CN106407237B - Online learning test question recommendation method and system - Google Patents
Online learning test question recommendation method and system Download PDFInfo
- Publication number
- CN106407237B CN106407237B CN201510481754.8A CN201510481754A CN106407237B CN 106407237 B CN106407237 B CN 106407237B CN 201510481754 A CN201510481754 A CN 201510481754A CN 106407237 B CN106407237 B CN 106407237B
- Authority
- CN
- China
- Prior art keywords
- test question
- user
- examination
- test
- questions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a method and a system for recommending online learning test questions, wherein the method comprises the following steps: acquiring question making information of a user and skill information of examination questions from a knowledge resource library, wherein the skill information of the examination questions comprises: knowledge point information of examination question investigation and abstract capability information of examination question investigation; performing learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result; determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination; and recommending the determined candidate recommended test question set to the user. By using the method and the device, the test questions recommended to the user can be more targeted, the requirement of the user on-line personalized learning is met, and the learning efficiency of the user is effectively improved.
Description
Technical Field
The invention relates to the technical field of online information recommendation, in particular to a method and a system for recommending online learning test questions.
Background
With the continuous popularization of computers and the rapid development of information technology, the way of acquiring knowledge has changed fundamentally, and the way of education based on network has been gradually known and accepted. An online learning test question recommendation system, an online examination system and the like are used as an education auxiliary platform, and a large number of students and teacher users are won by a convenient and practical learning method based on massive test question resources. However, these platforms often center on the system itself, and do not consider the actual situation of the user, which causes the problems of inconsistent recommended test questions and user ability, poor interactivity, low learning efficiency, and the like. Therefore, how to reasonably and efficiently recommend appropriate test questions according to the learning conditions of the users becomes a main direction for the development of the current online learning system.
The existing test question recommendation system generally recommends test questions according to the interests of users, the recommended test questions are equivalent to items in the traditional electronic commerce recommendation system such as movies and books during specific recommendation, the difference between an education direction online learning system and the traditional electronic commerce system is ignored, the education direction online learning system mainly aims at effectively improving the learning level of the users, the commodity recommendation is not performed according to the interests of the users, the test questions which are interested by the users are not necessarily suitable for the test questions recommended to the users, the actual skill mastering conditions of the users are not known enough, and the selection of the test questions is blind. Moreover, different users prefer different question making modes, some users prefer to select the questions with challenging and high difficulty, and some users prefer to select the common questions with low difficulty. Therefore, the traditional test question recommendation method cannot well explore the real learning level of the user.
Disclosure of Invention
The embodiment of the invention provides a method and a system for recommending on-line learning test questions, so that the test questions recommended to a user are more targeted, the requirements of the user on personalized on-line learning are met, and the learning efficiency of the user is effectively improved.
In order to achieve the purpose, the technical scheme of the invention is as follows:
an online learning test question recommendation method comprises the following steps:
acquiring question making information of a user and skill information of examination questions from a knowledge resource library, wherein the skill information of the examination questions comprises: knowledge point information of examination question investigation and abstract capability information of examination question investigation;
performing learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result;
determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination;
and recommending the determined candidate recommended test question set to the user.
Preferably, the performing a learning situation diagnosis on the learning situation of the user according to the question information of the user, and obtaining a learning situation diagnosis result includes:
incremental learning is carried out by utilizing the cognitive diagnosis model to obtain the skill mastering degree of the user;
and performing incremental learning by using the IRT model to obtain the test question difficulty, the test question discrimination and the overall capability of the user.
Preferably, the determining the set of candidate recommended test questions according to the study situation diagnosis result and the skill information of the test question examination includes:
calculating the matching degree of the skill information of the examination of the test questions and the skill mastering degree of the user, and taking the matching degree as a first matching degree;
calculating the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user, and taking the matching degree as a second matching degree;
and constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
Preferably, the method further comprises:
screening test questions from the candidate recommended test question set before recommending the determined candidate recommended test question set to the user to obtain a final recommended test question set;
the recommending the determined candidate recommended test question set to the user specifically comprises: and recommending the final recommended test question set to the user.
Preferably, the screening of the test questions from the candidate recommended test question set to obtain a final recommended test question set includes:
determining a test question screening principle, wherein the screening principle comprises the following steps:
(1) the difficulty distribution of the screened test question set is in a spindle-shaped structure;
(2) the screened test question set should cover as many examination skills as possible;
and screening the test questions from the candidate recommended test question set according to the screening principle to obtain a final recommended test question set.
Preferably, the screening of the test questions from the candidate recommended test question set according to the screening principle to obtain the screened test question set includes:
determining a test question screening loss function according to the screening principle;
initializing a final recommended test set into a candidate recommended test set;
calculating the value of a loss function of the final recommended test question set after deleting each test question in the final recommended test question set;
and determining whether to delete the test question corresponding to each loss function according to the obtained value of each loss function.
An online learning test question recommendation system comprising:
the information acquisition module is used for acquiring the question making information of the user and the skill information of the test question examination from the knowledge resource library, wherein the skill information of the test question examination comprises the following steps: knowledge point information of examination question investigation and abstract capability information of examination question investigation;
the learning condition diagnosis module is used for carrying out learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result;
the recommendation test question determining module is used for determining a candidate recommendation test question set according to the study condition diagnosis result and the skill information of the test question examination;
and the recommending module is used for recommending the candidate recommended test question set determined by the recommended test question determining module to the user.
Preferably, the situational diagnostic module comprises:
the first diagnosis unit is used for incremental learning by using the cognitive diagnosis model to obtain the skill mastering degree of the user;
and the second diagnosis unit is used for performing incremental learning by utilizing the IRT model to obtain the test question difficulty, the test question discrimination and the overall capability of the user.
Preferably, the recommended test question determining module includes:
the first calculation unit is used for calculating the matching degree of the skill information of the test examination and the skill mastering degree of the user and taking the matching degree as a first matching degree;
the second calculating unit is used for calculating the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user and taking the matching degree as a second matching degree;
and the determining unit is used for constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
Preferably, the system further comprises:
the screening module is used for screening the test questions from the candidate recommended test question set to obtain a final recommended test question set;
the recommending module is specifically used for recommending the final recommended test question set to the user.
Preferably, the screening module comprises:
the screening principle determining unit is used for determining a screening principle of test questions, and the screening principle comprises the following steps:
(1) the difficulty distribution of the screened test question set is in a spindle-shaped structure;
(2) the screened test question set should cover as many examination skills as possible;
and the screening unit is used for screening the test questions from the candidate recommended test question set according to the screening principle to obtain a final recommended test question set.
Preferably, the screening unit includes:
the function determining unit is used for determining a test question screening loss function according to the screening principle;
the initialization unit is used for initializing the final recommended test question set into a candidate recommended test question set;
the function value calculating unit is used for calculating the value of the loss function of the final recommended test question set after each test question in the final recommended test question set is deleted;
and the deleting unit is used for determining whether to delete the test questions corresponding to the values according to the obtained values of the loss functions to obtain a final recommended test question set.
According to the on-line learning test question recommendation method and system provided by the embodiment of the invention, the question making information of a user and the skill information of test question examination are obtained from a knowledge resource library, and the learning condition of the user is diagnosed according to the question making information of the user to obtain a learning condition diagnosis result; then determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination, and screening test questions from the candidate recommended test question set to obtain a final recommended test question set; and finally recommending the final recommended test question set to a user. The method realizes the personalized and adaptive recommendation of different users, meets the requirements of the user on personalized learning, and thus can effectively improve the learning efficiency of the user.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for recommending an online learning test question according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the determination of a set of candidate recommended test questions according to the study diagnosis result and the skill information of the test question examination according to an embodiment of the present invention;
FIG. 3 is another flow chart of a method for recommending an online learning test question according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating screening of a candidate set of recommended test questions according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an online learning test question recommendation system according to an embodiment of the present invention;
fig. 6 is another schematic structural diagram of the online learning test question recommendation system according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the flowchart of the method for recommending an online learning test question according to the embodiment of the present invention includes the following steps:
The question making information refers to the correction result of the answers made to the questions by the user, such as the scores of the user on the questions.
The skill information of the examination questions comprises knowledge point information of the examination questions and abstract ability information of the examination questions, and the information can be given by a field expert or obtained by an automatic prediction method in an off-line mode. The automatic prediction can be realized by collecting a large amount of test question information labeled by field experts in advance, carrying out statistical modeling and then carrying out prediction by utilizing a constructed statistical model.
For example, the skill information vector for the examination of the test question i can be represented as Qi＝{Qi1,Qi2,...QiK}，QijAnd (4) indicating whether the test question i examines the skill j, wherein K is the total skill required by the course.
And 102, carrying out learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result.
In an embodiment of the present invention, the diagnosis result of the emotional condition may include: the difficulty of the test questions, the degree of distinction of the test questions, the skill mastering degree of the user, the whole physical ability value and the like.
Specifically, the learning situation of the user can be diagnosed through a cognitive Diagnosis Model, such as RSM (rule space Model), AHM (Attribute Model), FM (Fusion Model), GDM (General diagnostics Model), DINA (deterministic inputs, noise and gate) Model, and the like.
Among them, the DINA model is one of the cognitive diagnosis models widely used at present, and the model is relatively simple and has high diagnosis accuracy. The DINA model mainly comprises two project parameters, namely a guess parameter (g) and a fault parameter(s), wherein the g is the probability that the tested item does not know all attributes of the item examination but answers the item; s is the probability of the trial mastering all the attributes of the project assessment but the wrong answer. The parameters s and g reflect to some extent the noise in the diagnosis. In cognitive diagnosis, it is generally considered that if a subject does not grasp all attributes of an item assessment, the subject tends to answer the item.
In the embodiment of the invention, incremental learning is carried out according to a probabilistic DINA model to obtain a user skill mastering vector U ═ { U ═ U { (U) }1,U2,...UK}。
The difficulty of the test questions, the degree of distinction and the overall ability of the user can be obtained by incremental learning according to a traditional IRT (Item response theory) model, and the difficulty of the test questions and the degree of distinction can also be given by field experts.
And 103, determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination.
And 104, recommending the determined candidate recommended test question set to the user.
For example, the test questions in the determined candidate recommended test question set can be displayed to the user one by one, the user can submit answers online, and the system gives the final scores; or packaging the test questions in the determined candidate recommended test question set, providing a download path for the user and the like. Of course, the test questions may also be recommended to the user in other ways, which is not limited in the embodiment of the present invention.
According to the method for recommending the on-line learning test questions, the question-making information of the user and the skill information of the test question examination are obtained from the knowledge resource library, and the learning condition of the user is diagnosed according to the question-making information of the user to obtain a learning condition diagnosis result; and then determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination, and recommending the determined candidate recommended test question set to the user. The method realizes the personalized and adaptive recommendation of different users, meets the requirements of the user on personalized learning, and thus can effectively improve the learning efficiency of the user.
In addition, the existing test question recommendation system takes the test question as the recommendation granularity during the test question recommendation, and does not analyze the skills or knowledge structures investigated by the test questions finely. For each course, different examination questions have different emphasis points and different requirements on the skill mastering of the user. The recommendation is directly carried out by taking the test questions as granularity, and the granularity is too large, so that the skill information examined by the test questions and the skill mastering condition of a user, such as the knowledge point mastering, cannot be considered, and finally, the recommendation effect is not ideal. The invention fully considers different skill information such as knowledge points, abstract ability and the like of examination question investigation, so that the examination granularity of the examination questions to be recommended is finer, and the requirement of user personalized learning can be better met.
As shown in fig. 2, the flowchart of determining a candidate recommended test question set according to the study situation diagnosis result and the skill information of the test question examination in the embodiment of the present invention includes the following steps:
The closer the mastering degree of the user to the test question examination skill is to the middle level mastering degree, the more suitable the test question is to be recommended to the user, and the test question can help the user to consolidate and strengthen the knowledge points to be mastered, so that the learning ability of the user is rapidly improved. Therefore, in the embodiment of the present invention, the first matching degree may be characterized by using the degree of grasp of the skill of the user for examination of the test question and the degree of grasp at the intermediate level.
The specific calculation process of the first matching degree is as follows:
first, the sum of the difference between the grasping degree of each skill of the user for examination and the grasping degree of the intermediate level is calculated as a first calculation value. For example, when the user grasp degree is expressed by a value between 0 and 1, the intermediate level grasp degree may be expressed by 0.5.
The first calculated value is then divided by the total skill in the lesson exam to produce a second calculated value.
Finally, the degree of grasp of the user for the examination skill of the test question is expressed by the inverse number of the second calculated value as the degree of grasp at the intermediate level.
The above calculation process can be described by the following formula (1):
wherein HiThe degree of mastery of the skill of the user for examination of the test question i is close to the degree of mastery of the intermediate level; qijFor the examination condition of the examination question i on the skill j, if the examination question i examines the skill j, Qij1, otherwise Qij＝0；UjFor the user's mastery degree of skill j, e.g. taking the value Uj∈[0,1]0 is completely not mastered, 1 is completely mastered; σ is a value at which the user's mastery degree of skill is at an intermediate level, and it takes, for example, 0.5.
In the embodiment of the invention, the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user is reflected by the information quantity provided by the test questions to the user.
According to the IRT theory, the larger the information quantity provided by the test questions to the user is, the more suitable the test questions are recommended to the user, the more the calculation of the information quantity of the test questions can be specifically, after the correct answer probability of the test questions to be recommended by the user is calculated according to the overall capacity value of the user, the information quantity of the test questions to be recommended is calculated by using the correct answer probability of the user, and the formula (2) is as follows:
wherein, Ii(θ)Indicates the amount of information, P, provided to the user with the overall physical strength value of theta for the ith test questioni(θ) represents the probability of correct answer of the user with the overall physical ability value θ on the test question i, and the specific calculation formula is as follows:
where θ is the user's overall physical strength value, biIs the difficulty coefficient of the ith test question, aiThe discrimination coefficient is the ith test question.
And step 203, constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
The test question selection conditions are as follows:
wherein Z is a candidate recommended test question set, tau is a skill matching degree threshold value, and epsilon is a test question information quantity threshold value; the threshold τ <0, ε >0, the specific value of which can be determined according to the actual situation.
Further, in another embodiment of the method of the present invention, the test questions in the determined candidate recommended test question set may be screened according to the application requirements, so as to obtain a certain number of recommended test questions or recommended test questions meeting a certain requirement, and the recommended test questions are more matched with the actual requirements of the user.
As shown in fig. 3, another flowchart of the method for recommending an online learning test question according to the embodiment of the present invention includes the following steps:
And 304, screening test questions from the candidate recommended test question set to obtain a final recommended test question set.
After the candidate recommended test question set is generated, test questions more suitable for being recommended to the user are screened from the candidate recommended test question set. For example, the following screening principles may be determined:
1) the difficulty distribution of the screened test question sets is in a spindle-shaped structure, that is, in the final recommended test question set, the difficulty distribution of the test questions should approximately follow a normal distribution, that is, the difficulty of most recommended test questions should be moderate, and a small number of questions are difficult or easy.
According to the principle, the final recommended test question set is W, and a difficulty distribution loss function F (W) of the screened test questions can be defined as shown in formula (4):
wherein mu is a target difficulty mean value; sigma2A target difficulty variance; mu (W) is the difficulty mean value of all the test questions in the test question set W, sigma2(W) is the difficulty variance of all the test questions in the test question set W.
The smaller F (W), the closer the difficulty distribution of the test questions in W is to (mu, sigma)2) Is a normal distribution of the target difficulty.
2) The set of screened questions should cover as much of the examination skills as possible.
According to the principle, a function G (W) of loss of skill coverage of the screening test questions can be defined as shown in formula (5):
wherein N is the total number of test questions in the test question set W, OiAnd OjRepresenting the ith and jth test questions in the test question set W. C is a similarity measurement function of the test questions, and the calculation method is shown in the formula (6):
wherein o isik,ojkTo show the question oiAnd examination question ojThe k-th dimension skill examination condition of (1) is not examined as 0; k is the total skill required for the course.
Then, according to the above principle, the candidate recommended test question set is screened to obtain a final recommended test question set, and a specific screening process will be described in detail later.
Of course, in practical applications, other screening principles may be set according to different user requirements, and the embodiment of the present invention is not limited thereto.
And 305, recommending the final recommended test question set to the user.
The method for recommending the test questions for online learning further screens out more suitable test questions from the determined candidate recommended test question set and recommends the test questions to the user, so that the requirements of the user on personalized learning can be better met, and the learning efficiency of the user is effectively improved.
As shown in fig. 4, which is a flowchart of screening test questions from a candidate recommended test question set in the embodiment of the present invention, the method includes the following steps:
Specifically, a test question screening loss function j (w) can be defined as shown in formula (7):
J(W)＝δ·F(W)+(1-δ)·G(W) (7)
wherein, delta is a weight coefficient and has a value range of 0-1. The specific value of the delta can be manually adjusted, the smaller the delta is, the larger the proportion of the skill coverage loss function G (W) in the loss function J (W) is, and the more the screening of the test questions is focused on the influence of the skill coverage; the greater the δ, the greater the proportion of the difficulty distribution loss function f (w) in the loss function j (w), and the more the test question is screened for the influence of difficulty distribution.
And step 402, initializing the final recommended test question set W into a candidate recommended test question set Z.
And step 403, calculating the loss function value of the final recommended test question set after deleting each test question in the final recommended test question set W.
That is, each test question O in the deleted W' is calculated, and the loss function J (W- { O } after deleting this question is calculated.
And step 404, determining whether to delete the test question corresponding to each obtained loss function value according to the obtained loss function value.
Specifically, a set number of test questions can be recommended to the user finally according to the actual application requirements, and an indefinite number of test questions meeting the requirements can be recommended to the user according to the matching condition of the test questions.
For example, if a set number of test questions are recommended to the user, the final recommended set of test questions may be determined as follows:
1) sequencing the obtained loss function values;
2) selecting the test questions deleted by the omega minimum loss function values to be put into a test question set T to be deleted, wherein T is (O)1,O2,…,Oω) Omega is the preset number of the test questions deleted each time, and omega is more than or equal to 1;
3) setting the index of each test question in the test question set to be deleted as d, and setting d as 1;
4) judging whether d is less than omega; if yes, executing step 5); otherwise, executing step 2);
5) determining the size (W) of the set W, if size (W)>Upsilon (upsilon is the number of the final recommended test questions), then the test questions O are deleteddAnd d +1, then executing step 4), otherwise, outputting a final recommended test question set W'.
For another example, if an indefinite number of test questions meeting the requirements are recommended to the user, a threshold may be set, and the test questions corresponding to the loss function values smaller than the threshold among the calculated loss function values are deleted from the candidate recommended test question set, so as to obtain the test question set most suitable for the user.
Of course, other screening methods are possible according to application requirements, and are not listed here.
Correspondingly, the embodiment of the invention also provides an online learning test question recommendation system, which is a structural schematic diagram of the system as shown in fig. 5.
In this embodiment, the system includes:
the information obtaining module 501 is configured to obtain question information of a user and skill information of test question examination from a knowledge resource library, where the skill information of the test question examination includes: knowledge point information of examination question investigation and abstract capability information of examination question investigation;
the learning condition diagnosis module 502 is configured to perform learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result;
a recommended test question determining module 503, configured to determine a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination;
a recommending module 504, configured to recommend the candidate recommended test question set determined by the recommended test question determining module to the user.
The situational diagnostic results may include: the difficulty of the test questions, the degree of distinction of the test questions, the skill mastering degree of the user, the whole physical ability value and the like. Accordingly, one specific structure of the situational diagnostic module 502 can include: the system comprises a first diagnosis unit and a second diagnosis unit, wherein the first diagnosis unit is used for incremental learning by using a cognitive diagnosis model to obtain the skill mastering degree of a user; the second diagnosis unit is used for incremental learning by utilizing the IRT model to obtain the test question difficulty, the test question discrimination and the overall capability of the user. Of course, the learning condition diagnosing module 502 may also perform learning condition diagnosis on the learning condition of the user by adopting other manners and corresponding structures, which is not limited in the embodiment of the present invention.
The recommended test question determining module 503 may specifically determine the candidate recommended test question set according to the matching degree between the skill information of the test question examination and the skill mastering degree of the user, and the matching degree between the difficulty and the discrimination degree of the test questions and the overall ability of the user, so that the determined recommended test questions can better meet the requirement of the user for personalized learning. Accordingly, a specific structure of the recommended test question determining module 503 may include the following units:
the first calculation unit is used for calculating the matching degree of the skill information of the test examination and the skill mastering degree of the user and taking the matching degree as a first matching degree;
the second calculating unit is used for calculating the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user and taking the matching degree as a second matching degree;
and the determining unit is used for constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
The on-line learning test question recommendation system of the embodiment of the invention obtains the question-making information of a user and the skill information of test question examination from a knowledge resource library, and carries out learning condition diagnosis on the learning condition of the user according to the question-making information of the user to obtain a learning condition diagnosis result; and then determining a candidate recommended test question set according to the study condition diagnosis result and the skill information of the test question examination, and recommending the determined candidate recommended test question set to the user. The method realizes the personalized and adaptive recommendation of different users, meets the requirements of the user on personalized learning, and thus can effectively improve the learning efficiency of the user. In addition, different skill information such as knowledge points, abstract ability and the like of examination question investigation is fully considered, so that the examination granularity of the examination questions to be recommended is finer, and the requirement of user personalized learning can be met.
Fig. 6 is another schematic structural diagram of the online learning test question recommendation system according to the embodiment of the present invention.
The difference with the embodiment shown in fig. 5 is that in this embodiment the system further comprises: and the screening module 601 is configured to screen the test questions from the candidate recommended test question set to obtain a final recommended test question set.
Moreover, in the embodiment shown in fig. 5, the recommending module 504 directly recommends the candidate recommended test question set determined by the recommended test question determining module 503 to the user; in the embodiment shown in fig. 6, the recommending module 504 recommends the final recommended test question set screened by the screening module 601 to the user. That is to say, in this embodiment, a more suitable test question is further screened from the determined candidate recommended test question set and recommended to the user, so that the requirement of the user for personalized learning can be better met, and the learning efficiency of the user is effectively improved.
In practical application, the screening module 601 may determine a screening principle according to actual needs of a user, and then screen the test questions in the candidate recommended test question set according to the screening principle to obtain a certain number of recommended test questions or recommended test questions meeting a certain requirement, so that the recommended test questions are more matched with the actual needs of the user.
Accordingly, one specific structure of the screening module 601 may include: screening principle determination unit and screening unit, wherein:
a screening rule determining unit, configured to determine a screening rule for the test question, where the screening rule includes the following two points:
(1) the difficulty distribution of the screened test question set is in a spindle-shaped structure;
(2) the set of screened questions should cover as much of the examination skills as possible.
Of course, other screening principles may be set according to the actual application requirement, and the embodiment of the present invention is not limited.
And the screening unit is used for screening the test questions from the candidate recommended test question set according to the screening principle to obtain a final recommended test question set.
A specific implementation structure of the screening unit may include the following units:
the function determining unit is used for determining a test question screening loss function according to the screening principle;
the initialization unit is used for initializing the final recommended test question set into a candidate recommended test question set;
the function value calculating unit is used for calculating the value of the loss function of the final recommended test question set after each test question in the final recommended test question set is deleted;
and the deleting unit is used for determining whether to delete the test questions corresponding to the values according to the obtained values of the loss functions to obtain a final recommended test question set.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, they are described in a relatively simple manner, and reference may be made to some descriptions of method embodiments for relevant points. The above-described system embodiments are merely illustrative, and the units and modules described as separate components may or may not be physically separate. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The construction, features and functions of the present invention are described in detail in the embodiments illustrated in the drawings, which are only preferred embodiments of the present invention, but the present invention is not limited by the drawings, and all equivalent embodiments modified or changed according to the idea of the present invention should fall within the protection scope of the present invention without departing from the spirit of the present invention covered by the description and the drawings.
Claims (12)
1. An online learning test question recommendation method is characterized by comprising the following steps:
acquiring question making information of a user and skill information of examination questions from a knowledge resource library, wherein the skill information of the examination questions comprises: knowledge point information of examination question investigation and abstract capability information of examination question investigation;
performing learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result;
determining a candidate recommended test question set according to the study situation diagnosis result and the skill information of the test question examination, wherein the candidate recommended test question set comprises the following steps: calculating the closeness degree of the mastery degree of the user on the skills of the examination questions and the middle level mastery degree according to the mastery degree of the user on each skill of the examination questions, the preset middle level mastery degree and the total skill number of the course examination;
and recommending the determined candidate recommended test question set to the user.
2. The method according to claim 1, wherein the performing the learning situation diagnosis on the learning situation of the user according to the question information of the user to obtain the learning situation diagnosis result comprises:
incremental learning is carried out by utilizing the cognitive diagnosis model to obtain the skill mastering degree of the user;
and performing incremental learning by using the IRT model to obtain the test question difficulty, the test question discrimination and the overall capability of the user.
3. The method of claim 2, wherein the determining the set of candidate recommended questions according to the study situation diagnosis result and the skill information of the examination question examination specifically comprises:
calculating the matching degree of the skill information of the examination of the test questions and the skill mastering degree of the user, and taking the matching degree as a first matching degree;
calculating the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user, and taking the matching degree as a second matching degree;
and constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
4. The method according to any one of claims 1 to 3, further comprising:
screening test questions from the candidate recommended test question set before recommending the determined candidate recommended test question set to the user to obtain a final recommended test question set;
the recommending the determined candidate recommended test question set to the user specifically comprises: and recommending the final recommended test question set to the user.
5. The method of claim 4, wherein screening the candidate recommended test question set for test questions to obtain a final recommended test question set comprises:
determining a test question screening principle, wherein the screening principle comprises the following steps:
(1) the difficulty distribution of the screened test question set is in a spindle-shaped structure;
(2) the screened test question set should cover as many examination skills as possible;
and screening the test questions from the candidate recommended test question set according to the screening principle to obtain a final recommended test question set.
6. The method of claim 5, wherein screening the set of candidate recommended test questions according to the screening rules to obtain a screened set of test questions comprises:
determining a test question screening loss function according to the screening principle;
initializing a final recommended test set into a candidate recommended test set;
calculating the value of a loss function of the final recommended test question set after deleting each test question in the final recommended test question set;
and determining whether to delete the test question corresponding to each loss function according to the obtained value of each loss function.
7. An online learning test question recommendation system, comprising:
the information acquisition module is used for acquiring the question making information of the user and the skill information of the test question examination from the knowledge resource library, wherein the skill information of the test question examination comprises the following steps: knowledge point information of examination question investigation and abstract capability information of examination question investigation;
the learning condition diagnosis module is used for carrying out learning condition diagnosis on the learning condition of the user according to the question making information of the user to obtain a learning condition diagnosis result;
the recommendation test question determining module is used for determining a candidate recommendation test question set according to the study condition diagnosis result and the skill information of the test question examination, and comprises the following steps: calculating the closeness degree of the mastery degree of the user on the skills of the examination questions and the middle level mastery degree according to the mastery degree of the user on each skill of the examination questions, the preset middle level mastery degree and the total skill number of the course examination;
and the recommending module is used for recommending the candidate recommended test question set determined by the recommended test question determining module to the user.
8. The system of claim 7, wherein the situational diagnostic module comprises:
the first diagnosis unit is used for incremental learning by using the cognitive diagnosis model to obtain the skill mastering degree of the user;
and the second diagnosis unit is used for performing incremental learning by utilizing the IRT model to obtain the test question difficulty, the test question discrimination and the overall capability of the user.
9. The system of claim 8, wherein the recommended test question determining module specifically comprises:
the first calculation unit is used for calculating the matching degree of the skill information of the test examination and the skill mastering degree of the user and taking the matching degree as a first matching degree;
the second calculating unit is used for calculating the matching degree of the difficulty and the discrimination of the test questions and the overall capability of the user and taking the matching degree as a second matching degree;
and the determining unit is used for constructing a candidate recommended test question set according to the first matching degree and the second matching degree.
10. The system of any one of claims 7 to 9, further comprising:
the screening module is used for screening the test questions from the candidate recommended test question set to obtain a final recommended test question set;
the recommending module is specifically used for recommending the final recommended test question set to the user.
11. The system of claim 10, wherein the screening module comprises:
the screening principle determining unit is used for determining a screening principle of test questions, and the screening principle comprises the following steps:
(1) the difficulty distribution of the screened test question set is in a spindle-shaped structure;
(2) the screened test question set should cover as many examination skills as possible;
and the screening unit is used for screening the test questions from the candidate recommended test question set according to the screening principle to obtain a final recommended test question set.
12. The system of claim 11, wherein the screening unit comprises:
the function determining unit is used for determining a test question screening loss function according to the screening principle;
the initialization unit is used for initializing the final recommended test question set into a candidate recommended test question set;
the function value calculating unit is used for calculating the value of the loss function of the final recommended test question set after each test question in the final recommended test question set is deleted;
and the deleting unit is used for determining whether to delete the test questions corresponding to the values according to the obtained values of the loss functions to obtain a final recommended test question set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510481754.8A CN106407237B (en) | 2015-08-03 | 2015-08-03 | Online learning test question recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510481754.8A CN106407237B (en) | 2015-08-03 | 2015-08-03 | Online learning test question recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106407237A CN106407237A (en) | 2017-02-15 |
| CN106407237B true CN106407237B (en) | 2020-02-07 |
Family
ID=58007601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510481754.8A Active CN106407237B (en) | 2015-08-03 | 2015-08-03 | Online learning test question recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407237B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107221212B (en) * | 2017-05-27 | 2020-08-14 | 广州大洋教育科技股份有限公司 | Online learner cognitive style analysis method based on time sequence |
| CN108133736A (en) * | 2017-12-22 | 2018-06-08 | 谢海群 | A kind of adaptivity cognitive function appraisal procedure and system |
| CN109242103A (en) * | 2018-07-20 | 2019-01-18 | 张有明 | Difficulty of knowledge points assignment processing method and processing device suitable for learning management system |
| CN109509126A (en) * | 2018-11-02 | 2019-03-22 | 中山大学 | A kind of personalized examination question recommended method based on user's learning behavior |
| CN109857835B (en) * | 2018-12-28 | 2021-04-02 | 北京红山瑞达科技有限公司 | Self-adaptive network security knowledge evaluation method based on cognitive diagnosis theory |
| CN109919810B (en) * | 2019-01-22 | 2023-01-24 | 山东科技大学 | Student modeling and personalized course recommendation method in online learning system |
| CN110033402A (en) * | 2019-04-12 | 2019-07-19 | 上海乂学教育科技有限公司 | Thinking mathematical studying method and computer learning system based on capacity sizing |
| CN110209951A (en) * | 2019-06-12 | 2019-09-06 | 广州壹学车智能信息科技有限公司 | A kind of reaction type driving school training system |
| CN110413728B (en) * | 2019-06-20 | 2023-10-27 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for recommending exercise problems |
| CN112307320A (en) * | 2019-08-20 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information pushing method and device, mobile terminal and storage medium |
| CN110659352B (en) * | 2019-10-10 | 2023-06-13 | 浙江蓝鸽科技有限公司 | Test question examination point identification method and system |
| CN110704510A (en) * | 2019-10-12 | 2020-01-17 | 中森云链(成都)科技有限责任公司 | User portrait combined question recommendation method and system |
| CN111460128B (en) * | 2019-11-14 | 2023-09-12 | 临沂市拓普网络股份有限公司 | Computerized self-adaptive testing method based on cognitive diagnosis |
| CN111310463B (en) * | 2020-02-10 | 2022-08-05 | 清华大学 | Test question difficulty estimation method and device, electronic equipment and storage medium |
| CN111415089B (en) * | 2020-03-20 | 2021-07-06 | 读书郎教育科技有限公司 | Online flat learning result early warning method based on learning degree analysis |
| CN111708951B (en) * | 2020-06-23 | 2023-06-09 | 广东讯飞启明科技发展有限公司 | Test question recommending method and device |
| CN112001656A (en) * | 2020-09-01 | 2020-11-27 | 北京弘远博学科技有限公司 | Method for carrying out training course recommendation pertinently based on employee historical training information |
| CN112232610B (en) * | 2020-12-18 | 2021-03-19 | 北京几原科技有限责任公司 | Personalized question recommendation method and system using machine learning model |
| CN112749336A (en) * | 2021-01-11 | 2021-05-04 | 徐州金林人工智能科技有限公司 | Online exercise personalized recommendation system based on machine learning algorithm |
| CN113377942A (en) * | 2021-07-12 | 2021-09-10 | 北京乐学帮网络技术有限公司 | Test paper generation method and device, computer equipment and storage medium |
| CN113239180A (en) * | 2021-07-13 | 2021-08-10 | 北京神州泰岳智能数据技术有限公司 | Learning path generation method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1516859A (en) * | 2001-04-20 | 2004-07-28 | 教育考试服务中心 | Latent property diagnosing procedure |
| CN101739855A (en) * | 2008-11-07 | 2010-06-16 | 北京宣爱智能模拟技术有限公司 | Automobilism network personalized teaching system and learning method thereof |
| CN101944122A (en) * | 2010-09-17 | 2011-01-12 | 浙江工商大学 | Incremental learning-fused support vector machine multi-class classification method |
| CN102194344A (en) * | 2011-06-02 | 2011-09-21 | 广州良师益友教育软件有限公司 | Test question generation system and implementation method thereof |
| KR20130082992A (en) * | 2011-12-26 | 2013-07-22 | 두산동아 주식회사 | Apparatus and method for recommending custom-made test on demand individual peculiarities using prerequisite and following logic |
| CN103577507A (en) * | 2012-08-10 | 2014-02-12 | 俞晓鸿 | Intelligent question bank system with real-time detection and self-adaptive evolution mechanism and method |
| CN103870463A (en) * | 2012-12-10 | 2014-06-18 | 中国电信股份有限公司 | Method and system for selecting test subjects |
| CN103927704A (en) * | 2014-04-01 | 2014-07-16 | 深圳中科教育考试服务有限公司 | Examination paper analysis reporting system and method |
| CN103942993A (en) * | 2014-03-17 | 2014-07-23 | 深圳市承儒科技有限公司 | Self-adaptive online assessment system and method based on IRT |
| CN104239969A (en) * | 2014-09-04 | 2014-12-24 | 上海合煦信息科技有限公司 | Evaluation and problem recommendation system for individualized education |
-
2015
- 2015-08-03 CN CN201510481754.8A patent/CN106407237B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1516859A (en) * | 2001-04-20 | 2004-07-28 | 教育考试服务中心 | Latent property diagnosing procedure |
| CN101739855A (en) * | 2008-11-07 | 2010-06-16 | 北京宣爱智能模拟技术有限公司 | Automobilism network personalized teaching system and learning method thereof |
| CN101944122A (en) * | 2010-09-17 | 2011-01-12 | 浙江工商大学 | Incremental learning-fused support vector machine multi-class classification method |
| CN102194344A (en) * | 2011-06-02 | 2011-09-21 | 广州良师益友教育软件有限公司 | Test question generation system and implementation method thereof |
| KR20130082992A (en) * | 2011-12-26 | 2013-07-22 | 두산동아 주식회사 | Apparatus and method for recommending custom-made test on demand individual peculiarities using prerequisite and following logic |
| CN103577507A (en) * | 2012-08-10 | 2014-02-12 | 俞晓鸿 | Intelligent question bank system with real-time detection and self-adaptive evolution mechanism and method |
| CN103870463A (en) * | 2012-12-10 | 2014-06-18 | 中国电信股份有限公司 | Method and system for selecting test subjects |
| CN103942993A (en) * | 2014-03-17 | 2014-07-23 | 深圳市承儒科技有限公司 | Self-adaptive online assessment system and method based on IRT |
| CN103927704A (en) * | 2014-04-01 | 2014-07-16 | 深圳中科教育考试服务有限公司 | Examination paper analysis reporting system and method |
| CN104239969A (en) * | 2014-09-04 | 2014-12-24 | 上海合煦信息科技有限公司 | Evaluation and problem recommendation system for individualized education |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106407237A (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407237B (en) | Online learning test question recommendation method and system | |
| Yang et al. | Predicting students' academic performance using multiple linear regression and principal component analysis | |
| Gunesekera et al. | The role of usability on e-learning user interactions and satisfaction: a literature review | |
| Al-Hmouz et al. | Modeling and simulation of an adaptive neuro-fuzzy inference system (ANFIS) for mobile learning | |
| CN110704732B (en) | Cognitive diagnosis based time-sequence problem recommendation method and device | |
| AlHamad | Acceptance of E-learning among university students in UAE: A practical study | |
| Kubricht et al. | Probabilistic Simulation Predicts Human Performance on Viscous Fluid-Pouring Problem. | |
| US20150154564A1 (en) | Weighted evaluation comparison | |
| CN109919252A (en) | The method for generating classifier using a small number of mark images | |
| CN111680216B (en) | Test question recommendation method, system, medium and equipment | |
| Vilbergsdottir et al. | Assessing the reliability, validity and acceptance of a classification scheme of usability problems (CUP) | |
| Pupara et al. | An institution recommender system based on student context and educational institution in a mobile environment | |
| CN111523738A (en) | System and method for predicting learning effect based on user online learning behavior pattern | |
| Aryadoust | Application of evolutionary algorithm-based symbolic regression to language assessment: Toward nonlinear modeling | |
| CN108055533A (en) | A kind of subjective quality assessment method for panoramic video | |
| Ahmad et al. | Requirements engineering framework for human-centered artificial intelligence software systems | |
| Chen et al. | Recommendation system based on rule-space model of two-phase blue-red tree and optimized learning path with multimedia learning and cognitive assessment evaluation | |
| Gupta et al. | Usability evaluation of live auction portal | |
| Muñoz et al. | A computational model of learners achievement emotions using control-value theory | |
| CN113361780A (en) | Behavior data-based crowdsourcing tester evaluation method | |
| Vydia et al. | The selection of learning platforms to support learning using fuzzy multiple attribute decision making | |
| Aryadinata et al. | Analysis acceptance of use Internet banking and mobile banking, case study: Standart application in XYZ company | |
| CN114936281A (en) | Big data based test question dynamic classification method, device, equipment and storage medium | |
| CN115713441A (en) | Teaching quality evaluation method and system based on AHP-Fuzzy algorithm and neural network | |
| CN113919983A (en) | Test question portrait method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |