponding first re-created variable items and the third re-created variable items in the main topic of the same question type, wherein the higher the correct answer rate, the lower the difficulty level of the re-created variable item.

[0096] Embodiment 3

[0097] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the question bank construction method as described above is implemented.

[0098] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0099] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as a hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of an electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 can also include both an internal storage unit of the electronic device and an external storage device. The memory 20 can not only be used to store application software and various types of data of the electronic device, but also can be used to temporarily store data that has been output or is to be output.

[0100] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0101] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for constructing a question bank as described above is implemented.

[0102] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0103] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0105] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0106] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for building a question bank, characterized in that: The method comprises: Obtain the current question bank, determine the motif in the current question bank, divide the motif into several question elements, the question element includes fixed items and recreated variable items, wherein the motif includes at least a question and a correct answer. Specifically, if the motif is a question containing an expression, determine the target punctuation mark in the motif, and divide the motif according to the target punctuation mark, wherein the content before the first target punctuation mark and between adjacent punctuation marks is the question element; If the motif is a question that does not contain an expression, identifying target punctuation marks and preset characters in the motif, wherein the target punctuation marks and preset characters in the motif are fixed items; Obtaining text content between fixed items, and determining whether the text content is a phrase; If it is determined that the text content is a phrase, the corresponding phrase is determined as the first re-created variable item; If it is determined that the text content is not a phrase, the corresponding text content is determined as a second re-created variable item; Analyzing the text content of the second re-created variable item, dividing the text content of the second re-created variable item into a plurality of phrases, and determining the corresponding phrases as the third re-created variable item; Determine the question type of the motif, derive one or more of the first re-creation variable item, the second re-creation variable item, and the third re-creation variable item in the motif, and combine them with the fixed item to obtain a first target question with the same question type as the motif; Determine the structure of the target question type, and integrate one or more of the first re-created variable item, the second re-created variable item, the third re-created variable item, the derived first re-created variable item, the derived second re-created variable item, and the derived third re-created variable item with the structure of the target question type to obtain a second target question that is different from the mother question type; Add the first target question and the second target question to the current question bank to complete the question bank construction.

2. The question bank construction method according to claim 1, characterized in that: The step of analyzing the text content of the second re-created variable item, dividing the text content of the second re-created variable item into a plurality of phrases, and determining the corresponding phrases as the third re-created variable item comprises: Determining the difficulty level of each first re-creation variable item and the third re-creation variable item according to the target element, wherein the target element is the knowledge point of the question; The first re-creation variable item and the third re-creation variable item with a higher difficulty level are selected as the objects for subsequent target question generation.

3. The question bank construction method according to claim 2, characterized in that: The step of determining the difficulty level of each first re-creation variable item and the third re-creation variable item according to the target element comprises: Obtain each of the target elements in the theme, and determine whether the number of the target elements is unique; If it is determined that the number of the target elements is unique, the first re-creation variable item and the third re-creation variable item corresponding to the unique target element are determined as the highest difficulty level; If it is determined that the number of the target elements is not unique, determining the semantics of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif; Respectively obtain the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements, and derive the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif in turn according to the semantics, and respectively count the number of derived results of the first re-creation variable item and the third re-creation variable item corresponding to each of the target elements in the motif; According to the number of derived results, the corresponding first re-creation variable item and the third re-creation variable item are ranked in difficulty level, wherein the re-creation variable item with the least number of derived results is determined as the highest difficulty level.

4. The method for constructing a question bank according to claim 3, characterized in that: The step of sorting the difficulty levels of the corresponding first re-creation variable items and the third re-creation variable items according to the number of the derived results includes: Determine whether the first re-created variable items and the third re-created variable items have the same number of derived results; If it is determined that the first re-created variable items and the third re-created variable items have the same number of derivative results, the answer status of the first re-created variable items and the third re-created variable items of the main topic is obtained respectively, and the difficulty level of the corresponding re-created variable item is determined based on the answer status.

5. The question bank construction method according to claim 4, characterized in that: In the steps of respectively obtaining the answer status of each first re-created variable item and the third re-created variable item of the theme, and determining the difficulty level of the corresponding re-created variable item based on the answer status, the user's correct answer rate when asking questions for the corresponding first re-created variable item and the third re-created variable item in the theme of the same question type is counted, wherein the higher the correct answer rate, the lower the difficulty level of the re-created variable item.

6. The method for constructing a question bank according to claim 5, characterized in that: The question types of the first target question and the second target question both include true-or-false questions, multiple-choice questions and fill-in-the-blank questions, wherein when the question type of the first target question is any one of true-or-false questions, multiple-choice questions and fill-in-the-blank questions, the question type of the second target question is the remaining question types.

7. A question bank construction system, characterized in that: Used to implement the question bank construction method according to any one of claims 1 to 6, the system comprises: A division module is used to obtain the current question bank, determine the motif in the current question bank, divide the motif into several question elements, and the question elements include fixed items and recreated variable items, wherein the motif includes at least a question and a correct answer; A first target topic generating module is used to determine the topic type of the motif, derive one or more of the first re-creation variable item, the second re-creation variable item and the third re-creation variable item in the motif, and combine them with the fixed item to obtain a first target topic with the same topic type as the motif; A second target question generation module is used to determine the structure of the target question type, and merge one or more of the first re-creation variable item, the second re-creation variable item, the third re-creation variable item, the derived first re-creation variable item, the derived second re-creation variable item, and the derived third re-creation variable item with the structure of the target question type to obtain a second target question different from the mother question type; An adding module is used to add the first target question and the second target question to the current question bank to complete the question bank construction.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for building a question bank as described in any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and running on the processor. When the processor executes the program, the method for building a question bank as claimed in any one of claims 1 to 6 is implemented.

Images