Method and System for Determining Knowledge Points Based on Wrong Test Questions

Abstract

The present invention provides a method and system for determining knowledge points based on wrong test questions, belonging to the technical fields of data processing and educational informatization. The method includes: obtaining M groups of wrong test question pictures; extracting multiple semantic features and / or answering features of each group of wrong test question pictures; assigning knowledge point weight scores to each group of wrong test question pictures; distributing the knowledge point weight scores to each wrong test question corresponding to the group; and determining multiple target knowledge points. The system includes a wrong test question collection module, a feature extraction module, a similarity determination module, a score determination module, and a target knowledge point determination module. When determining the target knowledge points based on the wrong test questions, the technical solution of the present application takes into account both the situation of each test taker himself / herself and the overall situation of all test takers, and performs weighted scoring and ranking based on the individual situation and the overall situation, so as to complete the push of the target knowledge points for each individual, and can improve the efficiency of checking for deficiencies and making up for omissions of the individual and the whole.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing and educational informatization, and particularly relates to a method and system for determining knowledge points based on wrong questions, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device. Background Art

[0002] Wrong questions themselves are a kind of learning resource and are resources tailored for learners. Wrong question management is an important way of knowledge learning. It can not only help teachers improve the quality of teaching, but also help students conduct personalized learning, play a role in drawing inferences from one instance and getting rid of the sea of questions tactics, and is a measure that can help students improve learning efficiency and develop scientific learning methods. The consolidation practice of wrong questions, as the most important part of the wrong question management system, mainly aims to recommend a certain number of practice questions related to relevant knowledge for learners according to the needs of learners for practice and knowledge consolidation.

[0003] Chinese invention patent CN117648934B has proposed a method, device, equipment and medium for determining knowledge points based on wrong questions, which determines accurate wrong questions caused by mistakes from the dimensions of question keywords and question options, achieving the purpose of determining the knowledge points corresponding to the wrong questions not caused by mistakes as the knowledge points to be improved, and solving the technical problem of poor accuracy in determining the knowledge points to be improved in the related art.

[0004] In practical applications, it is found that most of the existing wrong question management solutions are for online (electronic) examination systems or online (electronic) practice question systems, and for the more common offline (paper) examination or practice question scenarios, the above solutions cannot be directly applied; in addition, the existing wrong question management solutions all focus on collecting existing wrong questions as a whole for analysis, and the recommended knowledge points are also for the overall testers, without considering the different situations of individual testers and giving targeted recommendations.

[0005] Therefore, according to the above actual problems, on the basis of the existing technology, the present application proposes a method and system for determining knowledge points based on wrong questions, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device that can be applied to more common offline (paper) examinations or question scenarios, taking into account the situation of each test taker himself and the overall situation of all test takers, and performing weighted scoring and ranking based on the individual situation and the overall situation. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a method and system for determining knowledge points based on wrong questions, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device. The method and system can be applied to more general offline (paper-based) examination or practice question scenarios, taking into account the individual situations of each test taker and the overall situation of all test takers, and performing weighted scoring and ranking based on individual and overall situations as follows:

[0007] In the first aspect of the present invention, a method for determining knowledge points based on wrong questions is proposed, and the method is executed based on a mobile terminal;

[0008] The method includes the following steps:

[0009] S100: Use M mobile terminals to collect images of the target question area of the test paper to obtain M groups of wrong question pictures, where the target questions are the questions answered incorrectly in the test paper; M > 1;

[0010] S200: Extract multiple semantic features and / or answering features of each group of wrong question pictures;

[0011] S300: Assign knowledge point weight scores to each group of wrong question pictures according to the similarity of different groups of wrong question pictures;

[0012] S400: Distribute the knowledge point weight score corresponding to each group of wrong question pictures to each wrong question corresponding to the group;

[0013] S500: Determine multiple target knowledge points based on the assigned weight scores of each wrong question, the number of wrong question pictures in each group, and a preset reference score.

[0014] The specific steps of S100 include:

[0015] Use M mobile terminals to collect images of the target question area of the test paper;

[0016] where the mobile terminal is for a test paper including questions answered incorrectly, and the mobile terminal obtains wrong question pictures ; ;

[0017] Count the number of wrong question pictures obtained by each of the M mobile terminals ;

[0018] Calculate the maximum value of the number of wrong question pictures obtained by all mobile terminals ;

[0019] For a mobile terminal Obtained One picture of wrong test questions ,

[0020] If , then expand the one picture of wrong test questions obtained by the mobile terminal Obtained One picture of wrong test questions To One picture of wrong test questions as the i-th group of pictures of wrong test questions .

[0021] The S200 extracts multiple semantic features and / or answering features of each group of pictures of wrong test questions, specifically including:

[0022] The semantic feature is the semantic word segmentation feature of the question stem of the test question with answering errors;

[0023] The answering feature is the answer recognition feature corresponding to the test question with answering errors.

[0024] The S300 assigns knowledge point weight scores to each group of pictures of wrong test questions according to the similarity of different groups of pictures of wrong test questions, specifically including:

[0025] Calculate the semantic feature similarity of the i-th group of pictures of wrong test questions And the j-th group of pictures of wrong test questions ; ; ;

[0026] Based on the semantic feature similarity Determine the knowledge point weight score of the i-th group of pictures of wrong test questions And the j-th group of pictures of wrong test questions ; The knowledge point weight score is positively correlated with the semantic feature similarity .

[0027] The S400 distributes the knowledge point weight score corresponding to each group of pictures of wrong test questions to each wrong test question corresponding to this group, specifically including:

[0028] Obtain the answer recognition feature of each wrong test question included in the i-th group of pictures of wrong test questions ;

[0029] Based on the answer recognition feature, determine the actual score of each wrong test question

[0030] Based on the actual score of each wrong test question, determine the knowledge point weight score actually assigned to this wrong test question

[0031] Among them, the knowledge point weight score actually assigned to each wrong test question is inversely related to the actual score of each wrong test question.

[0032] The step S500 of determining multiple target knowledge points specifically includes:

[0033] Based on the assigned weight score of each wrong test question, the number of wrong test question pictures in each group, and a preset reference score, determine M groups of target knowledge points, where the M groups of target knowledge points correspond to the M mobile terminals;

[0034] After the step S500, the method further includes:

[0035] S600: Push the M groups of knowledge points to the corresponding M mobile terminals.

[0036] To implement the method described in the first aspect, in the second aspect of the present invention, a knowledge point determination system based on wrong test questions is proposed. The system includes a wrong test question collection module, a feature extraction module, a similarity determination module, a score determination module, and a target knowledge point determination module.

[0037] The wrong test question collection module includes M mobile terminals. Through the M mobile terminals, image acquisition is performed on the target test question area of the test paper to obtain M groups of wrong test question pictures, where the target test questions are the test questions with wrong answers in the test paper; M>1;

[0038] The feature extraction module extracts multiple semantic features and / or answer features of each group of wrong test question pictures;

[0039] The score determination module includes a group weight score determination unit and a test question assignment score determination unit;

[0040] The group weight score determination unit assigns a knowledge point weight score to each group of wrong test question pictures according to the similarity of different groups of wrong test question pictures determined by the similarity determination module;

[0041] The test question assignment score determination unit distributes the knowledge point weight score corresponding to each group of wrong test question pictures to each wrong test question corresponding to the group;

[0042] The target knowledge point determination module determines multiple target knowledge points based on the assigned weight score of each wrong test question, the number of wrong test question pictures in each group, and a preset reference score;

[0043] Among them, the test question assignment score determination unit determines the knowledge point weight score actually assigned to each wrong test question based on the actual score of each wrong test question;

[0044] Among them, the knowledge point weight score actually assigned to each wrong test question is inversely correlated with the actual score of each wrong test question.

[0045] The semantic feature is the semantic word segmentation feature of the test question stem with a wrong answer;

[0046] The answering feature is the answer recognition feature corresponding to the test question with a wrong answer;

[0047] The group weight score determination unit assigns knowledge point weight scores to each group of wrong test question pictures according to the similarity of different groups of wrong test question pictures determined by the similarity determination module, specifically including:

[0048] The similarity determination module calculates the semantic feature similarity of the semantic word segmentation of different groups of wrong test question pictures;

[0049] The group weight score determination unit determines the knowledge point weight scores of different groups of wrong test question pictures based on the semantic feature similarity;

[0050] The knowledge point weight score is positively correlated with the semantic feature similarity.

[0051] The target knowledge point determination module determines M groups of target knowledge points based on the assigned weight score of each wrong test question, the number of each group of wrong test question pictures, and a preset benchmark score,

[0052] The M groups of target knowledge points correspond to the M mobile terminals;

[0053] The target knowledge point determination module further includes a knowledge point push unit;

[0054] The knowledge point push unit pushes the M groups of knowledge points to the corresponding M mobile terminals.

[0055] Some or all of the steps of the method for determining knowledge points based on wrong test questions described in the first aspect can be automatically implemented through various forms of electronic devices by computer program instructions; the computer program instructions can be stored in different forms of storage media and loaded into computer electronic devices for execution.

[0056] Therefore, in the third aspect of the present invention, there is also provided a computer-readable storage medium for storing computer instructions, which when the computer instructions run on an electronic device, cause the electronic device to execute a method for determining knowledge points based on wrong test questions as described in the first aspect.

[0057] In a fourth aspect of the present invention, an electronic device is further proposed. The electronic device includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes a method for determining knowledge points based on wrong test questions described in the foregoing first aspect.

[0058] In a fifth aspect of the present invention, a computer program product is further proposed. The product includes a computer program. When the computer program is executed, a method for determining knowledge points based on wrong test questions described in the foregoing first aspect.

[0059] When the technical solution of the present application determines the target knowledge points based on wrong test questions, it takes into account both the situation of each test taker himself and the overall situation of all test takers, and performs weighted scoring and ranking based on the individual situation and the overall situation, so as to push the target knowledge points for each individual, which can improve the efficiency of checking for deficiencies and making up for omissions of individuals and the whole.

[0060] The further advantages of the present invention will be further detailed in the specific embodiment part in combination with the accompanying drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It is a schematic diagram of the main process of a method for determining knowledge points based on wrong test questions according to an embodiment of the present invention

[0063] Figure 2 is Figure 1 A schematic diagram of the principle of expanding the wrong test question pictures obtained by each mobile terminal in the method

[0064] Figure 3 It is a schematic diagram of the main process of a method for determining knowledge points based on wrong test questions according to a more preferred embodiment of the present invention

[0065] Figure 4 It is a schematic diagram of the functional module composition of a system for determining knowledge points based on wrong test questions according to an embodiment of the present invention

[0066] Figure 5 It is a schematic diagram of a preferred embodiment of a system for determining knowledge points based on wrong test questions of the present invention DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments identical to the present application. On the contrary, they are merely examples of devices and methods that are the same as some aspects of the present application as detailed in the appended claims.

[0068] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the function of the module or unit.

[0069] Meanwhile, in the specific implementation of the present application, if it involves user-related data, when the embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0070] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0071] See Figure 1 , Figure 1 which shows a schematic diagram of the main process of a method for determining knowledge points based on wrong test questions according to an embodiment of the present invention. Figure 1 The method is executed based on multiple mobile terminals and specifically includes Figure 1 the steps S100 - S500 described above, and the specific implementation of each step is as follows:

[0072] S100: Use M mobile terminals to perform image acquisition on the target test question area of the test paper to obtain M groups of wrong test question pictures, where the target test question is a test question with wrong answers in the test paper; M > 1.

[0073] S200: Extract multiple semantic features and / or answering features of each group of wrong test question pictures.

[0074] S300: Assign knowledge point weight scores to each group of wrong test question pictures according to the similarity of different groups of wrong test question pictures.

[0075] S400: Distribute the knowledge point weight scores corresponding to each group of wrong test question pictures to each wrong test question corresponding to the group.

[0076] S500: Determine multiple target knowledge points based on the distributed weight scores of each wrong test question, the number of wrong test question pictures in each group, and a preset benchmark score.

[0077] Next, in combination with a specific scenario, the above steps will be further elaborated.

[0078] After a certain exam or practice assignment is over, after the instructor (also known as the teacher, administrator, etc.) grades all the test questions (also known as test papers, practice questions, etc.), the graded test questions are returned to the test takers (also known as students, practitioners, examinees, etc.). After each test taker receives the returned test paper, the test paper will show the score of each question, whether the answer to each question is wrong (marked by the instructor), and the original answer (submitted by the test taker).

[0079] Therefore, the scenario targeted by this embodiment can be applicable to more general offline (paper) exams or test question scenarios.

[0080] On this basis, execute step S100 to collect images of the target test question areas of the test paper through M mobile terminals, obtaining M groups of wrong test question pictures, where the target test questions are the test questions with wrong answers in the test paper; M > 1.

[0081] Specifically, after M test takers receive the returned test papers, they use their own or their parents' mobile terminals to collect images of the target test question areas of their own test papers, obtaining M groups of wrong test question pictures.

[0082] Although the test papers of each test taker are the same, generally, the test questions answered wrongly by each test taker will not be exactly the same. Therefore, step S100 enables each test taker to take pictures of each wrong question content by themselves, which is more in line with the actual situation.

[0083] For the convenience of description, assume that the M mobile terminals are labeled , corresponding to M test takers respectively, and each test taker has answered at least one question wrongly (excluding the case of full marks).

[0084] At this time, there are test questions answered wrongly in the test paper targeted by the mobile terminal , that is, the test paper includes wrongly answered test questions. The mobile terminal takes a separate photo of each test question area, obtaining wrong test question pictures.

[0085] Preferably, the mobile terminal will The pictures of wrong test questions are sorted according to the priority level from high to low to form a picture queue set ; ;

[0086] Preferably, the priority level is determined when the tested person takes pictures, that is, the tested person first takes pictures of the wrong areas that he / she thinks are the most important to obtain pictures , and then takes pictures of the less important wrong areas to obtain pictures , and so on, and finally obtains pictures of wrong test questions;

[0087] It should be noted that the priority level determined by this shooting method is determined by the shooter according to his / her actual situation, which is more in line with the actual teaching scenario, because each tested person has different understandings and masteries of the importance of different knowledge points, that is, this application fully considers the actual situation of individual tested persons, which is one of the initial improvement bases for proposing the technical solution of this application.

[0088] More importantly, the picture queue set formed by the above sorting method , determines that the method of element expansion for the picture queue set subsequently is more targeted, which will be further emphasized in the following step introduction, and this is one of the improvement points of this application.

[0089] Figure 2 is Figure 1 a schematic diagram of the principle for expanding the pictures of wrong test questions obtained by each mobile terminal in the said method.

[0090] First, count the number of pictures of wrong test questions obtained by each of the M mobile terminals ;

[0091] Continuing the above description, the mobile terminal will the pictures of wrong test questions be sorted according to the priority level from high to low to form a picture queue set , that is to say, the number of pictures of wrong test questions obtained by the mobile terminal is ;

[0092] Next, calculate the maximum value of the number of pictures of wrong test questions obtained by all mobile terminals ;

[0093] In order to highlight the importance of the wrong test question with the highest priority among the pictures of wrong test questions obtained by each mobile terminal, this embodiment is further improved as follows:

[0094] If , then the mobile terminal Obtained Zhang wrong test question pictures Expanded to Zhang wrong test question pictures as the i-th group of wrong test question pictures .

[0095] Specifically, the expansion method is: copy the elements in one by one from the beginning to and keep looping until contains elements.

[0096] That is , ;

[0097] Since each expansion starts from the element at the beginning (with the highest priority).

[0098] According to the statistical principle, the scores of most test takers are distributed in a certain same interval, that is, the number of wrong test question pictures obtained by most mobile terminals will not differ too much.

[0099] Therefore, the above loop copying process generally does not exceed 2 or 3 times. No matter how many times the copying process is repeated, as long as there is repetition, it will definitely copy to the element at the beginning (with the highest priority).

[0100] After the above expansion operation, each mobile terminal corresponds to an expanded wrong test question picture queue set , and each wrong test question picture queue set contains the same elements (both contain elements).

[0101] Arrange the elements of all wrong test question picture queue sets to obtain a matrix KM of M× as follows:

[0102]

[0103] To better describe the above process, Figure 2 shows a simple specific parameterization process.

[0104] In Figure 2 , taking M = 3 as an example (that is, assuming there are three test takers A, B, and C), test taker A submitted three wrong test question pictures A1, A2, A3 (arranged according to the importance of test taker A itself); test taker B submitted two wrong test question pictures B1, B2 (arranged according to the importance of test taker B itself); test taker C submitted two wrong test question pictures C1, C2 (arranged according to the importance of test taker C itself);

[0105] At this time, ; therefore, it is necessary to expand {B1, B2} and {C1, C2} to obtain:

[0106] (No need to expand)

[0107]

[0108] As a further explanation,

[0109] Suppose , then

[0110] At this time

[0111]

[0112] This process is the one mentioned above of copying the elements in one by one from the beginning to and continuously looping until contains elements.

[0113] Taking the first case (M = 3, ) as an example, the matrix KM is as follows at this time:

[0114] .

[0115] Based on obtaining the matrix KM, the subsequent process can be continued as follows:

[0116] S200: Extract multiple semantic features and / or answering features of each group of wrong test question pictures;

[0117] Specifically, the semantic feature is the semantic word segmentation feature of the test question stem with answering errors;

[0118] The answering feature is the answer recognition feature corresponding to the test question with answering errors.

[0119] It can be understood that the semantic word segmentation feature necessarily exists in the wrong test question picture, but the answer recognition feature corresponding to the test question with answering errors is optional because there may be a situation where a certain question is not answered (i.e., the answer recognition feature is blank).

[0120] When the answer recognition feature does not exist, it can be determined that the score of this question is 0 points based on the answer recognition feature.

[0121] This application takes into account answer recognition features mainly to correctly distinguish the relative scores of each question. In the actual scenario, the teacher may not give scores for each question. The teacher may only count the correct answers, so there is no need to score the wrong questions. However, the subsequent steps of this application involve using the actual scoring situation of each (wrong) question. Therefore, the answer feature is introduced here, which also reflects the completeness of the technical solution of this application.

[0122] It can be understood that recognizing the semantic segmentation features of the question stem and the answer recognition features corresponding to the questions with wrong answers both belong to the prior art, which is not the focus of the technical solution of this application. This application will not expand on this, and for details, reference can be made to the relevant prior art (such as the relevant literature mentioned in the background art).

[0123] On this basis, step S300 assigns knowledge point weight scores to each group of wrong question pictures according to the similarity of the wrong question pictures of different groups, specifically including:

[0124] Calculate the semantic feature similarity of the wrong question pictures of the i-th group and the wrong question pictures of the j-th group ; ; ;

[0125] Based on the semantic feature similarity determine the knowledge point weight score of the wrong question pictures of the i-th group and the wrong question pictures of the j-th group ; the knowledge point weight score is positively correlated with the semantic feature similarity .

[0126] It can be understood that the semantic feature similarity of the wrong question pictures of the i-th group and the wrong question pictures of the j-th group , and the semantic feature similarity of the wrong question pictures of the j-th group and the wrong question pictures of the i-th group are the same, that is ; then, the knowledge point weight score of the wrong question pictures of the i-th group and the wrong question pictures of the j-th group is also the same. This is the overall situation of all test takers considered in this application.

[0127] The semantic feature similarity is generally between (0, 1]. For simplicity of description, the value of the semantic feature similarity can be directly used as the knowledge point weight score. Of course, other scoring methods (such as the decimal system, the percentage system, etc.) can also be used, as long as it is ensured that the knowledge point weight score is related to the semantic feature similarity A positive correlation will do.

[0128] Next, the step S400 allocates the knowledge point weights corresponding to each group of wrong test question images to each wrong test question corresponding to the group, specifically including:

[0129] Get the i-th group of wrong test questions The answer identification features for each incorrect test question included;

[0130] determining an actual score for each incorrect test question based on the answer identification feature;

[0131] Determine the knowledge point weight score actually assigned to each wrong question based on the actual score of the wrong question;

[0132] Among them, the knowledge point weight score actually assigned to each wrong test question is inversely correlated with the actual score of each wrong test question.

[0133] The negative correlation here means that the higher the actual score of each wrong question (an wrong question refers to a question that has errors and does not get full marks, but it is possible to get partial marks), the lower the knowledge point weight score actually assigned to each wrong question will be. This is because the lower the score, the lower the degree of mastery of the knowledge point, and the higher the importance of the knowledge point, which is also in line with the actual situation of the individual.

[0134] For example, when a test question scores 0 points, the knowledge point weight score actually assigned to the wrong test question may be directly equal to the knowledge point weight score of the group to which it belongs (the highest value).

[0135] After the knowledge point weights assigned to each wrong test picture are obtained, the aforementioned matrix KM can be transformed into the knowledge point weight matrix SM as follows:

[0136] ,

[0137] in, For wrong test picture The weight of the knowledge point assigned.

[0138] It can be understood that identifying the semantic word segmentation features of the test question stem, the answer recognition features corresponding to the wrongly answered questions, the similarity comparison calculation between the features, etc. all belong to the existing technology, which is not the focus of the technical solution of this application. This application will not expand on this. For details, please refer to the relevant existing technology (such as the relevant literature mentioned in the background technology).

[0139] Next, step S400 is executed to determine a plurality of target knowledge points based on the assigned weight score of each incorrect test question, the number of each group of incorrect test question pictures, and a pre-set benchmark score.

[0140] The determination of multiple target knowledge points in step S500 specifically includes:

[0141] Based on the assigned weight scores of each wrong test question, the number of wrong test question pictures in each group, and a preset reference score, determine M groups of target knowledge points, where the M groups of target knowledge points correspond to the M mobile terminals.

[0142] Preferably, use the knowledge points corresponding to the wrong test questions with all assigned weight scores greater than the preset reference score and the number of wrong test question pictures exceeding the overall average as recommended knowledge points, and determine the target knowledge points based on the recommended knowledge points.

[0143] Specifically, determining the target knowledge points based on the recommended knowledge points can be to determine the same or similar test questions or practice questions based on the recommended knowledge points as the target knowledge points. This can be achieved through relevant technologies of text-based recommendation and data mining in the prior art, and this application does not specifically expand on this. For example, the following prior art can be referred to:

[0144] [1] Wang Wenquan. Design and implementation of personalized recommended practice algorithm in wrong question management system [J]. China Education Informatization, 2016(11): 67 - 70 + 92.

[0145] [2] Guo Hongxia. Research and development of middle school students' wrong question data mining system [D]. North China University of Technology, 2012.

[0146] Optionally, for the convenience of computer program implementation, the matrix SM can first have some duplicate elements removed, and then be subjected to principal component analysis and dimension reduction to an X - dimensional matrix, where X < min{M, }

[0147] Based on the X - dimensional matrix, obtain the assigned weight scores of each wrong test question and the number of wrong test question pictures in each group.

[0148] On this basis, Figure 3 This is the main process schematic diagram of the knowledge point determination method based on wrong test questions in a more preferred embodiment of the present invention.

[0149] Combined with Figure 3 and the foregoing embodiments, the knowledge point determination method based on wrong test questions in a more preferred embodiment of the present invention is implemented as follows:

[0150] A knowledge point determination method based on wrong test questions, the method is executed based on a mobile terminal, and is characterized in that the method includes the following steps:

[0151] S100: Image acquisition of the target question area of the test paper is performed by M mobile terminals to obtain M groups of wrong question pictures, where the target questions are the questions answered wrongly in the test paper; M>1;

[0152] S200: Extract multiple semantic features and / or answering features of each group of wrong question pictures;

[0153] S300: Assign knowledge point weight scores to each group of wrong question pictures according to the similarity of different groups of wrong question pictures;

[0154] S400: Distribute the knowledge point weight scores corresponding to each group of wrong question pictures to each wrong question corresponding to that group;

[0155] S500: Based on the assigned weight scores of each wrong question, the number of wrong question pictures in each group, and a preset reference score, determine M groups of target knowledge points, where the M groups of target knowledge points correspond to the M mobile terminals.

[0156] S600: Push the M groups of knowledge points to the corresponding M mobile terminals.

[0157] Based on the method embodiment, Figure 4 It is a schematic diagram of the functional module composition of a knowledge point determination system based on wrong questions according to an embodiment of the present invention.

[0158] The system includes a wrong question collection module, a feature extraction module, a similarity determination module, a score determination module, and a target knowledge point determination module.

[0159] Figure 5 It is a schematic diagram of a preferred embodiment of a knowledge point determination system based on wrong questions of the present invention

[0160] Among them, it is shown that the score determination module includes a group weight score determination unit and a question assignment score determination unit.

[0161] The wrong question collection module includes M mobile terminals. Image acquisition of the target question area of the test paper is performed by M mobile terminals to obtain M groups of wrong question pictures, where the target questions are the questions answered wrongly in the test paper; M>1;

[0162] The feature extraction module extracts multiple semantic features and / or answering features of each group of wrong question pictures;

[0163] The semantic features are obtained by a semantic feature extraction unit, and the answering features are obtained by an answering feature extraction unit;

[0164] The score determination module includes a group weight score determination unit and a question assignment score determination unit;

[0165] The grouping weight score determination unit assigns knowledge point weight scores to each group of wrong test question pictures according to the similarity of wrong test question pictures of different groups determined by the similarity determination module;

[0166] The test question assignment score determination unit distributes the knowledge point weight scores corresponding to each group of wrong test question pictures to each wrong test question corresponding to the group;

[0167] The target knowledge point determination module determines multiple target knowledge points based on the assigned weight scores of each wrong test question, the number of wrong test question pictures in each group, and a preset reference score;

[0168] Among them, the test question assignment score determination unit determines the knowledge point weight score actually assigned to this wrong test question based on the actual score of each wrong test question;

[0169] Among them, the knowledge point weight score actually assigned to each wrong test question is inversely related to the actual score of each wrong test question.

[0170] The semantic feature is the semantic word segmentation feature of the test question stem with wrong answers;

[0171] The answering feature is the answer recognition feature corresponding to the test question with wrong answers;

[0172] The grouping weight score determination unit assigns knowledge point weight scores to each group of wrong test question pictures according to the similarity of wrong test question pictures of different groups determined by the similarity determination module, specifically including:

[0173] The similarity determination module calculates the semantic feature similarity of the semantic word segmentation of wrong test question pictures of different groups;

[0174] The grouping weight score determination unit determines the knowledge point weight scores of wrong test question pictures of different groups based on the semantic feature similarity;

[0175] The knowledge point weight score is positively related to the semantic feature similarity.

[0176] The target knowledge point determination module determines M groups of target knowledge points based on the assigned weight scores of each wrong test question, the number of wrong test question pictures in each group, and a preset reference score,

[0177] The M groups of target knowledge points correspond to the M mobile terminals;

[0178] The target knowledge point determination module further includes a knowledge point push unit;

[0179] The knowledge point push unit pushes the M groups of knowledge points to the corresponding M mobile terminals.

[0180] It can be understood that after elaborating on the embodiments in the form of method processes in detail, there is no need to repeat the corresponding embodiments in the form of system functional architectures. However, those skilled in the art can directly and unambiguously determine that the embodiments in the form of system functional architectures also correspondingly include all the contents of the embodiments in the form of method processes. The same applies to the embodiments in the form of computer program code in pseudo-language form.

[0181] The present invention provides multiple embodiments, each of which can constitute an independent technical solution and may contribute to the prior art and solve corresponding technical problems. However, it should be noted that different embodiments can be combined with each other without violating logic; at the same time, each embodiment can solve at least one technical problem, but it is not required that each individual embodiment solve multiple or all technical problems.

[0182] For other technologies, principles, algorithms, or models not elaborated in detail in this application, reference can be made to the prior art.

[0183] In the above embodiments, the descriptions of each embodiment have their own emphases. For parts not elaborated in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0184] It should be noted that for the method for determining knowledge points based on wrong test questions in the embodiments of this application, those of ordinary skill in the art can understand that all or part of the process of implementing the method for determining knowledge points based on wrong test questions in the embodiments of this application can be controlled by a computer program to complete the relevant hardware. The computer program can be stored in a computer-readable storage medium, such as stored in the memory of an electronic device and executed by at least one processor in the electronic device. During the execution process, it can include the process of the embodiments of the method for determining knowledge points based on wrong test questions. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

[0185] In summary, according to the actual problems encountered in the educational scenario, on the basis of the existing technology, this application proposes a method and system for determining knowledge points based on wrong test questions that can be applied to more general offline (paper) exams or test question scenarios, while considering the situation of each test taker himself / herself and the overall situation of all test takers, and performing weighted scoring and ranking based on the individual situation and the overall situation, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device. When the technical solution of this application determines the target knowledge points based on wrong test questions, it considers the situation of each test taker himself / herself and the overall situation of all test takers, and performs weighted scoring and ranking based on the individual situation and the overall situation, so as to complete the push of the target knowledge points for each individual, and can improve the efficiency of filling in the gaps for individuals and the overall situation.

[0186] The method embodiments and systems of the present invention have been shown and described above. However, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for determining knowledge points based on incorrect test questions, the method being executed on a mobile terminal, characterized in that: The method comprises the following steps: S100: Through M mobile terminals to the target test area of ​​the test paper to collect images, to obtain M groups of wrong test pictures, the target test paper for the wrong answer test; M> 1; S200: extracting multiple semantic features and answer features of each group of wrong test questions; S3 00: According to the similarity of wrong test pictures in different groups, each group of wrong test pictures is assigned a knowledge point weight score; The weight score of the knowledge point is positively correlated with the similarity of the semantic features; S400: Allocating the knowledge point weight corresponding to each group of wrong test question images to each wrong test question corresponding to the group; The knowledge point weight actually assigned to each wrong test question is inversely correlated with the actual score of each wrong test question; S500: Determine a plurality of target knowledge points based on the assigned weight score of each incorrect test question, the number of each group of incorrect test question pictures, and a pre-set benchmark score.

2. A method for determining knowledge points based on incorrect test questions as claimed in claim 1, characterized in that: The step S500 of determining a plurality of target knowledge points specifically includes: Based on the assigned weight score of each wrong test question, the number of each group of wrong test question pictures and a preset benchmark score, M groups of target knowledge points are determined, and the M groups of target knowledge points correspond to the M mobile terminals; After step S500, the method further includes: S600: Pushing the M groups of target knowledge points to the corresponding M mobile terminals.

3. A method for determining knowledge points based on incorrect test questions as claimed in claim 1, characterized in that: The step S100 specifically includes: Through M mobile terminals Capturing images of the target test question area of ​​the test paper; Among them, mobile terminals The test papers include Wrong answer on the test question, mobile terminal get Wrong test picture ; ; Count the number of wrong test pictures obtained by each mobile terminal among M mobile terminals ; Calculate the maximum number of wrong test pictures obtained by all mobile terminals ; For mobile terminals Obtained Wrong test picture , like , then the mobile terminal Obtained Wrong test picture Expand to The wrong test pictures are taken as the i-th group of wrong test pictures .

4. A method for determining knowledge points based on incorrect test questions as claimed in claim 1, characterized in that: The step S200 extracts multiple semantic features and answer features of each group of wrong test question images, specifically including: The semantic feature is a semantic segmentation feature of the incorrectly answered test question stem; The answer feature is an answer identification feature corresponding to the test question with an incorrect answer.

5. A method for determining knowledge points based on incorrect test questions as claimed in claim 3, characterized in that: The step S300 assigns knowledge point weights to each group of wrong test question pictures according to the similarities of the wrong test question pictures of different groups, specifically including: Calculate the i-th group of wrong test questions and the jth group of wrong test pictures The semantic feature similarity of ; ; Based on semantic feature similarity Determine the i-th group of wrong test questions and the jth group of wrong test pictures Knowledge point weighting.

6. A method for determining knowledge points based on incorrect test questions as claimed in claim 3, characterized in that: The step S400 allocates the knowledge point weights corresponding to each group of wrong test question images to each wrong test question corresponding to the group, specifically including: Get the i-th group of wrong test pictures The answer identification features for each incorrect test question included; determining an actual score for each incorrect test question based on the answer identification feature; The actual weight of the knowledge point to which the incorrect question is actually assigned is determined based on the actual score of each incorrect question.

7. A knowledge point determination system based on incorrect test questions, the system comprising an incorrect test question collection module, a feature extraction module, a similarity determination module, a score determination module and a target knowledge point determination module; Features: The wrong test question collection module includes M mobile terminals, through the M mobile terminals to the target test question area of ​​the test paper to collect images, to obtain M groups of wrong test question pictures, the target test question is the test question in the test paper with the wrong answer; M> 1; The feature extraction module extracts multiple semantic features and answer features of each group of wrong test question images; The score determination module includes a group weight determination unit and a test question allocation determination unit; The group weight determination unit assigns a knowledge point weight to each group of wrong test question pictures according to the similarities of the wrong test question pictures of different groups determined by the similarity determination module; The weight score of the knowledge point is positively correlated with the similarity of the semantic features; The test question allocation score determination unit allocates the knowledge point weight score corresponding to each group of wrong test question pictures to each wrong test question corresponding to the group; The target knowledge point determination module determines a plurality of target knowledge points based on the assigned weight score of each wrong test question, the number of wrong test question pictures in each group, and a preset benchmark score; Wherein, the test question allocation score determination unit determines the knowledge point weight score actually allocated to each wrong test question based on the actual score of the wrong test question; Among them, the knowledge point weight score actually assigned to each wrong test question is inversely correlated with the actual score of each wrong test question.

8. A knowledge point determination system based on incorrect test questions as claimed in claim 7, characterized in that: The semantic feature is a semantic segmentation feature of the incorrectly answered test question stem; The answer feature is an answer recognition feature corresponding to a test question with an incorrect answer; The grouping weight determination unit assigns a knowledge point weight to each group of wrong test question pictures according to the similarities of different groups of wrong test question pictures determined by the similarity determination module, specifically including: The similarity determination module calculates the semantic feature similarity of the semantic segmentation of the wrong test pictures of different groups; The grouping weight determination unit determines the knowledge point weights of different groups of wrong test question images based on the semantic feature similarity.

9. A knowledge point determination system based on incorrect test questions as claimed in claim 7, characterized in that: The target knowledge point determination module determines M groups of target knowledge points based on the assigned weight score of each wrong test question, the number of each group of wrong test question pictures and the preset benchmark score. The M groups of target knowledge points correspond to the M mobile terminals; The target knowledge point determination module also includes a knowledge point pushing unit; The knowledge point pushing unit pushes the M groups of target knowledge points to the corresponding M mobile terminals.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it is used to implement a method for determining knowledge points based on incorrect test questions as described in any one of claims 1 to 6 above.

Images