CN110413728A - Exercise recommended method, device, equipment and storage medium - Google Patents
Exercise recommended method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110413728A CN110413728A CN201910535204.8A CN201910535204A CN110413728A CN 110413728 A CN110413728 A CN 110413728A CN 201910535204 A CN201910535204 A CN 201910535204A CN 110413728 A CN110413728 A CN 110413728A
- Authority
- CN
- China
- Prior art keywords
- exercise
- knowledge point
- value
- candidate
- 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.)
- Granted
Links
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—Systems or methods specially adapted for 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (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
This application involves big data fields, provide exercise recommended method, device, equipment and storage medium, and method includes: the object knowledge point for obtaining candidate exercise;Determine that the association exercise set of the candidate exercise obtains the learner stored in database in the first history accuracy rate when being associated with exercise set of answering according to object knowledge point;Obtain the corresponding difficulty value of object knowledge point, the absolute value of the difference between computing capability value and difficulty value;If absolute value of the difference is less than or equal to preset threshold value, by candidate exercise labeled as recommendation exercise;Several are obtained from exam pool recommends exercise, the answer interface that exercise will be recommended to push to learner.Recommend exercise by compared with difficulty value, obtaining several to ability value, exercise will be recommended to recommend learner;Accuracy rate according to learner's answer constantly updates ability value of the learner relative to knowledge point, recommends the exercise adapted to for learner, improves the learning efficiency of learner.
Description
Technical field
This application involves field of computer technology more particularly to exercise recommended method, device, equipment and storage mediums.
Background technique
Exercise recommended method provides accurate exercise for learner and recommends clothes in the environment of magnanimity educational data
Business helps learner to make up knowledge loophole and improves cognition.
However, existing exercise recommended method provides exercise recommendation according only to the topic preference of doing of learner, it is learner
The exercise of recommendation may be partially simple or partially difficult, reduces the learning efficiency of learner and the experience to exercise recommendation service.
Summary of the invention
The main purpose of the application is that solving existing exercise recommended method does not consider learner to exercise institute
Cover the Grasping level of knowledge point, it is easy to the technical issues of recommending partially simple or hardly possible partially exercise out, by ability value
Compared with difficulty value, several being obtained from exam pool and recommends exercise, exercise will be recommended to recommend learner;According to study
The accuracy rate of person's answer constantly updates ability value of the learner relative to knowledge point, as learner grasps ability to knowledge point
Improve, the difficulty for the recommendation exercise recommended also steps up so that learner when doing Training of Exercises, follow it is progressive, can
With gradually, effectively improve learner to the grasp ability of knowledge point.
A kind of exercise recommended method, comprising: obtain the object knowledge point in candidate exercise, wherein the candidate white silk
Exercise is any exercise in exam pool;The association exercise collection of the candidate exercise is determined according to the object knowledge point
It closes, wherein association exercise set includes multiple association exercises, and the association is practiced covering the mesh in the entitled exam pool
Mark the exercise of knowledge point;Obtain first history of the learner stored in database when answering the association exercise set
Accuracy rate;Ability value is obtained according to the first history accuracy rate, wherein the ability value is for assessing the learner to institute
State the grasp ability of object knowledge point;The corresponding difficulty value of the object knowledge point is obtained, the ability value and the difficulty are calculated
Absolute value of the difference between angle value, if the absolute value of the difference is less than or equal to preset threshold value, by the candidate exercise
Labeled as recommendation exercise;The recommendation exercise is pushed to the answer interface of the learner.
Optionally, before the object knowledge point that the candidate exercise of the acquisition is covered, the method also includes:
Identify the object knowledge point that the candidate exercise is covered;By the object knowledge point and the candidate white silk
Exercise is associated storage.
Optionally, the association exercise set that the candidate exercise is determined according to the object knowledge point, comprising:
It obtains target practice in the exam pool and inscribes covered knowledge point;Appointing in the entitled exam pool of target practice
One exercise;Covered knowledge point is inscribed in the target practice to match with the object knowledge point;If successful match,
The association exercise is set by target practice topic.
Optionally, the object knowledge point that the identification candidate exercise is covered, comprising:
Obtain the text of the candidate exercise;The text of the candidate exercise is segmented, several lists are obtained
Word;The part of speech for identifying each word filters out candidate word from several described words according to the part of speech of each word;By the candidate
Word keyword corresponding with each knowledge point in knowledge point set is matched, if being matched to institute corresponding with the candidate word
Keyword is stated, then knowledge point corresponding to the keyword is determined as to the object knowledge point of the candidate exercise.
Optionally, before the object knowledge point that the candidate exercise of the acquisition is covered, the method also includes:
It obtains the learner stored in the database and is integrated into the answer candidate exercise and association practice
The second history accuracy rate when topic set;It is corresponding accurate that the second history accuracy rate is set as the object knowledge point
Rate;According to the corresponding accuracy rate of the object knowledge point, the corresponding difficulty value of the object knowledge point is set.
Optionally, the expression formula of the difficulty value are as follows:
H=(1-P1)*i;
Wherein, H is the difficulty value;P1For the corresponding accuracy rate of the object knowledge point;I is constant, 0 < i≤1.
Optionally, the object knowledge point has multiple.
The absolute value of the difference calculated between the ability value and the difficulty value, if the absolute value of the difference be less than or
Equal to preset threshold value, then by the candidate exercise labeled as recommendation exercise, comprising: calculate separately each object knowledge
The absolute value of the difference between the point corresponding ability value and the difficulty value, if each absolute value of the difference is respectively less than
Or be equal to the threshold value, then the candidate exercise is labeled as the recommendation exercise.
Based on the same technical idea, present invention also provides a kind of exercise recommendation apparatus, comprising:
Transceiver module, for obtaining the object knowledge point in candidate exercise, wherein in the candidate entitled exam pool of practice
Any exercise;
Processing module, for determining the association exercise set of the candidate exercise according to the object knowledge point,
In, the exercise for covering the object knowledge point in the entitled exam pool, the quantity of the association exercise are practiced in the association
At least two;It is accurate to obtain first history of the learner stored in database when answering the association exercise set
Rate;Ability value is obtained according to the first history accuracy rate, wherein the ability value is for assessing the learner to the mesh
Mark the grasp ability of knowledge point;The corresponding difficulty value of the object knowledge point is obtained, the ability value and the difficulty value are calculated
Between absolute value of the difference the candidate exercise is marked if the absolute value of the difference is less than or equal to preset threshold value
To recommend exercise;The recommendation exercise is pushed to the answer interface of the learner.
Optionally, processing module is also used to identify the object knowledge point that the candidate exercise is covered;It will be described
Object knowledge point and the candidate exercise are associated storage.
Optionally, processing module is specifically used for obtaining the knowledge point that target practice topic is covered in the exam pool;The mesh
Mark practices any exercise in the entitled exam pool;Covered knowledge point and the object knowledge are inscribed into the target practice
Point is matched;If successful match, the association exercise is set by target practice topic.
Optionally, processing module is specifically used for obtaining the text of the candidate exercise;To the text of the candidate exercise
This is segmented, several words are obtained;The part of speech for identifying each word, according to the part of speech of each word from several described words
Filter out candidate word;Candidate word keyword corresponding with each knowledge point in knowledge point set is matched, if matching
To the keyword corresponding with the candidate word, then knowledge point corresponding to the keyword is determined as the candidate white silk
The object knowledge point of exercise.
Optionally, processing module, which is also used to obtain the learner stored in the database using acquisition module, is integrated into work
Answer the second history accuracy rate when the candidate exercise and the association exercise set;By the second history accuracy rate
It is set as the corresponding accuracy rate of the object knowledge point;According to the corresponding accuracy rate of the object knowledge point, the target is set
The corresponding difficulty value in knowledge point.
Optionally, the expression formula of the difficulty value are as follows:
H=(1-P1)*i;
Wherein, H is the difficulty value;P1For the corresponding accuracy rate of the object knowledge point;I is constant, 0 < i≤1.
Optionally, the object knowledge point has multiple.Processing module is specifically used for calculating separately each object knowledge point
The absolute value of the difference between the corresponding ability value and the difficulty value, if each absolute value of the difference be respectively less than or
Equal to the threshold value, then the candidate exercise is labeled as the recommendation exercise.
Based on the same technical idea, present invention also provides a kind of computer equipments, including transceiver, memory and place
Device is managed, be stored with computer-readable instruction in the memory makes when the computer-readable instruction is executed by the processor
The processor is obtained to execute such as the step in above-mentioned exercise recommended method.
Based on the same technical idea, present invention also provides a kind of storage medium for being stored with computer-readable instruction,
When the computer-readable instruction is executed by one or more processors, so that one or more processors execute such as above-mentioned white silk
Step in exercise recommended method.
The application's by compared with difficulty value, obtaining ability value from exam pool several the utility model has the advantages that recommend to practice
Exercise will recommend exercise to recommend learner;Accuracy rate according to learner's answer constantly updates learner relative to knowledge
The ability value of point, as learner grasps the raising of ability to knowledge point, the difficulty for the recommendation exercise recommended also gradually is mentioned
Height so that learner when doing Training of Exercises, follow it is progressive, can gradually, effectively improve grasp of the learner to knowledge point
Ability.
Detailed description of the invention
Fig. 1 is the flow diagram of exercise recommended method in the embodiment of the present application.
Fig. 2 is the structural schematic diagram of exercise recommendation apparatus in the embodiment of the present application.
Fig. 3 is the structural schematic diagram of computer equipment in the embodiment of the present application.
Specific embodiment
It should be appreciated that specific embodiment described herein is not used to limit the application only to explain the application.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" also may include plural form.It is to be further understood that used in the description of the present application
Wording " comprising " refers to that there are the feature, program, step, operation, element and/or component, but it is not excluded that in the presence of or add
Add other one or more features, program, step, operation, element, component and/or their group.
Fig. 1 is a kind of flow chart of exercise recommended method in some embodiments of the application, the exercise recommended method
It is executed by exercise recommendation apparatus, exercise recommendation apparatus can be with smart machines such as computer or mobile phones, as shown in Figure 1, can wrap
Include following steps S1-S4:
Object knowledge point in S1, the candidate exercise of acquisition.
The candidate any exercise practiced in entitled exam pool.The object knowledge point is that the candidate exercise is contained
The knowledge point of lid.
Exercise in described exam pool covers several knowledge points in knowledge point set.
The knowledge point set includes the knowledge point in blocks of knowledge.
The blocks of knowledge can be 1 chapters and sections of 1 subject or section's purpose etc..For example, College Maths be divided into linear algebra,
The subjects such as complex function and probability theory, if each section is visually 1 unit, each subject is 1 blocks of knowledge.
Similarly, many chapters and sections are had in each subject, if some each chapters and sections of section's purpose is considered as 1 unit, each chapters and sections
For 1 blocks of knowledge.
The knowledge point that 1 exercise is covered might have multiple, some knowledge points are knowing in the knowledge point set
Know point, some knowledge points are not the knowledge points in the knowledge point set.Belong to the knowledge point set for what exercise was covered
Knowledge point in conjunction is labeled as the object knowledge point of exercise.
In some embodiments, before step S1, the method also includes following steps S011-S012:
S011, the object knowledge point that the candidate exercise is covered is obtained.
In some embodiments, step S011 includes the following steps S0111-S0114:
S0111, the text for obtaining the candidate exercise.
Text refers to the form of expression of written language, usually has complete, system meaning (Message) a sentence
Or the combination of multiple sentences.
S0112, the text of the candidate exercise is segmented, obtains several words.
Participle is the process that continuous word sequence is reassembled into word sequence according to certain specification.
The part of speech of S0113, each word of identification, filter out candidate from several described words according to the part of speech of each word
Word.
Basis of the characteristics of part of speech refers to using word as Part of Speech Division.The word obtained after text participle may have noun, move
Word, adjective, pronoun, quantifier and preposition etc..Information contained by the word of different parts of speech is different, such as pronoun, quantifier and preposition one
As do not contain the knowledge point information of exercise, to the knowledge point of parsing exercise without effect, and the knowledge point information of exercise is more
Included in noun and verb etc..Therefore, the application is filtered out from several described words according to part of speech is easy containing practice
The word of the knowledge point information of topic, as candidate word.
In some embodiments, step S0113 the following steps are included: by part of speech identifier identify the word whether be
Noun or verb are noun or verb if the word, then the word are labeled as the candidate word.
Generally, the examination point of exercise occurs mostly in the form of noun, secondly, occurring in the form of verb, such as photosynthetic
Effect, the Renaissance, electromagnetic induction etc., these nouns are mostly proper noun, resolution with higher, can be mapped exactly to pair
The knowledge point answered.Therefore, noun is determined as the candidate word by the noun in identification exercise text by the application, is reduced
It identifies target, reduces the operand to candidate word matching work.
S0114, candidate word keyword corresponding with each knowledge point in knowledge point set is matched, if matching
To the keyword corresponding with the candidate word, then knowledge point corresponding to the keyword is determined as the candidate white silk
The object knowledge point of exercise.
S012, the object knowledge point and the candidate exercise are associated storage.
In the application, the object knowledge point of each exercise in exam pool identifies in advance, the target that will identify that
Knowledge point is associated with exercise and stores.Exercise can cover one or more object knowledge points.In this way, according to exercise
It can determine object knowledge point associated with exercise.
It is understood that the object knowledge point may be covered in the candidate exercise, it is also possible to cover in institute
It states in exam pool in other exercises.Each exercise (including time of the object knowledge point will be covered in the exam pool
Select exercise) it is set as the exercise that is mutually related.
S2, the association exercise set that the candidate exercise is determined according to the object knowledge point, obtain in database
First history accuracy rate of the learner of storage when answering the association exercise set;According to the first history accuracy rate
Obtain ability value.
Wherein, the association exercise set includes at least two association exercises, and the entitled topic is practiced in the association
Cover the exercise of the object knowledge point in library.The ability value is for assessing the learner to the object knowledge point
Grasp ability.The learner is any learner in learner's set.
It is described that ability value is obtained according to the first history accuracy rate in step S2 in some embodiments, it is specific to wrap
It includes: the first history accuracy rate is arranged to force value.
In some embodiments, the expression formula of the ability value are as follows:
C=P2 (1)
Wherein, C is the ability value;P2For first history of the learner when answering the association exercise set
Accuracy rate.
Learner, can be by learner in the first history when being associated with exercise set of answering to the Grasping level of knowledge point
Accuracy rate makes effective assessment.Association exercise set, which is equivalent to, investigates the examination that learner grasps ability to object knowledge point
Volume, learner is higher in the first history accuracy rate when being associated with exercise set of answering, and illustrates grasp of the learner to knowledge point
Situation is higher.
Learner has certain palm to object knowledge point after having learnt blocks of knowledge corresponding with object knowledge point
It holds, at this point, exercise recommendation apparatus recommends several preset primary exercises for being easy to answer to learner, is learned to investigate
Grasp situation of the habit person to object knowledge point.Exercise recommendation apparatus by learner answer whole primary exercises when it is correct
Rate obtains initial ability value according to the first history accuracy rate as the first initial history accuracy rate.Exercise is recommended
Equipment stores the initial ability value in the database.Also, exercise recommendation apparatus is according to association of answering after learner
Accuracy when exercise set, the ability value in real-time update database, to keep assessment learner to slap object knowledge point
Hold the accuracy of ability.
The the first history accuracy rate of the ability value and the learner when answering each association exercise set is in
It is positively correlated.
The learner trained may cross the pass of the candidate exercise before the candidate exercise of answering
Join exercise.The learner is able to reflect out the learner couple in the first history accuracy rate when being associated with exercise of answering
The grasp situation of the object knowledge point.The i.e. described learner is higher in the first history accuracy rate when being associated with exercise of answering,
Then illustrate that the Grasping level of the point of object knowledge described in the learner is also higher.
Optionally, the course relevant with the object knowledge point that the ability value had also been learned to the learner into
Degree is positively correlated.
The course that the learner had learned may includes the related content of the object knowledge point, in this way,
Habit person has certain grasp to the object knowledge point before the topic that do not do one's exercises.In general, the learner has learned
The course relevant to the object knowledge point crossed is more, then the learner to the Grasping level of the object knowledge point also
It is higher.
In some embodiments, in step S2, the pass that the candidate exercise is determined according to the object knowledge point
Join exercise set, specifically include:
It obtains target practice in the exam pool and inscribes covered knowledge point;Appointing in the entitled exam pool of target practice
One exercise;Covered knowledge point is inscribed in the target practice to match with the object knowledge point;If successful match,
The association exercise is set by target practice topic, finally obtains the association exercise set.
S3, the corresponding difficulty value of the object knowledge point is obtained, calculates the difference between the ability value and the difficulty value
Absolute value, if the absolute value of the difference is less than or equal to preset threshold value, by the candidate exercise labeled as recommending to practice
Exercise.
The entitled exercise for being suitble to the learner to answer is practiced in the recommendation.
The threshold value is for measuring complexity of the object knowledge point for the learner.If the difference
Absolute value be less than or equal to preset threshold value, then illustrate that the deviation between the ability value and the difficulty value is smaller, it is described
For object knowledge point for the learner, difficulty is moderate, compares and the learner is suitble to answer.In the absolute of the difference
Value is less than or equal in the state of preset threshold value, when the ability value is greater than the difficulty value, illustrates the object knowledge
Point is slightly difficult for the learner, when the ability value is less than the difficulty value, illustrates the object knowledge point phase
It is slightly simple for the learner.In this way, the difficulty value and the ability value are effectively filtered out relative to described
The moderate recommendation exercise set of learner's difficulty, rationally recommends exercise to be embodied as the learner.
In some embodiments, before step S1, after step S013, further comprising the steps of S031-S032:
The learner stored in S031, the acquisition database is integrated into the answer candidate exercise and the association
The second history accuracy rate when exercise set;The second history accuracy rate is set as the corresponding standard of the object knowledge point
True rate.
Exercise recommendation apparatus records the result of answering for the exercise that each learner did.Count learner's collection
The second history accuracy rate when answering the candidate exercise and each association exercise set is closed, institute has also just been obtained
State learner set answer in the past the object knowledge point when accuracy rate.Because candidate's exercise or the association are practised
Topic is answered questions, then the object knowledge point covered also just is answered questions.The accuracy rate of the object knowledge point is institute
State the ratio of the total degree that object knowledge point was answered questions in the past Yu the total degree answered in the past.
S032, according to the corresponding accuracy rate of the object knowledge point, the corresponding difficulty of the object knowledge point is set
Value.
It is understood that the corresponding accuracy rate of the object knowledge point is higher, illustrate the difficulty of the object knowledge point
Lower, therefore, difficulty value accuracy rate corresponding with the object knowledge point is negatively correlated.Exercise recommendation apparatus will be described
Difficulty value stores in the database.As the association exercise that learner's set was done is more and more, learner gathers pass of answering
Accuracy rate when joining exercise set can constantly change, i.e., the difficulty value of the described object knowledge point can constantly change, practice
The difficulty value of recommendation apparatus object knowledge point according to the second history accuracy rate real-time update is inscribed, to guarantee the object knowledge
The accuracy of the difficulty value of point.
In some embodiments, the expression formula of the difficulty value are as follows:
H=(1-P1)*i; (2)
Wherein, H is the difficulty value;P1For the corresponding accuracy rate of the object knowledge point;I is constant, 0 < i≤1.
It is to be understood that i is for adjusting the difficulty value H.Because some when, the palm of the learner to knowledge point
It holds degree and is although not enough to answer the biggish knowledge point of difficulty, but often do ' lifting ' training, i.e., specially do some difficulty
Biggish exercise, to improve oneself grasp ability to knowledge point.For this purpose, the application can suitably be dropped using the constant i less than 1
The low difficulty value H ' is pulled out for the exercise that learner suitably recommends actual difficulty more slightly higher than the Grasping level of learner with reaching
The purpose of height ' training.
For example, it is assumed that i=95%, if the corresponding accuracy rate of object knowledge point is 75%, the object knowledge
The corresponding difficulty value of point is set as (1-75%) * 95%;If the corresponding accuracy rate of the object knowledge point is 20%,
The corresponding difficulty value of the object knowledge point is set as (1-20%) * 95%.
In above embodiment, the difficulty value C in the ability value H and expression formula (1) in expression formula (2) is equal
For the numerical value in [0,1] section, correspondingly, the absolute value of the difference is also the numerical value in [0,1] section.The ability value and
The difficulty value is that the accuracy rate inscribed of doing of foundation learner obtains, and has good objectivity and authenticity, Neng Gouke
Sight is that the learner filters out suitable exercise and answers.
For example, it is assumed that the threshold value J=5%, the ability value C of the learner is 70%;And assume i=100%,
The corresponding accuracy rate P of the object knowledge point1It is 20%, in this way, obtaining the difficulty value H is 80% according to expression formula (2);
Due to | C-H |=| 70%-80% |=10% > J, i.e., absolute value of the difference is more than between the described ability value C and the difficulty value H
Therefore the threshold value J determines that the candidate exercise is not suitable for the learner and answers.In the example, the object knowledge point
Corresponding accuracy rate P1Only 20%, it is seen that the object knowledge point is that comparison is difficult for most of learners,
The ability value C of habit person is 70%, and ability is much larger than accuracy rate P1, illustrate the learner to the palm of the object knowledge point
It is more much higher than the grasp ability of most of learners to hold ability, nonetheless, due to | C-H | > J illustrates the candidate practice
The difficulty of topic has been more than preset interval range for the learner, this is easy to expend the learner more
Reaction time is lost more than gain, and therefore, determines that the candidate exercise is not suitable for the learner and answers.Likewise, if described
The difficulty of candidate exercise is too simple for the learner, is similarly not suitable for the learner and currently continues to make
It answers, because too simple exercise is limited to the ability raising of learner, wastes the time of learner.
In some embodiments, before step S1, include the following steps S031:
S031, using the corresponding difficulty value in each knowledge point in the knowledge point set as element, establish difficulty value sequence;With
And using the learner relative to each knowledge point in the knowledge point set ability value as element, capacity-building value sequence.
The each element in each element and the ability value sequence in the difficulty value sequence corresponds.
For example, with the linear algebra in College Maths for the blocks of knowledge, it is assumed that the knowledge point set of the blocks of knowledge
Quantity k=5 in knowledge point in conjunction is inscribed according to learner is previous as a result, sampling out the ability value sequence for the learner that number is i
α _ i=(0.2,0.3,0.8,0.2,0), wherein each numerical value respectively indicates learner to the Grasping level of each knowledge point, knowledge point
Corresponding numerical value is bigger, illustrates that learner is higher to the Grasping level of knowledge point.It is assumed that the difficulty value for the exercise that number is j
Sequence q_j=(0.4,0,0.6,0.2,0), wherein each numerical value respectively indicates the difficulty of each knowledge point in exercise, knowledge point pair
The numerical value answered is bigger, and difficulty is higher.In difficulty value sequence q_j, the knowledge point that difficulty value is 0 indicates to number the exercise for being j not
Cover the knowledge point.That is, the exercise that number is j covers 3 knowledge points in knowledge point set, i.e., number is
The exercise of j has 3 object knowledge points, and difficulty value is respectively 0.4,0.6 and 0.2.
In some embodiments, the object knowledge point in candidate's exercise has multiple.From the difficulty value sequence
The difficulty value corresponding to each object knowledge point in the candidate exercise is extracted in column.From the ability value sequence
Middle extraction and each ability value corresponding to each object knowledge point in the candidate exercise.Step S3 includes following
Step: the absolute of the difference corresponding to each object knowledge point between the ability value and the difficulty value is calculated separately
Value practices the candidate exercise labeled as the recommendation if each absolute value of the difference is respectively less than or is equal to the threshold value
Exercise.
S4, several recommendation exercises are obtained from the exam pool, the recommendation exercise is pushed into
The answer interface of habit person.
In above-described embodiment, by the way that the ability value compared with the difficulty value, is obtained several from exam pool and is pushed away
Exercise is recommended, exercise will be recommended to recommend the learner;Accuracy rate according to learner's answer constantly updates learner's phase
For the ability value of knowledge point, as the learner grasps the raising of ability to knowledge point, the recommendation exercise recommended
Difficulty also steps up so that the learner when doing Training of Exercises, follow it is progressive, can gradually, effectively improve it is described
Grasp ability of the learner to knowledge point.
Based on the same technical idea, present invention also provides a kind of exercise recommendation apparatus, as shown in Fig. 2, the device
Including transceiver module 1 and processing module 2.The processing module 2 is used to control the information acquiring operation of the transceiver module 1.
The transceiver module 1, for the object knowledge point in candidate exercise, wherein the candidate entitled exam pool of practice
In any exercise.
The processing module 2, for determining the association exercise collection of the candidate exercise according to the object knowledge point
It closes, wherein the exercise for covering the object knowledge point in the entitled exam pool is practiced in the association, the association exercise
Quantity at least two;It is quasi- to obtain first history of the learner stored in database when answering the association exercise set
True rate;Ability value is obtained according to the first history accuracy rate, wherein the ability value is for assessing the learner to described
The grasp ability of object knowledge point;The corresponding difficulty value of the object knowledge point is obtained, the ability value and the difficulty are calculated
Absolute value of the difference between value, if the absolute value of the difference is less than or equal to preset threshold value, by the candidate exercise mark
It is denoted as recommendation exercise;The recommendation exercise is pushed to the answer interface of the learner.
In some embodiments, the processing module 2 is also used to identify the institute that the candidate exercise is covered
State object knowledge point;The object knowledge point and the candidate exercise are associated storage.
In some embodiments, the processing module 2 is specifically used for obtaining what target practice topic in the exam pool was covered
Knowledge point;Any exercise in the entitled exam pool of target practice;The target practice is inscribed to covered knowledge point
It is matched with the object knowledge point;If successful match, the association exercise is set by target practice topic.
In some embodiments, the processing module 2 is specifically used for obtaining the text of the candidate exercise;To the time
It selects the text of exercise to be segmented, obtains several words;The part of speech for identifying each word, according to the part of speech of each word from described
Candidate word is filtered out in several words;Candidate word keyword corresponding with each knowledge point in knowledge point set is carried out
Matching determines knowledge point corresponding to the keyword if being matched to the keyword corresponding with the candidate word
For the object knowledge point of the candidate exercise.
In some embodiments, the processing module 2 is also used to be stored in the database using obtaining module 1 and obtain
Learner is integrated into the second history accuracy rate when answering the candidate exercise and the association exercise set;It will be described
Second history accuracy rate is set as the corresponding accuracy rate of the object knowledge point;It is corresponding accurate according to the object knowledge point
The corresponding difficulty value of the object knowledge point is arranged in rate.
In some embodiments, the expression formula of the difficulty value are as follows:
H=(1-P1)*i;
Wherein, H is the difficulty value;P1For the corresponding accuracy rate of the object knowledge point;I is constant, 0 < i≤1.
In some embodiments, the object knowledge point has multiple.The processing module 2 is specifically used for calculating separately each institute
The absolute value of the difference corresponding to object knowledge point between the ability value and the difficulty value is stated, if each difference is exhausted
Value is respectively less than or is equal to the threshold value, then the candidate exercise is labeled as the recommendation exercise.
In above-described embodiment, by the way that the ability value compared with the difficulty value, is obtained several from exam pool and is pushed away
Exercise is recommended, exercise will be recommended to recommend the learner;Accuracy rate according to learner's answer constantly updates learner's phase
For the ability value of knowledge point, as the learner grasps the raising of ability to knowledge point, the recommendation exercise recommended
Difficulty also steps up so that the learner when doing Training of Exercises, follow it is progressive, can gradually, effectively improve it is described
Grasp ability of the learner to knowledge point.
Based on the same technical idea, present invention also provides a kind of computer equipments, as shown in figure 3, the computer is set
Standby includes transceiver 31, processor 32 and memory 33, is stored with computer-readable instruction, the calculating in the memory 33
When machine readable instruction is executed by the processor 32, so that the processor executes the practice in the respective embodiments described above
The step of inscribing recommended method.
The corresponding entity device of transceiver module 1 shown in Fig. 2 is transceiver 31 shown in Fig. 3, which can
It realizes all or part of function of transceiver module 1, or realizes and the same or similar function of transceiver module 1.
The corresponding entity device of processing module 2 shown in Fig. 2 is processor 32 shown in Fig. 3, which can
It realizes all or part of function of processing module 2, or realizes and the same or similar function of processing module 2.
Based on the same technical idea, present invention also provides a kind of storage medium for being stored with computer-readable instruction,
When the computer-readable instruction is executed by one or more processors, so that one or more processors execute above-mentioned each implementation
The step of exercise recommended method in mode.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, the technical solution of the application substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM), including some instructions are used so that a terminal (can be mobile phone, computer, server or network are set
It is standby etc.) execute method described in each embodiment of the application.
Embodiments herein is described above in conjunction with attached drawing, but the application be not limited to it is above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the enlightenment of the application, when not departing from the application objective and scope of the claimed protection, can also it make very much
Form, it is all using equivalent structure or equivalent flow shift made by present specification and accompanying drawing content, directly or indirectly
Other related technical areas are used in, these are belonged within the protection of the application.
Claims (10)
1. a kind of exercise recommended method characterized by comprising
Obtain the object knowledge point in candidate exercise, wherein the candidate any exercise practiced in entitled exam pool;
The association exercise set of the candidate exercise is determined according to the object knowledge point, wherein the association exercise
Set includes multiple association exercises, and the exercise for covering the object knowledge point in the entitled exam pool is practiced in the association;
Obtain first history accuracy rate of the learner stored in database when answering the association exercise set;
Ability value is obtained according to the first history accuracy rate, wherein the ability value is for assessing the learner to described
The grasp ability of object knowledge point;
The corresponding difficulty value of the object knowledge point is obtained, the absolute of the difference between the ability value and the difficulty value is calculated
Value, if the absolute value of the difference is less than or equal to preset threshold value, by the candidate exercise labeled as recommendation exercise;
The recommendation exercise is pushed to the answer interface of the learner.
2. exercise recommended method according to claim 1, which is characterized in that
Before the object knowledge point obtained in candidate exercise, the method also includes:
Identify the object knowledge point that the candidate exercise is covered;
The object knowledge point and the candidate exercise are associated storage.
3. exercise recommended method according to claim 2, which is characterized in that
The association exercise set that the candidate exercise is determined according to the object knowledge point, comprising:
Covered knowledge point is inscribed in the target practice obtained in the exam pool;Any in the entitled exam pool of target practice
Exercise;
Covered knowledge point is inscribed in the target practice to match with the object knowledge point;
If successful match, the association exercise is set by target practice topic, finally obtains the association exercise
Set.
4. exercise recommended method according to claim 2, which is characterized in that
The object knowledge point that the identification candidate exercise is covered, comprising:
Obtain the text of the candidate exercise;
The text of the candidate exercise is segmented, several words are obtained;
The part of speech for identifying each word filters out candidate word from several described words according to the part of speech of each word;
Candidate word keyword corresponding with each knowledge point in knowledge point set is matched, if being matched to and the time
The corresponding keyword of word is selected, then knowledge point corresponding to the keyword is determined as described in the candidate exercise
Object knowledge point.
5. exercise recommended method according to claim 1,2 or 3, which is characterized in that
Before the object knowledge point obtained in candidate exercise, the method also includes:
It obtains the learner stored in the database and is integrated into the answer candidate exercise and the association exercise collection
The second history accuracy rate when conjunction;
The second history accuracy rate is set as the corresponding accuracy rate of the object knowledge point;
According to the corresponding accuracy rate of the object knowledge point, the corresponding difficulty value of the object knowledge point is set.
6. exercise recommended method according to claim 5, which is characterized in that
The expression formula of the difficulty value are as follows:
H=(1-P1)*i;
Wherein, H is the difficulty value;P1For the corresponding accuracy rate of the object knowledge point;I is constant, 0 < i≤1.
7. exercise recommended method according to claim 1, which is characterized in that
The object knowledge point has multiple;
The absolute value of the difference calculated between the ability value and the difficulty value, if the absolute value of the difference is less than or equal to
Preset threshold value, then by the candidate exercise labeled as recommendation exercise, comprising:
Calculate separately the absolute of the difference corresponding to each object knowledge point between the ability value and the difficulty value
Value practices the candidate exercise labeled as the recommendation if each absolute value of the difference is respectively less than or is equal to the threshold value
Exercise.
8. a kind of exercise recommendation apparatus characterized by comprising
Transceiver module, for obtaining the object knowledge point in candidate exercise, wherein candidate times practiced in entitled exam pool
One exercise;
Processing module, for determining the association exercise set of the candidate exercise according to the object knowledge point, wherein institute
Stating association exercise set includes multiple association exercises, and the association is practiced covering the object knowledge in the entitled exam pool
The exercise of point;It is accurate to obtain first history of the learner stored in database when answering the association exercise set
Rate;Ability value is obtained according to the first history accuracy rate, wherein the ability value is for assessing the learner to the mesh
Mark the grasp ability of knowledge point;The corresponding difficulty value of the object knowledge point is obtained, the ability value and the difficulty value are calculated
Between absolute value of the difference the candidate exercise is marked if the absolute value of the difference is less than or equal to preset threshold value
To recommend exercise;The recommendation exercise is pushed to the answer interface of the learner.
9. a kind of computer equipment, which is characterized in that including transceiver, memory and processor, be stored in the memory
Computer-readable instruction, when the computer-readable instruction is executed by the processor, so that the processor executes such as right
It is required that the step in any exercise recommended method in 1 to 7.
10. a kind of storage medium for being stored with computer-readable instruction, which is characterized in that the computer-readable instruction is by one
Or multiple processors are when executing, so that one or more processors execute the exercise as described in any in claim 1 to 7
Step in recommended method.
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 true CN110413728A (en) | 2019-11-05 |
CN110413728B 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) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110751867A (en) * | 2019-11-27 | 2020-02-04 | 上海乂学教育科技有限公司 | 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 |
CN111275091A (en) * | 2020-01-16 | 2020-06-12 | 平安科技(深圳)有限公司 | Intelligent text conclusion recommendation method and device and computer readable storage medium |
CN111582694A (en) * | 2020-04-29 | 2020-08-25 | 腾讯科技(深圳)有限公司 | Learning evaluation method and device |
CN111914176A (en) * | 2020-08-07 | 2020-11-10 | 腾讯科技(深圳)有限公司 | Method and device for recommending subjects |
CN113934840A (en) * | 2021-11-01 | 2022-01-14 | 东北师范大学 | Covering heuristic quantity sensing exercise recommendation method |
CN114048377A (en) * | 2021-11-08 | 2022-02-15 | 网易有道信息技术(北京)有限公司 | Topic recommendation method and device, electronic equipment and storage medium |
CN114913729A (en) * | 2021-02-09 | 2022-08-16 | 广州视源电子科技股份有限公司 | Question selection 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 |
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 |
---|
蒋昌猛;冯筠;孙霞;陈静;张蕾;冯宏伟;: "基于知识点层次图的个性化习题推荐算法", 计算机工程与应用, no. 10, pages 234 - 240 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110751867A (en) * | 2019-11-27 | 2020-02-04 | 上海乂学教育科技有限公司 | English teaching system |
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 |
CN111275091A (en) * | 2020-01-16 | 2020-06-12 | 平安科技(深圳)有限公司 | Intelligent text conclusion recommendation method and device and computer readable 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 |
CN111582694A (en) * | 2020-04-29 | 2020-08-25 | 腾讯科技(深圳)有限公司 | Learning evaluation method and device |
CN111582694B (en) * | 2020-04-29 | 2023-08-08 | 腾讯科技(深圳)有限公司 | Learning evaluation method and device |
CN111914176A (en) * | 2020-08-07 | 2020-11-10 | 腾讯科技(深圳)有限公司 | Method and device for recommending subjects |
CN111914176B (en) * | 2020-08-07 | 2023-10-27 | 腾讯科技(深圳)有限公司 | Question recommendation method and device |
CN114913729A (en) * | 2021-02-09 | 2022-08-16 | 广州视源电子科技股份有限公司 | Question selection method and device, computer equipment and storage medium |
WO2022170985A1 (en) * | 2021-02-09 | 2022-08-18 | 广州视源电子科技股份有限公司 | Exercise selection method and apparatus, and computer device and storage medium |
CN113934840B (en) * | 2021-11-01 | 2022-04-01 | 东北师范大学 | Covering heuristic quantity sensing exercise recommendation method |
CN113934840A (en) * | 2021-11-01 | 2022-01-14 | 东北师范大学 | Covering heuristic quantity sensing exercise recommendation method |
CN114048377A (en) * | 2021-11-08 | 2022-02-15 | 网易有道信息技术(北京)有限公司 | Topic recommendation method and device, electronic equipment and storage medium |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN110413728B (en) | 2023-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110413728A (en) | Exercise recommended method, device, equipment and storage medium | |
CN106202059B (en) | Machine translation method and machine translation device | |
CN108536681A (en) | Intelligent answer method, apparatus, equipment and storage medium based on sentiment analysis | |
CN107918640A (en) | Sample determines method and device | |
CN108319581B (en) | Natural language sentence evaluation method and device | |
CN107967254A (en) | Knowledge point Forecasting Methodology and device, storage medium, electronic equipment | |
CN109471915A (en) | A kind of text evaluation method, device, equipment and readable storage medium storing program for executing | |
CN108549658A (en) | A kind of deep learning video answering method and system based on the upper attention mechanism of syntactic analysis tree | |
US11545042B2 (en) | Personalized learning system | |
CN110598786B (en) | Neural network training method, semantic classification method and semantic classification device | |
CN110991195B (en) | Machine translation model training method, device and storage medium | |
CN109299399A (en) | A kind of recommended method and terminal device of learning Content | |
CN117332072B (en) | Dialogue processing, voice abstract extraction and target dialogue model training method | |
KR20200107501A (en) | Device and Method of Scoring Emotion for Psychological Consultation | |
CN111126610A (en) | Topic analysis method, topic analysis device, electronic device and storage medium | |
CN115394393A (en) | Intelligent diagnosis and treatment data processing method and device, electronic equipment and storage medium | |
CN110765241B (en) | Super-outline detection method and device for recommendation questions, electronic equipment and storage medium | |
Jain et al. | AgriBot: agriculture-specific question answer system | |
CN109002477B (en) | Information processing method, device, terminal and medium | |
Zhao et al. | Gptbias: A comprehensive framework for evaluating bias in large language models | |
Lior et al. | Comparing humans and models on a similar scale: Towards cognitive gender bias evaluation in coreference resolution | |
CN112860983B (en) | Method, system, equipment and readable storage medium for pushing learning content | |
CN109918651A (en) | Synonymous part of speech template acquisition methods and device | |
CN113392221B (en) | Method and related device for processing thin entity | |
CN114942980B (en) | Method and device for determining text matching |
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 |