Test question recommendation method and device, equipment and medium

Abstract

The invention relates to a test question recommendation method and device, equipment and a medium, and relates to the technical field of computers, the method comprises the following steps: obtaining historical answer data of a target user, the historical answer data comprising question information and answer information; inputting the question information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the question information; determining a user portrait of the target user according to the answer information, wherein the user portrait comprises a learning situation report; determining a knowledge point graph according to the knowledge points and the learning condition report; and determining recommended test questions according to the knowledge point graph. The knowledge point graph is specifically formed for the user, a clear direction and basis are provided for test question generation, it is ensured that the recommended test questions can effectively help students consolidate knowledge, and the learning effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a test question recommendation method, device, equipment and medium. Background Art

[0002] With the rapid development of artificial intelligence technology, automated test question recommendation has become a new research direction. However, the existing test question recommendation effect is not ideal. First, the recommended test questions cannot fully meet the students' learning needs and knowledge points. Second, the ability to process large amounts of data and generate recommended test questions in real time still needs to be improved. Third, there are also deficiencies in question difficulty control, question type diversity, and comprehensive coverage of knowledge points, making it difficult to fully meet the needs of personalized teaching. Summary of the invention

[0003] The present invention provides a test question recommendation method to solve the problem that the recommended test questions cannot fully meet the learning needs and knowledge points of students.

[0004] In a first aspect, the present invention provides a method for recommending test questions, the method comprising: Obtaining historical answer data of the target user, wherein the historical answer data includes question information and answer information; Inputting the topic information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the topic information; Determine a user profile of the target user according to the answer information, wherein the user profile includes a learning status report; Determine a knowledge point map according to the knowledge points and the learning report; Determine recommended test questions based on the knowledge point map.

[0005] In a second aspect, the present invention provides a test question recommendation device, comprising: An acquisition unit, used to acquire historical answer data of a target user, wherein the historical answer data includes question information and answer information; A first determining unit, configured to input the topic information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the topic information; A second determining unit, configured to determine a user profile of the target user according to the answer information, wherein the user profile includes a learning status report; A third determining unit, configured to determine a knowledge point map according to the knowledge point and the learning status report; The fourth determining unit is used to determine recommended test questions according to the knowledge point map.

[0006] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the test question recommendation method described in any embodiment of the first aspect when executing the program stored in the memory.

[0007] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the test question recommendation method as described in any embodiment of the first aspect are implemented.

[0008] The above technical solution provided by the embodiment of the present invention has the following advantages compared with the prior art: Use natural language processing (NLP) technology to extract relevant knowledge points from the collected data. Through semantic analysis and information extraction, the system classifies and organizes these knowledge points to form a structured knowledge point map. The knowledge point map not only includes the relationship between knowledge points, but also reflects the hierarchy and importance of knowledge points, providing a clear direction and basis for question generation, ensuring that the recommended questions can effectively help students consolidate knowledge and improve learning outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0011] Figure 1 A flowchart of a test question recommendation method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a sub-flow chart of a test question recommendation method provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-flow chart of a test question recommendation method provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a test question recommendation device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] Example 1 Figure 1 The present invention provides a flowchart of a method for recommending test questions. Figure 1 , the test question recommendation method includes the following steps S101-S105.

[0014] S101, obtaining historical answer data of a target user, wherein the historical answer data includes question information and answer information.

[0015] In the specific implementation, students' answer data is fully recorded through various data collection methods, including online answering system, data import tools, scanners, etc. The data of each answer will be recorded in detail, and the answer information includes whether it is correct or not, answering time, thinking path, etc. Question information includes title, options and analysis.

[0016] S102, inputting the question information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the question information.

[0017] In the specific implementation, the natural language analysis model is a model trained based on natural language processing (NLP) technology, which is used to extract relevant knowledge points from the collected data, and extract the knowledge points contained in the question information through semantic analysis and information extraction. For example: the question information contains "Answer: A. In the same plane, two non-intersecting straight lines must be parallel lines, so A is wrong and does not meet the requirements of the question; B. The length of the perpendicular line segment from a point to a straight line is the distance from the point to the straight line, so B is wrong and does not meet the requirements of the question; C. The line segment between two points is the shortest, so C is correct and meets the requirements of the question; D. In the same plane, there is only one straight line passing through a point and is perpendicular to the known straight line, so D is wrong and does not meet the requirements of the question; so choose: C." The keywords of the question information extracted by the natural language analysis model include: "parallel lines", "line segments", and "distance", and the knowledge points obtained by analysis are "determination of parallel lines", "properties of line segments", "distance between two points", and "distance from a point to a straight line".

[0018] In one embodiment, the above step S102 includes the steps of: obtaining the content of the question sample as input data; inputting the input data into a preset neural network model; determining whether the output result of the neural network model is the same as the knowledge point of the question sample; if the output result of the neural network model is different from the knowledge point of the question sample, using the output result of the neural network model as new input data, and returning to the step of inputting the input data into the neural network model.

[0019] In the specific implementation, the sample questions include content and target knowledge points. The content includes text and pictures, which are data that can be recognized by the neural network model, and the target knowledge points are the output results of the neural network model. Through the learning technology of the neural network model, the various attributes of the test questions are automatically identified and annotated, and the corresponding knowledge point labels are marked for the test questions, thereby improving the efficiency and accuracy of labeling.

[0020] S103, determining a user portrait of the target user according to the answer information, wherein the user portrait includes a learning status report.

[0021] In the specific implementation, the answer information includes whether it is correct or not, the answer time, the thinking path, etc. The answer information is processed and analyzed by a specific algorithm to generate a user portrait of the student. The user portrait includes not only the basic information and personal information of the target user, but also the learning report. In this embodiment, the learning report is used to evaluate the user habits of the target user and the target user's mastery of the knowledge points. For example, the number of errors of user A's knowledge point "perfect square formula" is 21, and the error rate is 20.2%. The number of errors of the knowledge point "mixed operations of integers-simplified evaluation" is 25, and the error rate is 24%. In one embodiment, by comparing the error rates between knowledge points, it can be determined that user A's mastery of the knowledge point "perfect square formula" is lower than that of the knowledge point "mixed operations of integers-simplified evaluation".

[0022] In one embodiment, see Figure 2 , Figure 2 A schematic diagram of a sub-flow of a test question recommendation method provided by an embodiment of the present invention. The above step S103 includes steps S201-S202: S201, obtaining the answer record, answer time, error rate and number of errors of the answer information.

[0023] In specific implementations, answer information is comprehensively recorded through a variety of data collection methods, including online answering systems, data import tools, scanners, etc. In this embodiment, answer records, answering time, error rate, and number of errors of answer information are obtained. For example, answering time can be collected through the online answering system.

[0024] S202, determining the user habits according to the answering records and the answering time, and determining the mastery status according to the error rate and the number of errors, and the learning report includes the user habits and the mastery status.

[0025] In specific implementation, the answer records can be collected by scanning draft paper with a scanner, and the answer records and answer time can be analyzed to obtain user habits. User habits are used to evaluate the speed of the user's answering and the correctness of the answering ideas. Each knowledge point has an error rate and number of errors. The error rate and number of errors are analyzed to obtain the mastery status, which is used to evaluate the user's understanding of the knowledge points.

[0026] S104, determining a knowledge point map according to the knowledge points and the learning status report.

[0027] In the specific implementation, the knowledge point map is a multivariate connection graph with knowledge points as nodes. The degree of association between knowledge points is determined through learning reports. For example: the target user's wrong question 1 involves the knowledge point "determination of parallel lines", and wrong question 2 involves the knowledge point "properties of parallel lines", then the target user's "parallel lines" knowledge point is determined as the first weight, and "determination of parallel lines" and "properties of parallel lines" are respectively used as the second weights and are respectively associated with "parallel lines". The first weight is greater than the second weight, and the knowledge point map is divided into levels according to the weight size, and the association between nodes is marked with connecting lines.

[0028] In one embodiment, see Figure 3 , Figure 3 A schematic diagram of a sub-flow of a test question recommendation method provided by an embodiment of the present invention. The above step S104 includes steps S301-S302: S301, sorting the knowledge points based on the learning report.

[0029] In a specific implementation, the user habits in the learning report are used to evaluate the speed of the user's answering and the correctness of the answering ideas, and the mastery status of the learning report is used to evaluate the user's level of understanding of the knowledge points. Technical personnel in this field can flexibly adjust the basis for sorting. In one embodiment, the knowledge points are sorted from high to low according to the mastery status, and / or the knowledge points are sorted from slow to fast according to the answering speed.

[0030] S302, associating and sorting the knowledge points based on a preset association rule mining algorithm to obtain the knowledge point graph.

[0031] In the specific implementation, the association rule mining algorithm includes Apriori algorithm, PCY algorithm, multi-stage algorithm, multi-hash algorithm, FP-Tree algorithm, XFP-Tree algorithm, GPApriori algorithm, etc. In this embodiment, the association rule mining algorithm (such as Apriori algorithm) is used to discover the association relationship between knowledge points. The association relationship mining can reveal the logical connection between knowledge points and assist in the construction of knowledge point map. Knowledge point map: The extracted knowledge points and the association relationship between knowledge points are constructed into a map to form a structured and visual knowledge network. The intuitive display and query function of the knowledge map facilitates users to understand and use the relationship between knowledge points, thereby improving the teaching and learning effect.

[0032] S105, determining recommended test questions according to the knowledge point map.

[0033] In specific implementation, the knowledge point map can fully reflect the user's mastery level of each knowledge point. The knowledge point map can help students conduct targeted practice and review to improve learning outcomes.

[0034] In one embodiment, the above step S105 includes: inputting the knowledge point graph into a pre-trained test question recommendation model to obtain a target test question corresponding to the knowledge point graph, and the recommended test question includes the target test question.

[0035] In a specific implementation, the test question recommendation model obtains target test questions based on the knowledge points in the knowledge point map. For example, in a user's knowledge point map, the first weight is "parallel lines", the second weight is "properties of parallel lines" and "determination of parallel lines", and the third weight is "equal corresponding angles" and "equal interior alternate angles". The test question recommendation model collects test questions based on the first weight "parallel lines", arranges and filters the collected test questions based on the second weight, and selects any number of test questions based on the third weight, so that the selected test questions cover the knowledge points in the knowledge point map.

[0036] In one embodiment, the above step S105 also includes: determining similar users of the target user according to the knowledge point graph; obtaining historical answer data of the similar users, and the recommended test questions include the historical answer data of the similar users.

[0037] In a specific implementation, similar users are matched according to the knowledge point map. In this embodiment, a knowledge point map with the most similarity is determined through the database as the first knowledge point map, similar users are determined according to the first knowledge point map, and the knowledge point map subsequently generated by the similar users is obtained as the second knowledge point map. By comparing the first knowledge point map with the second knowledge point map, the improvement efficiency of the similar users is determined. If the improvement efficiency of the similar users is higher than the preset threshold, the recommended test questions determined according to the second knowledge point map are pushed to the target user as the recommended test questions. By determining the recommended test questions by imitating the order of similar users' questions, on the one hand, the efficiency of generating test questions can be improved, and on the other hand, the improvement effect of similar users provides a clear direction and basis for the target users.

[0038] In one embodiment, after the above step S105, the method further includes: based on a preset evaluation strategy, evaluating whether the content, difficulty and format of the recommended test questions meet the evaluation criteria; If any of the content, difficulty and format of the test questions do not meet the evaluation criteria, the step of determining recommended test questions based on the knowledge point map is performed.

[0039] In the specific implementation, the generated test questions will be reviewed and optimized by the test question optimization module. The test question optimization module has a preset evaluation strategy and will evaluate the content, difficulty, format, etc. of the test questions to ensure that they meet the educational standards and difficulty requirements. The formulation of the evaluation strategy can be combined with manual review and / or machine review to further improve the quality and applicability of the test questions. The optimized test questions will be sorted and classified and entered into the question bank for subsequent use.

[0040] The embodiments of the present invention can achieve the following advantages: Using natural language processing (NLP) technology, relevant knowledge points are extracted from the collected data. Through semantic analysis and information extraction, the system classifies and organizes these knowledge points to form a structured knowledge point map. The knowledge point map not only includes the relationship between knowledge points, but also reflects the hierarchy and importance of knowledge points, providing a clear direction and basis for question generation, ensuring that the recommended questions can effectively help students consolidate knowledge and improve learning outcomes.

[0041] See also Figure 4 The embodiment of the present invention further provides a test question recommendation device 400 , which includes an acquisition unit 401 , a first determination unit 402 , a second determination unit 403 , a third determination unit 404 and a fourth determination unit 405 .

[0042] The acquisition unit 401 is used to acquire the historical answer data of the target user, and the historical answer data includes question information and answer information.

[0043] The first determination unit 402 is used to input the topic information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the topic information.

[0044] In one embodiment, the pre-trained natural language analysis model includes: Obtain the content of the question sample as input data; Inputting the input data into a preset neural network model; Determine whether the output result of the neural network model is the same as the knowledge point of the question sample; If the output result of the neural network model is different from the knowledge point of the question sample, the output result of the neural network model is used as new input data, and the step of inputting the input data into the neural network model is returned.

[0045] The second determination unit 403 is used to determine the user portrait of the target user according to the answer information, and the user portrait includes a learning status report.

[0046] In one embodiment, the user profile of the target user is determined according to the answer information, and the user profile includes a learning status report, including: Obtain answer records, answer time, error rate, and number of errors of the answer information; The user habit is determined according to the answering record and the answering time, the mastery status is determined according to the error rate and the number of errors, and the learning report includes the user habit and the mastery status.

[0047] The third determination unit 404 is used to determine a knowledge point map according to the knowledge points and the learning situation report.

[0048] In one embodiment, determining a knowledge point map according to the knowledge point and the learning report includes: sorting the knowledge points based on the learning report; The knowledge point graph is obtained by associating and sorting the knowledge points based on a preset association rule mining algorithm.

[0049] The fourth determining unit 405 is used to determine recommended test questions according to the knowledge point map.

[0050] In one embodiment, determining recommended test questions according to the knowledge point graph includes: The knowledge point graph is input into a pre-trained test question recommendation model to obtain a target test question corresponding to the knowledge point graph, and the recommended test question includes the target test question.

[0051] In one embodiment, determining recommended test questions according to the knowledge point graph further includes: Determine similar users of the target user according to the knowledge point graph; The historical answering data of the similar users is obtained, and the recommended test questions include the historical answering data of the similar users.

[0052] In one embodiment, after determining the recommended test questions according to the knowledge point map, the method further includes: Based on the preset evaluation strategy, respectively evaluate whether the content, difficulty and format of the recommended test questions meet the evaluation criteria; If any of the content, difficulty and format of the test questions do not meet the evaluation criteria, the step of determining recommended test questions based on the knowledge point map is performed.

[0053] like Figure 5 As shown, Figure 5 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0054] The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0055] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a test question recommendation method.

[0056] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0057] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a test question recommendation method.

[0058] The network interface 505 is used to communicate with other devices over the network. Those skilled in the art will appreciate that the above structure is only a block diagram of a portion of the structure related to the present application solution, and does not constitute a limitation on the computer device 500 to which the present application solution is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0059] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0060] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0061] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program.

[0062] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes. The computer-readable storage medium can be non-volatile or volatile.

[0063] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0064] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0065] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0066] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0067] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0068] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0069] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A test question recommendation method, characterized in that: The method comprises: Obtaining historical answer data of the target user, wherein the historical answer data includes question information and answer information; Inputting the topic information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the topic information; Determine a user profile of the target user according to the answer information, wherein the user profile includes a learning status report; Determine a knowledge point map according to the knowledge points and the learning report; Determine recommended test questions based on the knowledge point map.

2. The method according to claim 1, characterized in that The pre-trained natural language analysis model includes: Obtain the content of the question sample as input data; Inputting the input data into a preset neural network model; Determine whether the output result of the neural network model is the same as the knowledge point of the question sample; If the output result of the neural network model is different from the knowledge point of the question sample, the output result of the neural network model is used as new input data, and the step of inputting the input data into the neural network model is returned.

3. The method according to claim 1, characterized in that The determining of the user profile of the target user according to the answer information, wherein the user profile includes a learning status report, including: Obtain answer records, answer time, error rate, and number of errors of the answer information; The user habit is determined according to the answering record and the answering time, the mastery status is determined according to the error rate and the number of errors, and the learning report includes the user habit and the mastery status.

4. The method according to claim 1, characterized in that Determining a knowledge point map according to the knowledge point and the learning report includes: sorting the knowledge points based on the learning report; The knowledge point graph is obtained by associating and sorting the knowledge points based on a preset association rule mining algorithm.

5. The method according to claim 1, characterized in that The determining of recommended test questions according to the knowledge point map includes: The knowledge point graph is input into a pre-trained test question recommendation model to obtain a target test question corresponding to the knowledge point graph, and the recommended test question includes the target test question.

6. The method according to claim 1, characterized in that The step of determining the recommended test questions according to the knowledge point graph further includes: Determine similar users of the target user according to the knowledge point graph; The historical answering data of the similar users is obtained, and the recommended test questions include the historical answering data of the similar users.

7. The method according to claim 1, characterized in that After determining the recommended test questions according to the knowledge point map, the method further includes: Based on the preset evaluation strategy, respectively evaluate whether the content, difficulty and format of the recommended test questions meet the evaluation criteria; If any of the content, difficulty and format of the test questions do not meet the evaluation criteria, the step of determining recommended test questions based on the knowledge point map is performed.

8. A test question recommendation device, characterized in that: include: An acquisition unit, used to acquire historical answer data of a target user, wherein the historical answer data includes question information and answer information; A first determining unit, configured to input the topic information into a pre-trained natural language analysis model to obtain knowledge points corresponding to the topic information; A second determining unit, configured to determine a user profile of the target user according to the answer information, wherein the user profile includes a learning status report; A third determining unit, configured to determine a knowledge point map according to the knowledge point and the learning status report; The fourth determining unit is used to determine recommended test questions according to the knowledge point map.

9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the steps of the method described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images