CN110413728B - Method, device, equipment and storage medium for recommending exercise problems - Google Patents
Method, device, equipment and storage medium for recommending exercise problems Download PDFInfo
- Publication number
- CN110413728B CN110413728B CN201910535204.8A CN201910535204A CN110413728B CN 110413728 B CN110413728 B CN 110413728B CN 201910535204 A CN201910535204 A CN 201910535204A CN 110413728 B CN110413728 B CN 110413728B
- Authority
- CN
- China
- Prior art keywords
- practice
- candidate
- target knowledge
- value
- learner
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 53
- 238000012549 training Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000002596 correlated effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application relates to the field of big data, and provides a method, a device, equipment and a storage medium for recommending exercises, wherein the method comprises the following steps: acquiring target knowledge points of candidate practice problems; determining an associated practice problem set of the candidate practice problems according to the target knowledge points to obtain a first historical accuracy of a learner when answering the associated practice problem set, wherein the first historical accuracy is stored in a database; acquiring a difficulty value corresponding to the target knowledge point, and calculating an absolute value of a difference between the capability value and the difficulty value; if the absolute value of the difference is smaller than or equal to a preset threshold value, marking the candidate practice problem as a recommended practice problem; and acquiring a plurality of recommended practice problems from the problem library, and pushing the recommended practice problems to a question answering interface of the learner. A plurality of recommended practice problems are obtained through comparison of the capability value and the difficulty value, and the recommended practice problems are recommended to a learner; and continuously updating the ability value of the learner relative to the knowledge points according to the accuracy of the questions of the learner, recommending the adaptive practice questions for the learner, and improving the learning efficiency of the learner.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for recommending exercise problems.
Background
The practice problem recommendation method provides accurate practice problem recommendation service for learners under the environment of massive educational data, and helps the learners to make up knowledge holes and improve cognition.
However, the conventional practice problem recommendation method only gives problem recommendation according to the problem making preference of the learner, so that practice problems recommended to the learner may be simple or difficult, and the learning efficiency of the learner and the experience of the practice problem recommendation service are reduced.
Disclosure of Invention
The application mainly aims to solve the technical problem that the prior practice problem recommendation method does not consider the mastering degree of a learner on knowledge points covered by practice problems, and easily recommends simple or difficult practice problems, and a plurality of recommended practice problems are obtained from a problem library by comparing a capability value with a difficulty value, and are recommended to the learner; according to the accuracy of the questions of the learner, the ability value of the learner relative to the knowledge points is continuously updated, and the difficulty of the recommended practice questions is gradually increased along with the improvement of the learning ability of the learner to the knowledge points, so that the learning ability of the learner to the knowledge points can be gradually and effectively improved in a circulating way when the learner does the practice exercises.
A method for recommending practice problems, comprising: obtaining target knowledge points in candidate practice problems, wherein the candidate practice problems are any practice problem in a problem base; determining an associated practice problem set of the candidate practice problems according to the target knowledge points, wherein the associated practice problem set comprises a plurality of associated practice problems, and the associated practice problems are practice problems covering the target knowledge points in the problem base; acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set; obtaining a capability value according to the first historical accuracy, wherein the capability value is used for evaluating the mastering capability of the learner on the target knowledge point; acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and marking the candidate practice problem as a recommended practice problem if the absolute value of the difference is smaller than or equal to a preset threshold value; pushing the recommended practice questions to a question answering interface of the learner.
Optionally, before the target knowledge points covered by the candidate practice problem are acquired, the method further comprises:
identifying the target knowledge points covered by the candidate practice problems; and carrying out association storage on the target knowledge points and the candidate practice problems.
Optionally, the determining the associated practice problem set of the candidate practice problems according to the target knowledge point includes:
acquiring knowledge points covered by a target practice problem in the problem base; the target exercise question is any exercise question in the question bank; matching the knowledge points covered by the target practice problem with the target knowledge points; if the matching is successful, the target practice problem is set as the associated practice problem.
Optionally, the identifying the target knowledge points covered by the candidate practice problem includes:
acquiring the text of the candidate practice problem; word segmentation is carried out on the text of the candidate practice problem to obtain a plurality of words; identifying the part of speech of each word, and screening candidate words from the plurality of words according to the part of speech of each word; and matching the candidate words with keywords corresponding to all knowledge points in a knowledge point set, and if the keywords corresponding to the candidate words are matched, determining the knowledge points corresponding to the keywords as the target knowledge points of the candidate practice problems.
Optionally, before the target knowledge points covered by the candidate practice problem are acquired, the method further comprises:
acquiring a second historical accuracy rate of the learner set stored in the database when the candidate practice problem and the associated practice problem set are answered; setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point; and setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point.
Optionally, the expression of the difficulty value is:
H＝(1-P 1 )*i；
wherein H is the difficulty value; p (P) 1 The accuracy corresponding to the target knowledge point is obtained; i is a constant, 0<i≤1。
Optionally, there are a plurality of the target knowledge points.
Calculating the absolute value of the difference between the capability value and the difficulty value, and if the absolute value of the difference is smaller than or equal to a preset threshold value, marking the candidate practice problem as a recommended practice problem, including: and respectively calculating absolute values of the differences between the capability values and the difficulty values corresponding to the target knowledge points, and marking the candidate practice problems as recommended practice problems if the absolute values of the differences are smaller than or equal to the threshold value.
Based on the same technical conception, the application also provides a practice problem recommending device, which comprises:
the receiving and transmitting module is used for acquiring target knowledge points in candidate practice problems, wherein the candidate practice problems are any practice problem in a problem base;
the processing module is used for determining an associated practice problem set of the candidate practice problems according to the target knowledge points, wherein the associated practice problems are practice problems covering the target knowledge points in the problem base, and the number of the associated practice problems is at least two; acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set; obtaining a capability value according to the first historical accuracy, wherein the capability value is used for evaluating the mastering capability of the learner on the target knowledge point; acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and marking the candidate practice problem as a recommended practice problem if the absolute value of the difference is smaller than or equal to a preset threshold value; pushing the recommended practice questions to a question answering interface of the learner.
Optionally, the processing module is further configured to identify the target knowledge points covered by the candidate practice problems; and carrying out association storage on the target knowledge points and the candidate practice problems.
Optionally, the processing module is specifically configured to obtain knowledge points covered by the target practice problem in the problem base; the target exercise question is any exercise question in the question bank; matching the knowledge points covered by the target practice problem with the target knowledge points; if the matching is successful, the target practice problem is set as the associated practice problem.
Optionally, the processing module is specifically configured to obtain a text of the candidate practice problem; word segmentation is carried out on the text of the candidate practice problem to obtain a plurality of words; identifying the part of speech of each word, and screening candidate words from the plurality of words according to the part of speech of each word; and matching the candidate words with keywords corresponding to all knowledge points in a knowledge point set, and if the keywords corresponding to the candidate words are matched, determining the knowledge points corresponding to the keywords as the target knowledge points of the candidate practice problems.
Optionally, the processing module is further configured to obtain, by using the obtaining module, a second historical accuracy of the learner set stored in the database when answering the candidate practice problem and the associated practice problem set; setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point; and setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point.
Optionally, the expression of the difficulty value is:
H＝(1-P 1 )*i；
wherein H is the difficulty value; p (P) 1 The accuracy corresponding to the target knowledge point is obtained; i is a constant, 0<i≤1。
Optionally, there are a plurality of the target knowledge points. The processing module is specifically configured to calculate absolute values of the differences between the capability values and the difficulty values corresponding to the target knowledge points, and if the absolute values of the differences are less than or equal to the threshold value, mark the candidate practice problem as the recommended practice problem.
Based on the same technical concept, the application also provides computer equipment, which comprises a transceiver, a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps in the practice problem recommending method.
Based on the same technical idea, the present application also provides a storage medium storing computer readable instructions, which when executed by one or more processors, cause the one or more processors to perform the steps in the practice problem recommendation method as described above.
The application has the beneficial effects that: acquiring a plurality of recommended practice problems from a problem library through comparing the capability value with the difficulty value, and recommending the recommended practice problems to a learner; according to the accuracy of the questions of the learner, the ability value of the learner relative to the knowledge points is continuously updated, and the difficulty of the recommended practice questions is gradually increased along with the improvement of the learning ability of the learner to the knowledge points, so that the learning ability of the learner to the knowledge points can be gradually and effectively improved in a circulating way when the learner does the practice exercises.
Drawings
FIG. 1 is a flowchart of a method for recommending exercise problems according to an embodiment of the present application.
FIG. 2 is a schematic diagram of a device for recommending exercise problems according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, procedures, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, procedures, steps, operations, elements, components, and/or groups thereof.
FIG. 1 is a flowchart of a method for recommending exercise problems according to some embodiments of the present application, wherein the method is performed by an exercise problem recommending device, which may be an intelligent device such as a computer or a mobile phone, and as shown in FIG. 1, the method may include the following steps S1-S4:
s1, acquiring target knowledge points in the candidate practice problems.
The candidate exercise question is any exercise question in the question bank. The target knowledge points are knowledge points covered by the candidate practice problems.
The practice problem in the question bank covers a plurality of knowledge points in the knowledge point set.
The set of knowledge points includes knowledge points in a knowledge unit.
The knowledge unit may be 1 subject or 1 chapter of a subject, etc. For example, university mathematics are divided into linear algebra, complex function, probability theory, etc., and if each subject is considered to be 1 unit, each subject is 1 of the knowledge units. Similarly, there are many chapters in each subject, and if each chapter of a subject is regarded as 1 unit, each chapter is 1 of the knowledge units.
There may be multiple knowledge points covered by 1 practice problem, some are knowledge points in the knowledge point set, and some are not. And marking the knowledge points covered by the practice problem and belonging to the knowledge point set as target knowledge points of the practice problem.
In some embodiments, prior to step S1, the method further comprises the steps of S011-S012:
s011, acquiring the target knowledge points covered by the candidate practice problems.
In some embodiments, step S011 includes the following steps S0111-S0114:
s0111, acquiring the text of the candidate practice problem.
Text refers to a representation of a written language, typically a sentence or a combination of sentences, having a complete, systematic meaning (Message).
S0112, word segmentation is carried out on the text of the candidate practice problem, and a plurality of words are obtained.
Word segmentation is the process of recombining a sequence of consecutive words into a sequence of words according to a certain specification.
S0113, identifying the part of speech of each word, and screening candidate words from the plurality of words according to the part of speech of each word.
Parts of speech refers to the feature of a word as the basis for dividing the parts of speech. Words obtained after text word segmentation may be nouns, verbs, adjectives, pronouns, graduated words, prepositions and the like. The words with different parts of speech contain different information, such as pronouns, graduated words and prepositions, do not generally contain knowledge point information of practice problems, and have no effect on analyzing knowledge points of practice problems, and the knowledge point information of practice problems is mostly contained in nouns, verbs and the like. Therefore, the application screens words which easily contain knowledge point information of practice problems from the words according to the parts of speech as candidate words.
In some embodiments, step S0113 includes the steps of: and identifying whether the word is a noun or a verb through a part-of-speech identifier, and if the word is the noun or the verb, marking the word as the candidate word.
In general, the examination points of practice problems are usually presented in the form of nouns, and secondly, in the form of verbs, such as photosynthesis, literature review, electromagnetic induction and the like, the nouns are mostly proper nouns, and the examination points have higher recognition degree and can be accurately mapped to corresponding knowledge points. Therefore, the application identifies nouns in the exercise problem text, determines the nouns as the candidate words, reduces the identification target, and reduces the operation amount of the matching work of the candidate words.
And S0114, matching the candidate word with the keywords corresponding to all the knowledge points in the knowledge point set, and if the keywords corresponding to the candidate word are matched, determining the knowledge point corresponding to the keywords as the target knowledge point of the candidate practice problem.
S012, the target knowledge points and the candidate practice exercises are stored in a correlated mode.
In the application, the target knowledge points of each practice problem in the problem library are identified in advance, and the identified target knowledge points are associated with the practice problem and stored. The practice problem may cover 1 or more target knowledge points. Thus, a target knowledge point associated with the practice problem can be determined based on the practice problem.
It will be appreciated that the target knowledge points may be included in the candidate exercises or in other exercises in the question bank. And setting all the exercises (including the candidate exercises) covering the target knowledge point in the question bank as the associated exercises.
S2, determining an associated practice problem set of the candidate practice problems according to the target knowledge points, and acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set; and obtaining a capability value according to the first historical accuracy rate.
The associated exercise questions comprise at least two associated exercise questions, and the associated exercise questions are exercise questions covering the target knowledge points in the question bank. The ability value is used to evaluate the learner's ability to grasp the target knowledge point. The learner is any one of a set of learners.
In some embodiments, in step S2, the obtaining the capability value according to the first historical accuracy rate specifically includes: setting the first historical accuracy rate to a capability value.
In some embodiments, the capability value is expressed as:
C＝P 2 (1)
wherein C is the capability value; p (P) 2 For a first historical accuracy of the learner in answering the set of associated practice problems.
The learner's mastery of the knowledge points can be effectively evaluated by means of the first historical accuracy of the learner in answering the associated exercise problem set. The associated practice problem set is equivalent to a test paper for examining the grasping ability of a learner to a target knowledge point, and the higher the first historical accuracy of the learner in answering the associated practice problem set, the higher the grasping condition of the learner to the knowledge point is.
After learning the knowledge units corresponding to the target knowledge points, the learner has a certain grasp on the target knowledge points, and at this time, the practice problem recommending device recommends a plurality of preset primary practice problems easy to answer to the learner so as to examine the grasp condition of the learner on the target knowledge points. The practice problem recommending device takes the accuracy rate of the learner when answering all primary practice problems as an initial first historical accuracy rate, and obtains an initial capability value according to the first historical accuracy rate. The practice problem recommendation device stores the initial capability value in a database. And, the practice problem recommending device updates the ability value in the database in real time according to the accuracy of the learner in the process of answering the associated practice problem set in the future, so as to keep the accuracy of evaluating the grasping ability of the learner to the target knowledge point.
The ability value is positively correlated to a first historical accuracy of the learner in answering each of the associated set of practice problems.
The learner may have trained the associated practice problem of the candidate practice problem prior to answering the candidate practice problem. The first historical accuracy of the learner in answering the associated practice problem can reflect the mastering condition of the learner on the target knowledge point. That is, the higher the first historical accuracy of the learner in answering the associated practice problems, the higher the grasping degree of the target knowledge point of the learner.
Optionally, the ability value is also positively correlated with the progress of a course that the learner has learned in relation to the target knowledge point.
The lesson learned by the learner may include content related to the target knowledge point, such that the learner has had a certain grasp of the target knowledge point before doing exercises. In general, the more courses that the learner has learned in relation to the target knowledge point, the higher the learner's level of mastery of the target knowledge point.
In some embodiments, in step S2, the determining the associated practice problem set of the candidate practice problem according to the target knowledge point specifically includes:
acquiring knowledge points covered by a target practice problem in the problem base; the target exercise question is any exercise question in the question bank; matching the knowledge points covered by the target practice problem with the target knowledge points; if the matching is successful, setting the target practice problem as the associated practice problem, and finally obtaining the associated practice problem set.
S3, acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and marking the candidate practice problem as a recommended practice problem if the absolute value of the difference is smaller than or equal to a preset threshold value.
The recommended practice questions are practice questions suitable for the learner to answer.
The threshold is used to measure how hard the target knowledge point is relative to the learner. If the absolute value of the difference is smaller than or equal to a preset threshold value, the deviation between the ability value and the difficulty value is smaller, the difficulty of the target knowledge point is moderate relative to the learner, and the target knowledge point is suitable for the learner to answer. In a state that the absolute value of the difference is smaller than or equal to a preset threshold value, when the capability value is larger than the difficulty value, the target knowledge point is slightly difficult for the learner, and when the capability value is smaller than the difficulty value, the target knowledge point is slightly simple for the learner. Therefore, the difficulty value and the ability value effectively screen a recommended practice problem set with moderate difficulty relative to the learner so as to reasonably recommend practice problems for the learner.
In some embodiments, before step S1, after step S013, the following steps S031-S032 are further included:
s031, obtaining a second historical accuracy rate of the learner set stored in the database when the candidate practice problem and the associated practice problem set are answered; and setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point.
The practice problem recommending device records the answer result of the practice problem done by each learner. And counting a second historical accuracy rate of the learner set when the candidate practice problems and each associated practice problem set are answered, and obtaining the accuracy rate of the learner set when the target knowledge points are answered in the past. Because the candidate practice problem or the associated problem is answered, the covered target knowledge points are also answered. The accuracy of the target knowledge point is the ratio of the total number of times the target knowledge point has been answered in the past to the total number of times the target knowledge point has been answered in the past.
S032, setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point.
It can be appreciated that the higher the accuracy corresponding to the target knowledge point, the lower the difficulty of the target knowledge point, and therefore, the difficulty value is inversely related to the accuracy corresponding to the target knowledge point. The practice problem recommending device stores the difficulty value in a database. Along with the increasing number of associated practice problems made by the learner set, the accuracy rate of the learner set for answering the associated practice problems can be changed continuously, namely the difficulty value of the target knowledge point can be changed continuously, and the practice problem recommending equipment updates the difficulty value of the target knowledge point in real time according to the second historical accuracy rate so as to ensure the accuracy of the difficulty value of the target knowledge point.
In some embodiments, the difficulty value is expressed as:
H＝(1-P 1 )*i； (2)
wherein H is the difficulty value; p (P) 1 The accuracy corresponding to the target knowledge point is obtained; i is a constant, 0<i≤1。
It should be explained that i is used to adjust the difficulty value H. Because, in some cases, the learner's mastering degree of the knowledge points is insufficient to solve the knowledge points with larger difficulty, but the learner will often do ' pull-up ' training, i.e. do some exercises with larger difficulty, so as to improve the mastering ability of the learner on the knowledge points. Therefore, the application can properly reduce the difficulty value H by adopting the constant i smaller than 1, and properly recommend the problem that the actual difficulty is slightly higher than the mastering degree of the learner for the learner, so as to achieve the aim of 'pulling up' training.
For example, assuming i=95%, if the accuracy corresponding to the target knowledge point is 75%, the difficulty value corresponding to the target knowledge point is set to (1-75%) ×95%; and if the accuracy corresponding to the target knowledge point is 20%, setting the difficulty value corresponding to the target knowledge point to be (1-20%) 95%.
In the above embodiment, the capability value H in expression (2) and the difficulty value C in expression (1) are both values in the [0,1] interval, and correspondingly, the absolute value of the difference is also a value in the [0,1] interval. The ability value and the difficulty value are obtained according to the accuracy of questions made by a learner, and the ability value and the difficulty value have good objectivity and authenticity, and can objectively screen out proper practice questions for the learner to answer.
For example, assuming that the threshold j=5%, the ability value C of the learner is 70%; and assuming i=100%, the accuracy P corresponding to the target knowledge point 1 20%, thus, according to expression (2), the difficulty value H is 80%; since |c-h|= |70% -80% |=10%>J, that is, the absolute value of the difference between the ability value C and the difficulty value H exceeds the threshold J, and thus it is determined that the candidate practice problem is not suitable for the learner to answer. In this example, the accuracy P corresponding to the target knowledge point 1 Only 20%, it can be seen that the target knowledge point is relatively difficult for most learners, who have the ability value C of 70%, with an ability much greater than the accuracy P 1 Indicating that the learner's ability to grasp the target knowledge point is much higher than most learners, even so, due to |C-H|>J, the difficulty of the candidate exercise questions exceeds a preset interval range relative to the learner, so that more answering time of the learner is easily consumed, and the candidate exercise questions are not reimbursed, and therefore the candidate exercise questions are judged to be unsuitable for the learner to answer. Similarly, if the difficulty of the candidate practice problem is too simple relative to the learner, it is also unsuitable for the learner to continue to answer at present, because the too simple practice problem has limited improvement on the learner's ability, wasting the learner's time.
In some embodiments, prior to step S1, the following step S031 is included:
s031, establishing a difficulty value sequence by taking difficulty values corresponding to all knowledge points in the knowledge point set as elements; and establishing a capability value sequence by taking capability values of the learner relative to all knowledge points in the knowledge point set as elements.
And each element in the difficulty value sequence corresponds to each element in the capability value sequence one by one.
For example, assuming that the number k=5 of knowledge points in the knowledge point set of the knowledge unit is the linear algebra in university mathematics, the capability value sequence α_i= (0.2,0.3,0.8,0.2,0) of the learner with the number i is sampled according to the previous problem making result of the learner, wherein each value represents the grasping degree of the learner on each knowledge point, and the larger the corresponding value of the knowledge point is, the higher the grasping degree of the learner on the knowledge point is. Assume that a difficulty value sequence q_j= (0.4,0,0.6,0.2,0) of a practice problem with the number j, wherein each numerical value respectively represents the difficulty of each knowledge point in the practice problem, and the larger the numerical value corresponding to the knowledge point is, the higher the difficulty is. In the difficulty value sequence q_j, the knowledge point with the difficulty value of 0 indicates that the practice problem with the number of j is not covered by the knowledge point. That is, the practice problem with the number j covers 3 knowledge points in the knowledge point set, namely, the practice problem with the number j has 3 target knowledge points, and the difficulty values are respectively 0.4, 0.6 and 0.2.
In some embodiments, the target knowledge points in the candidate practice problem are multiple. And extracting the difficulty value corresponding to each target knowledge point in the candidate practice problem from the difficulty value sequence. And extracting each capability value corresponding to each target knowledge point in the candidate practice problem from the capability value sequence. Step S3 comprises the steps of: and respectively calculating absolute values of the differences between the capability values and the difficulty values corresponding to the target knowledge points, and marking the candidate practice problems as recommended practice problems if the absolute values of the differences are smaller than or equal to the threshold value.
S4, acquiring a plurality of recommended practice problems from the problem library, and pushing the recommended practice problems to a question answering interface of the learner.
In the above embodiment, by comparing the ability value and the difficulty value, a plurality of recommended practice problems are obtained from a problem base, and the recommended practice problems are recommended to the learner; according to the accuracy of the questions of the learner, the ability value of the learner relative to the knowledge points is continuously updated, and along with the improvement of the learning ability of the learner on the knowledge points, the difficulty of the recommended practice exercises is gradually improved, so that the learning ability of the learner on the knowledge points can be gradually and effectively improved in a circulating way when the learner does the exercise training.
Based on the same technical conception, the application also provides a practice problem recommending device, which comprises a receiving and transmitting module 1 and a processing module 2 as shown in fig. 2. The processing module 2 is configured to control an information acquisition operation of the transceiver module 1.
The receiving and transmitting module 1 is configured to select a target knowledge point in a training problem, where the training problem candidate is any training problem in a problem base.
The processing module 2 is configured to determine, according to the target knowledge point, an associated practice problem set of the candidate practice problem, where the associated practice problem is a practice problem covering the target knowledge point in the problem base, and the number of the associated practice problems is at least two; acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set; obtaining a capability value according to the first historical accuracy, wherein the capability value is used for evaluating the mastering capability of the learner on the target knowledge point; acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and marking the candidate practice problem as a recommended practice problem if the absolute value of the difference is smaller than or equal to a preset threshold value; pushing the recommended practice questions to a question answering interface of the learner.
In some embodiments, the processing module 2 is further configured to identify the target knowledge points covered by the candidate practice problem; and carrying out association storage on the target knowledge points and the candidate practice problems.
In some embodiments, the processing module 2 is specifically configured to obtain knowledge points covered by the target practice problem in the problem base; the target exercise question is any exercise question in the question bank; matching the knowledge points covered by the target practice problem with the target knowledge points; if the matching is successful, the target practice problem is set as the associated practice problem.
In some embodiments, the processing module 2 is specifically configured to obtain the text of the candidate practice problem; word segmentation is carried out on the text of the candidate practice problem to obtain a plurality of words; identifying the part of speech of each word, and screening candidate words from the plurality of words according to the part of speech of each word; and matching the candidate words with keywords corresponding to all knowledge points in a knowledge point set, and if the keywords corresponding to the candidate words are matched, determining the knowledge points corresponding to the keywords as the target knowledge points of the candidate practice problems.
In some embodiments, the processing module 2 is further configured to obtain, using the obtaining module 1, a second historical accuracy of the learner set stored in the database when answering the candidate practice problem and the associated practice problem set; setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point; and setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point.
In some embodiments, the difficulty value is expressed as:
H＝(1-P 1 )*i；
wherein H is the difficulty value; p (P) 1 The accuracy corresponding to the target knowledge point is obtained; i is a constant, 0<i≤1。
In some embodiments, the target knowledge points are multiple. The processing module 2 is specifically configured to calculate absolute values of the differences between the capability values and the difficulty values corresponding to the target knowledge points, and if the absolute values of the differences are less than or equal to the threshold, mark the candidate practice problem as the recommended practice problem.
In the above embodiment, by comparing the ability value and the difficulty value, a plurality of recommended practice problems are obtained from a problem base, and the recommended practice problems are recommended to the learner; according to the accuracy of the questions of the learner, the ability value of the learner relative to the knowledge points is continuously updated, and along with the improvement of the learning ability of the learner on the knowledge points, the difficulty of the recommended practice exercises is gradually improved, so that the learning ability of the learner on the knowledge points can be gradually and effectively improved in a circulating way when the learner does the exercise training.
Based on the same technical concept, the present application also provides a computer device, as shown in fig. 3, which includes a transceiver 31, a processor 32, and a memory 33, where the memory 33 stores computer readable instructions, and the computer readable instructions when executed by the processor 32 cause the processor to execute the steps of the practice problem recommendation method in the foregoing embodiments.
The corresponding physical device of the transceiver module 1 shown in fig. 2 is the transceiver 31 shown in fig. 3, and the transceiver 31 can implement part or all of the functions of the transceiver module 1, or implement the same or similar functions as the transceiver module 1.
The corresponding physical device of the processing module 2 shown in fig. 2 is the processor 32 shown in fig. 3, and the processor 32 can implement part or all of the functions of the processing module 2, or implement the same or similar functions as the processing module 2.
Based on the same technical concept, the present application also provides a storage medium storing computer readable instructions, which when executed by one or more processors, cause the one or more processors to perform the steps of the practice problem recommendation method in the above embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM), comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server or a network device, etc.) to perform the method according to the embodiments of the present application.
While the embodiments of the present application have been described above with reference to the drawings, the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many modifications may be made thereto by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the appended claims, which are to be accorded the full scope of the present application as defined by the following description and drawings, or by any equivalent structures or equivalent flow changes, or by direct or indirect application to other relevant technical fields.
Claims (8)
1. A practice problem recommendation method, comprising:
obtaining target knowledge points in candidate practice problems, wherein the candidate practice problems are any practice problem in a problem base;
determining an associated practice problem set of the candidate practice problems according to the target knowledge points, wherein the associated practice problem set comprises a plurality of associated practice problems, and the associated practice problems are practice problems covering the target knowledge points in the problem base;
acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set;
obtaining a capability value according to the first historical accuracy, wherein the capability value is used for evaluating the mastering capability of the learner on the target knowledge point;
acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and if the absolute value of the difference is smaller than or equal to a preset threshold value, marking the candidate exercise question as a recommended exercise question, wherein the difficulty value is inversely related to the accuracy of the target knowledge point, and the accuracy of the target knowledge point is a ratio of the total number of times the target knowledge point has been answered to the total number of times the target knowledge point has been answered in the past;
pushing the recommended practice questions to a question answering interface of the learner;
before the target knowledge points in the candidate practice problems are obtained, the method further comprises:
acquiring a second historical accuracy rate of the learner set stored in the database when the candidate practice problem and the associated practice problem set are answered;
setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point;
setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point;
the expression of the difficulty value is as follows:
H=(1-P 1 )*i；
wherein H is the difficulty value; p (P) 1 The accuracy corresponding to the target knowledge point is obtained; i is a constant, 0<i≤1。
2. The method for recommending exercise problems according to claim 1, wherein,
before the target knowledge points in the candidate practice problems are obtained, the method further comprises:
identifying the target knowledge points covered by the candidate practice problems;
and carrying out association storage on the target knowledge points and the candidate practice problems.
3. The method for recommending exercise problems according to claim 2, wherein,
the determining the associated practice problem set of the candidate practice problems according to the target knowledge points comprises the following steps:
acquiring knowledge points covered by a target practice problem in the problem base; the target exercise question is any exercise question in the question bank;
matching the knowledge points covered by the target practice problem with the target knowledge points;
if the matching is successful, setting the target practice problem as the associated practice problem, and finally obtaining the associated practice problem set.
4. The method for recommending exercise problems according to claim 2, wherein,
the identifying the target knowledge points covered by the candidate practice problems comprises:
acquiring the text of the candidate practice problem;
word segmentation is carried out on the text of the candidate practice problem to obtain a plurality of words;
identifying the part of speech of each word, and screening candidate words from the plurality of words according to the part of speech of each word;
and matching the candidate words with keywords corresponding to all knowledge points in a knowledge point set, and if the keywords corresponding to the candidate words are matched, determining the knowledge points corresponding to the keywords as the target knowledge points of the candidate practice problems.
5. The method for recommending exercise problems according to claim 1, wherein,
the target knowledge points are multiple;
calculating the absolute value of the difference between the capability value and the difficulty value, and if the absolute value of the difference is smaller than or equal to a preset threshold value, marking the candidate practice problem as a recommended practice problem, including:
and respectively calculating absolute values of the differences between the capability values and the difficulty values corresponding to the target knowledge points, and marking the candidate practice problems as recommended practice problems if the absolute values of the differences are smaller than or equal to the threshold value.
6. A practice problem recommendation device, comprising:
the receiving and transmitting module is used for acquiring target knowledge points in candidate practice problems, wherein the candidate practice problems are any practice problem in a problem base;
the processing module is used for determining an associated practice problem set of the candidate practice problems according to the target knowledge points, wherein the associated practice problem set comprises a plurality of associated practice problems, and the associated practice problems are practice problems covering the target knowledge points in the problem base; acquiring a first historical accuracy rate of a learner stored in a database when answering the associated practice problem set; obtaining a capability value according to the first historical accuracy, wherein the capability value is used for evaluating the mastering capability of the learner on the target knowledge point; acquiring a difficulty value corresponding to the target knowledge point, calculating an absolute value of a difference between the capability value and the difficulty value, and if the absolute value of the difference is smaller than or equal to a preset threshold value, marking the candidate exercise question as a recommended exercise question, wherein the difficulty value is inversely related to the accuracy of the target knowledge point, and the accuracy of the target knowledge point is a ratio of the total number of times the target knowledge point has been answered to the total number of times the target knowledge point has been answered in the past; pushing the recommended practice questions to a question answering interface of the learner;
the processing module is further used for obtaining a second historical accuracy rate of the learner set stored in the database when the candidate practice problems and the associated practice problem set are answered; setting the second historical accuracy rate as the accuracy rate corresponding to the target knowledge point; setting the difficulty value corresponding to the target knowledge point according to the accuracy corresponding to the target knowledge point; the expression of the difficulty value is as follows: h= (1-P1) i; wherein H is the difficulty value; p1 is the accuracy corresponding to the target knowledge point; i is a constant, 0<i is less than or equal to 1.
7. A computer device comprising a transceiver, a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the practice problem recommendation method according to any one of claims 1 to 5.
8. A storage medium storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps in the practice problem recommendation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910535204.8A CN110413728B (en) | 2019-06-20 | 2019-06-20 | Method, device, equipment and storage medium for recommending exercise problems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910535204.8A CN110413728B (en) | 2019-06-20 | 2019-06-20 | Method, device, equipment and storage medium for recommending exercise problems |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110413728A CN110413728A (en) | 2019-11-05 |
| CN110413728B true CN110413728B (en) | 2023-10-27 |
Family
ID=68359402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910535204.8A Active CN110413728B (en) | 2019-06-20 | 2019-06-20 | Method, device, equipment and storage medium for recommending exercise problems |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110413728B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751867B (en) * | 2019-11-27 | 2021-06-01 | 上海松鼠课堂人工智能科技有限公司 | English teaching system |
| CN111090809A (en) * | 2019-12-20 | 2020-05-01 | 广州摩翼信息科技有限公司 | Topic recommendation method and device, computer equipment and storage medium |
| CN111275091B (en) * | 2020-01-16 | 2024-05-10 | 平安科技（深圳）有限公司 | Text conclusion intelligent recommendation method and device and computer readable storage medium |
| CN111582694B (en) * | 2020-04-29 | 2023-08-08 | 腾讯科技（深圳）有限公司 | Learning evaluation method and device |
| CN111914176B (en) * | 2020-08-07 | 2023-10-27 | 腾讯科技（深圳）有限公司 | Question recommendation method and device |
| CN114913729B (en) * | 2021-02-09 | 2023-06-20 | 广州视源电子科技股份有限公司 | Question selecting method, device, computer equipment and storage medium |
| CN113934840B (en) * | 2021-11-01 | 2022-04-01 | 东北师范大学 | Covering heuristic quantity sensing exercise recommendation method |
| CN114048377B (en) * | 2021-11-08 | 2024-05-03 | 网易有道信息技术（北京）有限公司 | Question recommending method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006285299A (en) * | 2005-03-31 | 2006-10-19 | Kddi Corp | Ability filter type content recommendation device, method and program |
| CN106407237A (en) * | 2015-08-03 | 2017-02-15 | 科大讯飞股份有限公司 | An online study test question recommendation method and system |
| CN107992595A (en) * | 2017-12-12 | 2018-05-04 | 广东小天才科技有限公司 | A kind of learning Content recommends method, apparatus and smart machine |
| CN108491451A (en) * | 2018-02-27 | 2018-09-04 | 北京云知学科技有限公司 | A kind of English reads article and recommends method, apparatus, electronic equipment and storage medium |
| CN108647211A (en) * | 2018-05-17 | 2018-10-12 | 宁波薄言信息技术有限公司 | A kind of method for pushing of children for learning content |
| CN108932246A (en) * | 2017-05-24 | 2018-12-04 | 肖方良 | User's on-line study capability evaluation and topic recommended method and system |
| CN109360457A (en) * | 2018-09-03 | 2019-02-19 | 浙江学海教育科技有限公司 | A kind of topic method for pushing, storage medium and application system |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
-
2019
- 2019-06-20 CN CN201910535204.8A patent/CN110413728B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006285299A (en) * | 2005-03-31 | 2006-10-19 | Kddi Corp | Ability filter type content recommendation device, method and program |
| CN106407237A (en) * | 2015-08-03 | 2017-02-15 | 科大讯飞股份有限公司 | An online study test question recommendation method and system |
| CN108932246A (en) * | 2017-05-24 | 2018-12-04 | 肖方良 | User's on-line study capability evaluation and topic recommended method and system |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
| CN107992595A (en) * | 2017-12-12 | 2018-05-04 | 广东小天才科技有限公司 | A kind of learning Content recommends method, apparatus and smart machine |
| CN108491451A (en) * | 2018-02-27 | 2018-09-04 | 北京云知学科技有限公司 | A kind of English reads article and recommends method, apparatus, electronic equipment and storage medium |
| CN108647211A (en) * | 2018-05-17 | 2018-10-12 | 宁波薄言信息技术有限公司 | A kind of method for pushing of children for learning content |
| CN109360457A (en) * | 2018-09-03 | 2019-02-19 | 浙江学海教育科技有限公司 | A kind of topic method for pushing, storage medium and application system |
Non-Patent Citations (1)
| Title |
|---|
| 基于知识点层次图的个性化习题推荐算法;蒋昌猛;冯筠;孙霞;陈静;张蕾;冯宏伟;;计算机工程与应用(第10期);第234-240页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110413728A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110413728B (en) | Method, device, equipment and storage medium for recommending exercise problems | |
| US10741092B1 (en) | Application of high-dimensional linguistic and semantic feature vectors in automated scoring of examination responses | |
| CN112487139B (en) | Text-based automatic question setting method and device and computer equipment | |
| EP2956919A2 (en) | Language learning systems and methods | |
| US11507888B2 (en) | Training method and device for machine translation model and storage medium | |
| US11763174B2 (en) | Learning material recommendation method, learning material recommendation device, and learning material recommendation program | |
| CN111090809A (en) | Topic recommendation method and device, computer equipment and storage medium | |
| WO2006134759A1 (en) | Sentence evaluating device and sentence evaluating program | |
| WO2022170985A1 (en) | Exercise selection method and apparatus, and computer device and storage medium | |
| CN110910043A (en) | Analysis method of test paper information | |
| JP2022189908A (en) | Point rating support device, and control method and control program therefor | |
| CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
| WO2020074067A1 (en) | Automatic language proficiency level determination | |
| CN110765241B (en) | Super-outline detection method and device for recommendation questions, electronic equipment and storage medium | |
| CN110134945B (en) | Method, device, equipment and storage medium for identifying examination points of exercise | |
| CN111915224A (en) | Teaching evaluation system | |
| Lee et al. | Personalized item generation method for adaptive testing systems | |
| CN115050039A (en) | Automatic test paper analysis method, system, electronic device and storage medium | |
| CN112860983B (en) | Method, system, equipment and readable storage medium for pushing learning content | |
| Perez et al. | Implementation of a test constructor utilizing a calibrated item bank using 3PL-IRT model | |
| CN113539520A (en) | Method, device, computer equipment and storage medium for implementing inquiry session | |
| CN112598202A (en) | Test question difficulty evaluation method and device, storage medium and computing equipment | |
| CN111915227B (en) | Teaching evaluation data analysis method | |
| KR102412381B1 (en) | Learning contents evaluation apparatus, system, and operation method thereof for evaluating a problem based on the predicted correct answer probability for the added problem contents without solving experience | |
| US11423796B2 (en) | Interactive feedback based evaluation using multiple word cloud |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |