CN108897879A - A method of individualized teaching is realized by human-computer interaction - Google Patents
A method of individualized teaching is realized by human-computer interaction Download PDFInfo
- Publication number
- CN108897879A CN108897879A CN201810725586.6A CN201810725586A CN108897879A CN 108897879 A CN108897879 A CN 108897879A CN 201810725586 A CN201810725586 A CN 201810725586A CN 108897879 A CN108897879 A CN 108897879A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- user
- answer
- examination question
- explained
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 67
- 239000000463 material Substances 0.000 claims description 28
- 230000006978 adaptation Effects 0.000 claims description 12
- 238000013178 mathematical model Methods 0.000 claims description 10
- 238000012790 confirmation Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000007257 malfunction Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- QGWYLXFVPIMLDO-UHFFFAOYSA-N ethyl n-[4-[benzyl(2-phenylethyl)amino]-2-(2,4,5-trimethoxyphenyl)-1h-imidazo[4,5-c]pyridin-6-yl]carbamate Chemical compound N=1C(NC(=O)OCC)=CC=2NC(C=3C(=CC(OC)=C(OC)C=3)OC)=NC=2C=1N(CC=1C=CC=CC=1)CCC1=CC=CC=C1 QGWYLXFVPIMLDO-UHFFFAOYSA-N 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 230000003827 upregulation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to field of artificial intelligence, disclose a kind of method for realizing individualized teaching by human-computer interaction.It includes learning tasks automatic classifying that it, which provides a kind of realize by human-computer interaction,,Examination question is recommended automatically,The individualized teaching method of the teaching links such as the step that malfunctions positioning and query explanation,This method is other than needing to carry out data preparation and parameter setting in first step,Any human teachers are not needed in other steps to participate in,Human resources are reduced to the maximum extent,The especially occupancy of educational resource,Traditional time-consuming average explanation mode at 15~20 minutes is compared simultaneously,This method by determine it is wrong because and explain with carrying out step dimension accuracy,It is not only able to skip the content without explanation to greatest extent for the specific study situation of user,Emphasis is explained where the query of user,And go deep into excavating its question classification,User is set to be easier to understand knowledge point,The explanation time can also be foreshortened to 2~3 minutes,Greatly improve the learning efficiency of user.
Description
Technical field
The invention belongs to field of artificial intelligence, and in particular to it is a kind of can be applied to education sector pass through human-computer interaction
The method for realizing individualized teaching.
Background technique
In education sector, realize that individualized education is a big important topic.Currently, existing online education technology is a
Property in terms of exploration, i.e. it is technical can only to rest on live streaming, video teaching, personalized operation/exam pool etc. adaptive learning.
Direct seeding technique is divided into 1 pair of 1 live streaming, the application such as top class in a kindergarten's live streaming.Wherein, in 1 pair of 1 live streaming, each teacher can only be simultaneously
A student is served, that is, needs to be equipped with independent teacher for every student, therefore consider teacher strength, especially outstanding qualified teachers
The tensity of strength, this mode cost is high and is difficult to promote.And in top class in a kindergarten's live streaming, teacher in face of it is hundreds of even
Thousands of students needs the case where combining all students, therefore can not can be carried out such as to stop for some student and answer
The equal individualized teaching mode for each student of explaining the puzzle is doubted, causing to impart knowledge to students is substantially not present specific aim (or personalization).
In video teaching technology, student is learnt by watching given instructional video, and is completed for having recorded
Video there will be no any variation, the content that all students see is just the same, naturally also just be not present any personalization
Possibility.The video for making different student viewings different is a kind of trial well, but since video record cost is high, one
It has been the limit that 2-3 video is recorded in knowledge point, and difference carries out the personalized number of videos that will lead to needs the case where to student
It is promoted with index speed, therefore increases number of videos and can be carried out very coarse personalization to be adapted to student only, it can not be real
It refines and provides for each student and targetedly explain enough.
Other than both the above technology, the adaptive education skill of most mainstream is then based on personalized exam pool/operation at present.
In a technology, system inscribes outcome evaluation student by collecting doing for student, and recommends more exercises according to assessment result,
A degree of personalization is realized for the angle inscribed from doing.But the tool of topic mistake is not can determine that when student's error
Body position, this unit for directly resulting in explanation is topic rather than a certain step in topic, so that student has to waste
More time is in the content for not needing study.Meanwhile the explanation of progress then still relies on above-mentioned video class teaching
Mode, therefore still can not solve the problems, such as to be difficult to personalized explanation.
Summary of the invention
In order to solve the above problem in the presence of the prior art, it is an object of that present invention to provide one kind to pass through human-computer interaction
The method for realizing individualized teaching.
The technical scheme adopted by the invention is as follows：
A method of individualized teaching is realized by human-computer interaction, is included the following steps：
S100. knowledge point master data, the current learning data of user and several examination questions of answering are stored in advance in the database
Examination question master data, wherein the knowledge point master data includes the knowledge of several study ranges, corresponding each study range
Point and the first topological order for expressing the successive customs examination system in all knowledge points, the current learning data of user include that user has learned
Knowledge point set, user have been examination question set and user in the current power of each knowledge point, the examination question fundamental packets
Containing item content, the model answer at least two answer steps, the calculus technique for corresponding at least one answer step, it is used for
Express the second topological order of all answer successive customs examination systems of step and knowledge point, the difficulty of knowledge points of corresponding each answer step
Angle value is distinguished in value and knowledge point；
S101. by human-computer interaction, the target study range and target power value of user are obtained；
S102. according to the corresponding relationship of study range and knowledge point, target corresponding with target study range is obtained
Learning knowledge point set；
S103. according to first topological order and the current learning data of the user, the target learning knowledge point is adjusted
Set；
S104. the knowledge that user's current power is more than target power value is rejected in the target learning knowledge point set
Point thens follow the steps S113 if the element in the target learning knowledge point set is zero, otherwise from the target learning knowledge
The target learning knowledge point for being located at most priori position in first topological order is selected to know in point set as current preference study
Know point；
S105. it is directed to the current preference learning knowledge point, is currently learned according to the knowledge point master data, the user
The examination question master data for practising data and all examination questions of answering, calculates the current adaptation degree of each examination question, will currently be adapted to degree
Highest examination question is as preferential teaching examination question；
S106. the item content of the preferential teaching examination question is sent to human-computer interaction interface, and by human-computer interaction, obtained
Take the result of answering at family；
If S107. it is described answer result and it is corresponding it is described it is preferential teaching examination question model answer it is inconsistent, determine answer
Mistake executes step S108, otherwise determines that answer is correct, executing step is 112；
S108. according to the examination question master data of the current learning data of the user and the preferential teaching examination question, positioning is used
Step is answered in this error of estimating answered of family；
S109. error answer step is estimated described in showing in human-computer interaction interface output and by the second topological order sequence
Step is answered positioned at all priori for estimating before step is answered in error and unmarked human-computer interaction result, is then passed through
Human-computer interaction marks the human-computer interaction result of shown answer step, wherein the human-computer interaction is the result is that digit synbol is corresponding aobvious
Show that answer step is to have a question or without query；
S110. the display for being for new label answers step/or for solving a problem comprising display answer step
Skill is explained using the corresponding explanation material prestored in the database；
S111. in all answer steps of the preferential teaching examination question, if there are still unmarked human-computer interaction results
Step is answered, then returns to step S108~S111；
S112. correctly answer result or the human-computer interaction that is generated in step S109~110 that according to user, this is answered
Record, updates the current learning data of the user, then returns to step S104~S112；
S113. terminate this study, learn the information that finishes to human-computer interaction interface output, wherein described to learn the letter that finishes
Current power lifting capacity of the breath comprising user each knowledge point in target study range.
Optimization, in the step S103, according to the mode as described in step S301~S302 as follows and/or by step
Mode described in rapid S303~S304 adjusts the target learning knowledge point set：
S301. for each knowledge point in the target learning knowledge point set, according to the first topological order sequence
Search before being located at the knowledge point and be spaced all priori knowledge points that number is not more than pre-determined distance value；
S302. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the target learning knowledge point set by ability value；
S303. for each knowledge point in the target learning knowledge point set, according to the first topological order sequence
Search be located at the knowledge point before and be spaced number be greater than pre-determined distance value all priori knowledge points and be located at the knowledge point it
Aposterior knowledge point afterwards；
S304. it is directed to each aposterior knowledge point, if user is lower than the target in the current power of the aposterior knowledge point
The aposterior knowledge point is then pushed to human-computer interaction interface by ability value, if by human-computer interaction, confirmation will learn the aposterior knowledge
The aposterior knowledge point is then added in the target learning knowledge point set by point.
Optimization, in the step S105, the current adaptation degree of each examination question is calculated as follows：
S501. according to the current preference learning knowledge point, the target power value, the knowledge point master data, institute
The examination question master data for stating the current learning data of user and corresponding examination question, calculates separately the following index of corresponding examination question：In examination question
The ratio F of knowledge point quantity in the outer knowledge point quantity of target and examination question1, in knowledge point topological order span and library knowledge point in examination question
The ratio F of quantity2, user do not grasp the ratio F of knowledge point quantity in knowledge point quantity and examination question in examination question3, user do not grasp examination
The ratio F of knowledge point topological order most posteriority position and knowledge point quantity in library in inscribing4, answered outside target in examination question step weight with
The ratio F of answer step weight in examination question5And/or the probability ratio F of user's mistake knowledge point outside target6；
S502. a column vector will be spliced into all indexs obtained in step S501；
S503. column vector is subtracted each other with the corresponding ideal column vector for being most adapted to examination question, obtains error vector, wherein described
Ideal column vector is 0 vector or is preset according to experience with students；
S504. using two norms of error vector as the current adaptation degree of corresponding examination question.
Optimization, further include following steps before the step S107：
If S700. obtain for the first time answer result and it is corresponding it is described it is preferential teaching examination question model answer it is inconsistent, will
The item content of the preferential teaching examination question and examination point prompt are sent to human-computer interaction interface, and by human-computer interaction, obtain again
Take the result of answering at family, wherein the examination point prompt is stored in advance in the examination question master data of the preferential teaching examination question.
Optimization, in the step S108, this error answer of estimating answered of positioning user is walked as follows
Suddenly：
S801. for each answer step of the preferential teaching examination question, according to the current learning data of the user and institute
Examination question master data is stated, is calculated and individually does to prediction probability accordingly；
S802. in all answer steps of unmarked human-computer interaction result, the solution minimum to prediction probability will individually be done
Step is answered as error is estimated and answers step.
It advanced optimizes, it is basic according to the current learning data of the user and the examination question in the step S801
Data are calculated individually doing for answer step and include the following steps to the method for prediction probability：
Knowledge point, difficulty of knowledge points value and the knowledge point of the corresponding answer step are found from the examination question master data
Angle value is distinguished, user is found from the current learning data of the user in the current ability of the knowledge point of the corresponding answer step
Then the current power, the difficulty of knowledge points value and the knowledge point are distinguished angle value and input IRT mathematical model by value,
Using the output probability of the IRT mathematical model individually doing to prediction probability as the corresponding answer step.
Optimization, in the step S110, display answer step is explained as follows：
S1101. the first writing on the blackboard information is generated, wherein the first writing on the blackboard information includes to answer step pair with the display
All knowledge points answered；
S1102. by the first writing on the blackboard information and be used to explain it is described display answer step first explanation material send to
Human-computer interaction interface carries out output and shows, wherein the first explanation material includes picture file, text file, voice document
And/or video file, and the examination question for being stored in the preferential teaching examination question is bound together with corresponding display answer step in advance
In master data；
If S1103. user feedback is not understood, S1104 is thened follow the steps, otherwise terminates to say display answer step
Solution；
S1104. the first knowledge point set to be explained is generated, and will all knowledge points corresponding with display answer step
It is included in the described first knowledge point set to be explained；
S1105. it for each knowledge point to be explained in the described first knowledge point set to be explained, is opened up according to described first
Flutter all priori knowledge points before sequence sequential search is located at the knowledge point to be explained；
S1106. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the described first knowledge point set to be explained by ability value；
S1107. according to first topological order from elder generation to rear sequence, the described first knowledge point set to be explained is explained one by one
Knowledge point to be explained in conjunction.
Optimization, in the step S110, calculus technique is explained as follows：
S1111. the second writing on the blackboard information is generated, wherein the second writing on the blackboard information includes the institute of the corresponding calculus technique
There are answer step and all knowledge points corresponding with these answer steps；
S1112. by the second writing on the blackboard information and be used to explain the calculus technique second explanation material send to man-machine
Interactive interface carries out output and shows, wherein it is described second explanation material include picture file, text file, voice document and/or
Video file, and the examination question master data for being stored in the preferential teaching examination question is bound together with corresponding calculus technique in advance
In；
If S1113. user feedback is not understood, S1114 is thened follow the steps, otherwise terminates the explanation to the calculus technique；
S1114. the second knowledge point set to be explained is generated, and will be in all answer steps of the correspondence calculus technique
It is included in the described second knowledge point set to be explained in all knowledge points corresponding with these answer steps；
S1115. it for each knowledge point to be explained in the described second knowledge point set to be explained, is opened up according to described first
Flutter all priori knowledge points before sequence sequential search is located at the knowledge point to be explained；
S1116. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the described second knowledge point set to be explained by ability value；
S1117. according to first topological order from elder generation to rear sequence, the described second knowledge point set to be explained is explained one by one
Knowledge point to be explained in conjunction.
It advanced optimizes, explains knowledge point to be explained as follows：
S1121. the current power according to user in the knowledge point to be explained determines that difficulty is explained in knowledge point；
S1122. according to user the knowledge point to be explained study number to the knowledge point explanation difficulty carry out to
Upper or downward revision, the study number are stored in the user and currently learn with corresponding wait explain to bind together with knowledge point in advance
It practises in data；
S1123. third explanation that is difficulty being explained into the correspondence knowledge point and being used to explain the knowledge point to be explained
Material, which is sent, to carry out output to human-computer interaction interface and shows, and make the study number of the knowledge point to be explained from plus 1, wherein institute
Stating third explanation material includes picture file, text file, voice document and/or video file, and in advance with corresponding wait say
Solution knowledge point is bound together to be stored in the knowledge point master data；
If S1124. user feedback is not understood, S1125 is thened follow the steps, otherwise terminates to say the knowledge point to be explained
Solution；
If being S1125. stored with other thirds that explanation difficulty is just below the knowledge point explanation difficulty in the database
Material is explained, then third explanation material is sent and carries out output to human-computer interaction interface and show, and make the knowledge point to be explained
Study number from plus 1, then return to step S1124, it is no to then follow the steps S1126；
If S1126. existing in first topological order described in being located at wait the current energy of before explaining knowledge point and user
Force value is lower than the priori knowledge point of the target power value, then using the priori knowledge point as the new knowledge to be explained preferentially explained
Point, otherwise will be located at it is described wait all priori knowledge points before explaining knowledge point all as the new knowledge to be explained preferentially explained
Point；
S1127. it according to first topological order from elder generation to rear sequence, is one by one explained according to step S1121~S1127
Newly knowledge point to be explained.
Optimization, further include following steps after the step S110：
S1131. after terminating some display answer step or showing the explanation for answering the calculus technique of step comprising some,
It is all marked according to the second topological order sequence if all priori before discovery is located at display answer step answer step
For no query, then display answer step is answered into step labeled as really doing wrong, then execute step S1132, otherwise continue
Subsequent explanation；
If S1132. user it is described it is preferential teaching examination question number of answering be less than preset value and by human-computer interaction it is true
Recognizing will continue to answer, then terminates subsequent explanation, then return to step S106, otherwise continue subsequent explanation.
Beneficial effects of the present invention are：
(1) the invention provides a kind of automatic including learning tasks automatic classifying, examination question by human-computer interaction realization
The individualized teaching method of the teaching links such as recommendation, the positioning of error step and query explanation, this method is in addition to needing in first step
It is carried out in rapid outside data preparation and parameter setting, does not need any human teachers in other steps and participate in, to the maximum extent
The occupancy of human resources, especially educational resource is reduced, while comparing traditional time-consuming average explanation side at 15~20 minutes
Formula, this method by determine it is wrong because and explain with carrying out step dimension accuracy, be not only able to be directed to the specific study situation of user
The content without explanation is skipped to greatest extent, where emphasis explains the query of user, and is goed deep into excavating its question classification, is made user
It is easier to understand knowledge point, moreover it is possible to the explanation time be foreshortened to 2~3 minutes, the learning efficiency of user is greatly improved；
(2) explanation compared to traditional as unit of topic and capability evaluation, this method pass through the examination question more refined
It middle step relationship and the mark such as is associated between knowledge point, for providing the user of identical result, can accomplish fine to know
Know point level assessment, therefore this method can obtain more accurate student ability assessment result with less examination question, and it is more acurrate
Assessment result can then make topic recommend and knowledge point explanation all more targetedly, further realize really personalized religion
It educates.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the method flow schematic diagram provided by the invention that individualized teaching is realized by human-computer interaction.
Specific embodiment
With reference to the accompanying drawing and specific embodiment the present invention is further elaborated.It should be noted that for this
The explanation of a little way of example is used to help understand the present invention, but and does not constitute a limitation of the invention.
The terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate：Individualism A, individualism B exist simultaneously tri- kinds of situations of A and B, the terms
"/and " it is to describe another affiliated partner relationship, indicate may exist two kinds of relationships, for example, A/ and B, can indicate：Individually deposit
In A, two kinds of situations of individualism A and B, in addition, character "/" herein, typicallying represent forward-backward correlation object is a kind of "or" pass
System.
Embodiment one
As shown in Figure 1, the method that individualized teaching is realized by human-computer interaction provided in this embodiment, including it is as follows
Step.
S100. knowledge point master data, the current learning data of user and several examination questions of answering are stored in advance in the database
Examination question master data, wherein the knowledge point master data includes the knowledge of several study ranges, corresponding each study range
Point and the first topological order for expressing the successive customs examination system in all knowledge points, the current learning data of user include that user has learned
Knowledge point set, user have been examination question set and user in the current power of each knowledge point, the examination question fundamental packets
Containing item content, the model answer at least two answer steps, the calculus technique for corresponding at least one answer step, it is used for
Express the second topological order of all answer successive customs examination systems of step and knowledge point, the difficulty of knowledge points of corresponding each answer step
Angle value is distinguished in value and knowledge point.
In the step S100, the successive customs examination system in knowledge point refers to for knowledge point a and knowledge point b, if necessary
First learning knowledge point a, could learning knowledge point b again, then knowledge point a and knowledge point b has successive customs examination system：Knowledge point a is first
Knowledge point is tested, knowledge point b is aposterior knowledge point.So as to obtain having certain length and expression all knowledge point elder generations posteriority
First topological order of relationship.The successive customs examination system of answer step refers to for answer step a and answer step b, if must
It must first do to answer step a, could do again to answer step b, then answering step a and answer step b has successive customs examination system：Solution
Answering step a is priori step, and answer step b is posteriority step.So as to obtain having certain topology network architecture and table
Up to second topological order of all answer successive customs examination systems of step.In addition, optimization, the examination question master data can also wrap
Containing examination point prompt, weight coefficient of corresponding each answer step etc..
S101. by human-computer interaction, the target study range and target power value of user are obtained.
In the step S101, the concrete mode of the human-computer interaction be can be, but not limited to as based on virtual AI teacher angle
The question and answer teaching method of color, i.e. voice dialogue or text conversation by virtual AI teacher and user in man-machine interface obtain
The target study range and target power value of user, wherein the target study range can be, but not limited to as in teaching material
Some chapters and sections.In addition it is also possible to obtain answer result and the specific answer step of subsequent examination question based on identical question and answer teaching method
Rapid human-computer interaction result.
S102. according to the corresponding relationship of study range and knowledge point, target corresponding with target study range is obtained
Learning knowledge point set.
It is each due in the knowledge point master data including several study ranges and correspondence in the step S102
Learn the knowledge point of range, therefore can automatically learning tasks be carried out with the decomposition of knowledge point rank, facilitates subsequent based on institute
The first topological order sequence is stated, specific aim teaching seriatim is carried out.
S103. according to first topological order and the current learning data of the user, the target learning knowledge point is adjusted
Set.
In the step S103, in order to ensure user can reach the capability improving in each target learning knowledge point,
It can be, but not limited to according to the mode as described in step S301~S302 as follows and/or as described in step S303~S304
Mode adjusts the target learning knowledge point set：
S301. for each knowledge point in the target learning knowledge point set, according to the first topological order sequence
Search before being located at the knowledge point and be spaced all priori knowledge points that number is not more than pre-determined distance value；
S302. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the target learning knowledge point set by ability value；
S303. for each knowledge point in the target learning knowledge point set, according to the first topological order sequence
Search be located at the knowledge point before and be spaced number be greater than pre-determined distance value all priori knowledge points and be located at the knowledge point it
Aposterior knowledge point afterwards；
S304. it is directed to each aposterior knowledge point, if user is lower than the target in the current power of the aposterior knowledge point
The aposterior knowledge point is then pushed to human-computer interaction interface by ability value, if by human-computer interaction, confirmation will learn the aposterior knowledge
The aposterior knowledge point is then added in the target learning knowledge point set by point.
The mode as described in step S301~S302 is to force the mode of addition knowledge point, for being in certain intervals model
Interior priori knowledge point is enclosed, due to being to learn the precondition for understanding target learning knowledge point, also must be learned by.By step S303
Mode described in~S304 is the mode of optional addition knowledge point, for the priori knowledge point except certain intervals range
With aposterior knowledge point, can determine whether to take as an elective course by human-computer interaction.The pre-determined distance value is nature that is preset and being not less than 2
Number.
S104. the knowledge that user's current power is more than target power value is rejected in the target learning knowledge point set
Point thens follow the steps S113 if the element in the target learning knowledge point set is zero, otherwise from the target learning knowledge
The target learning knowledge point for being located at most priori position in first topological order is selected to know in point set as current preference study
Know point.
In the step S104, particularly, if discovery needs preferentially to explain multiple knowledge during user inscribes
Point then preferentially can be selected successively from these knowledge points.In addition, if having been completed on some current preference learning knowledge point
A certain number of examination questions (even if there is still a need for teaching for the current preference learning knowledge point), then record the current preference learning and know
Know point to be skipped, it, so can be to avoid at certain later by it from needing to reject in the target learning knowledge point set imparted knowledge to students
Study schedule is blocked on a knowledge point.
S105. it is directed to the current preference learning knowledge point, is currently learned according to the knowledge point master data, the user
The examination question master data for practising data and all examination questions of answering, calculates the current adaptation degree of each examination question, will currently be adapted to degree
Highest examination question is as preferential teaching examination question.
In the step S105, the current adaptation degree for calculating each examination question as follows can be, but not limited to.
S501. according to the current preference learning knowledge point, the target power value, the knowledge point master data, institute
The examination question master data for stating the current learning data of user and corresponding examination question, calculates separately the following index of corresponding examination question：In examination question
The ratio F of knowledge point quantity in the outer knowledge point quantity of target and examination question1, in knowledge point topological order span and library knowledge point in examination question
The ratio F of quantity2, user do not grasp the ratio F of knowledge point quantity in knowledge point quantity and examination question in examination question3, user do not grasp examination
The ratio F of knowledge point topological order most posteriority position and knowledge point quantity in library in inscribing4, answered outside target in examination question step weight with
The ratio F of answer step weight in examination question5And/or the probability ratio F of user's mistake knowledge point outside target6。
In the step S501, it can be, but not limited to calculate in accordance with the following steps in the examination question of examination question and know outside target
Know the ratio F of knowledge point quantity in point quantity and examination question1：
S5101. according to the examination question master data of corresponding examination question, summarize to obtain examination question and cover knowledge point set；
S5102. knowledge point quantity in knowledge point quantity and examination question is calculated in the examination question outside target according to following formula
Ratio F1：
In formula,Cover knowledge point set to belong to the examination question and be not belonging to the current preference learning knowledge point
Knowledge point sum,To belong to the knowledge point sum that the examination question covers knowledge point set.In the step S5101, by
It include that item content, the model answer containing at least two answer steps and correspondence are each in the examination question master data
The knowledge point of step is answered, therefore the examination question that can easily obtain the examination question covers knowledge point set.
In the step S501, it can be, but not limited to calculate knowledge point in the examination question of examination question in accordance with the following steps and open up
Flutter the ratio F of knowledge point quantity in sequence span and library2：
S5201. according to the examination question master data of corresponding examination question, summarize to obtain examination question and cover knowledge point set；
S5202. according to the knowledge point master data, determine that the examination question is covered in knowledge point set in the first topology
The sequence most priori knowledge point of position and the most posteriority knowledge point in topological order rearmost position at first；
S5203. the ratio of knowledge point quantity in knowledge point topological order span and library in the examination question is calculated according to following formula
Value F2：
In formula, M is the knowledge point sum in database, XMaxLFor the topological serial number of the most posteriority knowledge point, XMinFFor institute
State the topological serial number of most priori knowledge point, XMaxL-XMinFFor topological order span in knowledge point in examination question.Since the knowledge point is basic
Data include the first topological order for expressing the successive customs examination system in all knowledge points, therefore can easily determine that most priori is known
Know point, most posteriority knowledge point and corresponding topological serial number.
In the step S501, the user that can be, but not limited to calculate examination question in accordance with the following steps does not grasp examination question
The ratio F of knowledge point quantity in interior knowledge point quantity and examination question3：
S5301. according to the examination question master data of corresponding examination question, summarize to obtain examination question and cover knowledge point set；
S5302. cover each knowledge point in knowledge point set for the examination question, from the current learning data of the user
In find corresponding current power, if the current power be lower than the target power value, using the knowledge point as use
Knowledge point in examination question is not grasped in family；
S2303. summarize to obtain user and do not grasp knowledge point set in examination question, and calculate the user not according to following formula
Grasp the ratio F of knowledge point quantity and knowledge point quantity in examination question in examination question3：
In formula,To belong to the knowledge point sum that the user does not grasp knowledge point set in examination question,To belong to
State the knowledge point sum that examination question covers knowledge point set.Since the current learning data of the user includes user in each knowledge point
Current power, therefore be easy to judge that can some knowledge point be grasped by user.
In the step S501, the user that can be, but not limited to calculate examination question in accordance with the following steps does not grasp examination question
The ratio F of knowledge point quantity in interior knowledge point topological order most posteriority position and library4：
S5401. according to the examination question master data of corresponding examination question, summarize to obtain examination question and cover knowledge point set；
S5402. cover each knowledge point in knowledge point set for the examination question, from the current learning data of the user
In find corresponding current power, if the current power be lower than the target power value, using the knowledge point as use
Knowledge point in examination question is not grasped in family；
S5403. summarize to obtain user and do not grasp knowledge point set in examination question；
S5404. it according to the knowledge point master data, determines that the user does not grasp in examination question and is in knowledge point set
The most posteriority of topological order rearmost position does not grasp knowledge point；
S5405. the user is calculated according to following formula do not grasp knowledge point topological order most posteriority position and library in examination question
The ratio F of interior knowledge point quantity4：
In formula, M is the knowledge point sum in database,The topological serial number of knowledge point is not grasped for the most posteriority.
In the step S501, it can be, but not limited to calculate target in the examination question of examination question in accordance with the following steps and solve outside
Answer the ratio F of answer step weight in step weight and examination question5：
S5501. according to the examination question master data of corresponding examination question, summarize to obtain and answer set of steps in examination question；
S5502. for each answer step in the examination question in answer set of steps, according to the examination question base of corresponding examination question
Notebook data judges whether the answer step corresponds to the current preference learning knowledge point, if not corresponding to, which is made
To answer step outside target in examination question；
S5503. summarize to obtain in examination question and answer set of steps outside target, then calculated in the examination question according to following formula
The ratio F of answer step weight in step weight and examination question is answered outside target5：
In formula, wsTo be answered the in set of steps outside target in the examination questionA answer step
Weight coefficient, wjTo be answered the in set of steps in the examination questionThe weight system of a answer step
Number,To belong in the examination question answer step sum for answering set of steps outside target,It is solved to belong in the examination question
Answer the answer step sum of set of steps.
In the step S501, the probability ratio F of user's mistake knowledge point outside target6Refer in examination question and
The answer step of the current preference learning knowledge point is not corresponded to, and according to the current learning data of the user, (it contains user and exists
The current power of each knowledge point) and the examination question master data (its degree-of-difficulty factor for containing corresponding each answer step),
Prediction calculates user's doing to probability in the answer step, and last join probability opinion can calculate user and do wrong at least one
Probability --- the i.e. probability of user's mistake knowledge point outside target of these answer steps.
S502. a column vector will be spliced into all indexs obtained in step S501.
S503. column vector is subtracted each other with the corresponding ideal column vector for being most adapted to examination question, obtains error vector, wherein described
Ideal column vector is 0 vector or is preset according to experience with students.
After the step S503, the problem of taking into account all situations in need while in order to avoid overlapping development, also
Include the following steps：Error vector is multiplied with preset weight row vector, completes the adjustment to the error vector.
S504. using two norms of error vector as the current adaptation degree of corresponding examination question.
After the step S504, new topic practice is reviewed with old topic in order to balance, and topic under same capabilities is avoided to recommend
Monotonicity, further include following steps：
Examination question set is done according to user in the current learning data of user, the user for counting corresponding examination question does topic number, right
Current adaptation degree correct upwards shown in following formula：
a′i=γtai
In formula, a 'iIt is i-th (i=1,2,3 ..., N) a examination question in revised current adaptation degree, aiFor i-th (i=1,
2,3 ..., N) the current adaptation degree of a examination question before amendment, γ is upward correction factor, and t is to inscribe in the user of the examination question
Number.From there through the amendment for doing topic number is added, avoidable repetition is inscribed, but remains the possibility of recommendation, to realize multiple
Practise purpose.
S106. the item content of the preferential teaching examination question is sent to human-computer interaction interface, and by human-computer interaction, obtained
Take the result of answering at family.
In the step S106, the result of answering be can be, but not limited to comprising several answer step and final results.
If S107. it is described answer result and it is corresponding it is described it is preferential teaching examination question model answer it is inconsistent, determine answer
Mistake executes step S108, otherwise determines that answer is correct, executing step is 112.
It further include following steps for error correction chance of mostly once answering to user before the step S107：
If S700. obtain for the first time answer result and it is corresponding it is described it is preferential teaching examination question model answer it is inconsistent, will
The item content of the preferential teaching examination question and examination point prompt are sent to human-computer interaction interface, and by human-computer interaction, obtain again
Take the result of answering at family, wherein the examination point prompt is stored in advance in the examination question master data of the preferential teaching examination question.
S108. according to the examination question master data of the current learning data of the user and the preferential teaching examination question, positioning is used
Step is answered in this error of estimating answered of family.
In the step S108, it can be, but not limited to position user this estimating out of answering as follows and misexplain
Answer step：
S801. for each answer step of the preferential teaching examination question, according to the current learning data of the user and institute
Examination question master data is stated, is calculated and individually does to prediction probability accordingly；
S802. in all answer steps of unmarked human-computer interaction result, the solution minimum to prediction probability will individually be done
Step is answered as error is estimated and answers step.
In the step S801, according to the current learning data of the user and the examination question master data, it is calculated
Individually doing for answer step includes the following steps the method for prediction probability：
Knowledge point, difficulty of knowledge points value and the knowledge point of the corresponding answer step are found from the examination question master data
Angle value is distinguished, user is found from the current learning data of the user in the current ability of the knowledge point of the corresponding answer step
Then the current power, the difficulty of knowledge points value and the knowledge point are distinguished angle value and input IRT mathematical model by value,
Using the output probability of the IRT mathematical model individually doing to prediction probability as the corresponding answer step.
The IRT mathematical model is that (Item Response Theory, item response theory are also known as inscribed based on IRT theory
Mesh reaction theory or latent trait theory are a series of general names of Psychological Statistics models) and be used to analyze total marks of the examination or
The existing mathematical model of person's questionnaire survey data.Specifically, the IRT mathematical model can be, but not limited to as 3 parameter Normal-
Ogive model or 3 parameter Logistic models；Alternatively, calculating individually doing to prediction probability for answer step according to following formula：
psgr=sigmoid (κ (v-d))
In formula, sigmoid () is the nonlinear function applied in IRT mathematical model, and κ is the knowledge of corresponding answer step
Point distinguishes angle value, and d is the difficulty of knowledge points value of corresponding answer step.
S109. error answer step is estimated described in showing in human-computer interaction interface output and by the second topological order sequence
Step is answered positioned at all priori for estimating before step is answered in error and unmarked human-computer interaction result, is then passed through
Human-computer interaction marks the human-computer interaction result of shown answer step, wherein the human-computer interaction is the result is that digit synbol is corresponding aobvious
Show that answer step is to have a question or without query.
In the step S109, particularly, when all answer steps of some corresponding calculus technique have been shown completely
After, it is also necessary to it shows the calculus technique, and is interacted with user.After user proposes feedback result, first by the result
It records, as the foundation in error procedure positioning.In addition, if user is to problematic, Ke Yidian the step of merging display
It hits expansion and shows all independent answer steps being merged, then carry out the human-computer interaction result for individually answering step for these
Label.
S110. the display for being for new label answers step/or for solving a problem comprising display answer step
Skill is explained using the corresponding explanation material prestored in the database.
In the step S110, it can be, but not limited to as follows explain display answer step：
S1101. the first writing on the blackboard information is generated, wherein the first writing on the blackboard information includes to answer step pair with the display
All knowledge points answered；
S1102. by the first writing on the blackboard information and be used to explain it is described display answer step first explanation material send to
Human-computer interaction interface carries out output and shows, wherein the first explanation material can be, but not limited to comprising picture file, text text
Part, voice document and/or video file, and binding is stored in the preferential teaching together with corresponding display answer step in advance
In the examination question master data of examination question；
If S1103. user feedback is not understood, S1104 is thened follow the steps, otherwise terminates to say display answer step
Solution；
S1104. the first knowledge point set to be explained is generated, and will all knowledge points corresponding with display answer step
It is included in the described first knowledge point set to be explained；
S1105. it for each knowledge point to be explained in the described first knowledge point set to be explained, is opened up according to described first
Flutter all priori knowledge points before sequence sequential search is located at the knowledge point to be explained；
S1106. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the described first knowledge point set to be explained by ability value；
S1107. according to first topological order from elder generation to rear sequence, the described first knowledge point set to be explained is explained one by one
Knowledge point to be explained in conjunction.
In the step S110, it can be, but not limited to as follows explain calculus technique：
S1111. the second writing on the blackboard information is generated, wherein the second writing on the blackboard information includes the institute of the corresponding calculus technique
There are answer step and all knowledge points corresponding with these answer steps；
S1112. by the second writing on the blackboard information and be used to explain the calculus technique second explanation material send to man-machine
Interactive interface carries out output and shows, wherein it is described second explanation material include picture file, text file, voice document and/or
Video file, and the examination question master data for being stored in the preferential teaching examination question is bound together with corresponding calculus technique in advance
In；
If S1113. user feedback is not understood, S1114 is thened follow the steps, otherwise terminates the explanation to the calculus technique；
S1114. the second knowledge point set to be explained is generated, and will be in all answer steps of the correspondence calculus technique
It is included in the described second knowledge point set to be explained in all knowledge points corresponding with these answer steps；
S1115. it for each knowledge point to be explained in the described second knowledge point set to be explained, is opened up according to described first
Flutter all priori knowledge points before sequence sequential search is located at the knowledge point to be explained；
S1116. it is directed to each priori knowledge point, if user is lower than the target in the current power of the priori knowledge point
The priori knowledge point is then added in the described second knowledge point set to be explained by ability value；
S1117. according to first topological order from elder generation to rear sequence, the described second knowledge point set to be explained is explained one by one
Knowledge point to be explained in conjunction.
In the step S1107 or the step S1117, it can be, but not limited to explain as follows and know wait explain
Know point：
S1121. the current power according to user in the knowledge point to be explained determines that difficulty is explained in knowledge point；
S1122. according to user the knowledge point to be explained study number to the knowledge point explanation difficulty carry out to
Upper or downward revision, the study number are stored in the user and currently learn with corresponding wait explain to bind together with knowledge point in advance
It practises in data；
S1123. third explanation that is difficulty being explained into the correspondence knowledge point and being used to explain the knowledge point to be explained
Material, which is sent, to carry out output to human-computer interaction interface and shows, and make the study number of the knowledge point to be explained from plus 1, wherein institute
Stating third explanation material includes picture file, text file, voice document and/or video file, and in advance with corresponding wait say
Solution knowledge point is bound together to be stored in the knowledge point master data；
If S1124. user feedback is not understood, S1125 is thened follow the steps, otherwise terminates to say the knowledge point to be explained
Solution；
If being S1125. stored with other thirds that explanation difficulty is just below the knowledge point explanation difficulty in the database
Material is explained, then third explanation material is sent and carries out output to human-computer interaction interface and show, and make the knowledge point to be explained
Study number from plus 1, then return to step S1124, it is no to then follow the steps S1126；
If S1126. existing in first topological order described in being located at wait the current energy of before explaining knowledge point and user
Force value is lower than the priori knowledge point of the target power value, then using the priori knowledge point as the new knowledge to be explained preferentially explained
Point, otherwise will be located at it is described wait all priori knowledge points before explaining knowledge point all as the new knowledge to be explained preferentially explained
Point；
S1127. it according to first topological order from elder generation to rear sequence, is one by one explained according to step S1121~S1127
Newly knowledge point to be explained.
After the step S110, in order to confirm it is true wrong because and consolidate understanding of the user to explanation knowledge in time, and also
Include the following steps：
S1131. after terminating some display answer step or showing the explanation for answering the calculus technique of step comprising some,
It is all marked according to the second topological order sequence if all priori before discovery is located at display answer step answer step
For no query, then display answer step is answered into step labeled as really doing wrong, then execute step S1132, otherwise continue
Subsequent explanation；
If S1132. user it is described it is preferential teaching examination question number of answering be less than preset value and by human-computer interaction it is true
Recognizing will continue to answer, then terminates subsequent explanation, then return to step S106, otherwise continue subsequent explanation.
S111. in all answer steps of the preferential teaching examination question, if there are still unmarked human-computer interaction results
Step is answered, then returns to step S108~S111.
S112. correctly answer result or the human-computer interaction that is generated in step S109~110 that according to user, this is answered
Record, updates the current learning data of the user, then returns to step S104~S112.
In the step S112, it can be, but not limited to update the current learning data of the user in the following way：Needle
To have correctly answer result the case where, all answer steps are collectively labeled as unquestionable answer step, then for whether there is or not
The answer step of query, current power of the up-regulation user on the knowledge point of corresponding answer step, and have a question for all
Answer step, lower current power of the user on the knowledge point of corresponding answer step.Particularly, for by described second
Topological order sequence continues to inscribe in the answer step of the posteriority after answering step that really does wrong if not returning, will not
Update current power of the user on the knowledge point of corresponding posteriority answer step.Further, it is also possible to human-computer interaction interface to
User shows all answer steps of the preferential teaching examination question, and what is carried out on the basis of these answer steps all say
Solution record, so that student consolidates.
S113. terminate this study, learn the information that finishes to human-computer interaction interface output, wherein described to learn the letter that finishes
Current power lifting capacity of the breath comprising user each knowledge point in target study range.
To sum up, using the method for realizing individualized teaching by human-computer interaction provided by the present embodiment, there is following skill
Art effect：
(1) a kind of realize by human-computer interaction is present embodiments provided to push away automatically including learning tasks automatic classifying, examination question
Recommend, the step that malfunctions positioning and query explanation etc. teaching links individualized teaching method, this method in addition to need in first step
Outside middle carry out data preparation and parameter setting, does not need any human teachers in other steps and participate in, drop to the maximum extent
The low occupancy of human resources, especially educational resource, while traditional time-consuming average explanation mode at 15~20 minutes is compared,
This method by determine it is wrong because and explain with carrying out step dimension accuracy, be not only able to the specific study situation maximum for user
Limit skips the content without explanation, where emphasis explains the query of user, and gos deep into excavating its question classification, holds that user more
Readily understood knowledge point, moreover it is possible to the explanation time be foreshortened to 2~3 minutes, the learning efficiency of user is greatly improved；
(2) explanation compared to traditional as unit of topic and capability evaluation, this method pass through the examination question more refined
It middle step relationship and the mark such as is associated between knowledge point, for providing the user of identical result, can accomplish fine to know
Know point level assessment, therefore this method can obtain more accurate student ability assessment result with less examination question, and it is more acurrate
Assessment result can then make topic recommend and knowledge point explanation all more targetedly, further realize really personalized religion
It educates.
The present invention is not limited to above-mentioned optional embodiment, anyone can show that other are each under the inspiration of the present invention
The product of kind form.Above-mentioned specific embodiment should not be understood the limitation of pairs of protection scope of the present invention, protection of the invention
Range should be subject to be defined in claims, and specification can be used for interpreting the claims.
Claims (10)
1. a kind of method for realizing individualized teaching by human-computer interaction, which is characterized in that include the following steps：
S100. the examination of knowledge point master data, the current learning data of user and several examination questions of answering is stored in advance in the database
Inscribe master data, wherein the knowledge point master data include several study ranges, corresponding each study range knowledge points and
For expressing the first topological order of the successive customs examination system in all knowledge points, the current learning data of user includes user's knowledge
Point set, user have been examination question set and user in the current power of each knowledge point, and the examination question master data includes topic
Mesh content, the model answer at least two answer steps, the calculus technique of at least one corresponding answer step, for expressing
The knowledge point of second topological orders of all answer successive customs examination systems of step and corresponding each answer step, difficulty of knowledge points value and
Distinguish angle value in knowledge point；
S101. by human-computer interaction, the target study range and target power value of user are obtained；
S102. it according to the corresponding relationship of study range and knowledge point, obtains target corresponding with target study range and learns
Knowledge point set；
S103. according to first topological order and the current learning data of the user, the target learning knowledge point set is adjusted；
S104. the knowledge point that user's current power is more than target power value is rejected in the target learning knowledge point set,
If the element in the target learning knowledge point set is zero, S113 is thened follow the steps, otherwise from the target learning knowledge point
Select the target learning knowledge point for being located at most priori position in first topological order as current preference learning knowledge in set
Point；
S105. it is directed to the current preference learning knowledge point, number is currently learnt according to the knowledge point master data, the user
According to the examination question master data with all examination questions of answering, the current adaptation degree of each examination question is calculated, degree highest will be currently adapted to
Examination question as preferential teaching examination question；
S106. the item content of the preferential teaching examination question is sent to human-computer interaction interface, and by human-computer interaction, obtains and use
The result of answering at family；
If S107. it is described answer result and it is corresponding it is described it is preferential teaching examination question model answer it is inconsistent, determine answer mistake,
Step S108 is executed, otherwise determines that answer is correct, executing step is 112；
S108. according to the examination question master data of the current learning data of the user and the preferential teaching examination question, user's sheet is positioned
Step is answered in the secondary error of estimating answered；
S109. error answer step is estimated described in showing in human-computer interaction interface output and is located at by the second topological order sequence
All priori answer step for estimating before step is answered in error and unmarked human-computer interaction result, then by man-machine
Interaction marks the human-computer interaction result of shown answer step, wherein the human-computer interaction is the result is that the corresponding display solution of digit synbol
Answering step is to have a question or without query；
S110. the display answer step/that is for new label or for the calculus technique comprising display answer step,
It is explained using the corresponding explanation material prestored in the database；
S111. in all answer steps of the preferential teaching examination question, if there are still the answers of unmarked human-computer interaction result
Step then returns to step S108~S111；
S112. according to user this answer correctly answer result or generated in step S109~110 human-computer interaction record,
The current learning data of the user is updated, S104~S112 is then returned to step；
S113. terminate this study, learn the information that finishes to human-computer interaction interface output, wherein described to learn the packet that finishes
The current power lifting capacity of each knowledge point in target study range containing user.
2. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
In step S103, according to the mode as described in step S301~S302 as follows and/or as described in step S303~S304
Mode adjusts the target learning knowledge point set：
S301. for each knowledge point in the target learning knowledge point set, according to the first topological order sequential search
Before the knowledge point and it is spaced all priori knowledge points that number is not more than pre-determined distance value；
S302. it is directed to each priori knowledge point, if user is lower than the target capability in the current power of the priori knowledge point
The priori knowledge point, then be added in the target learning knowledge point set by value；
S303. for each knowledge point in the target learning knowledge point set, according to the first topological order sequential search
Before the knowledge point and interval number is greater than all priori knowledge points of pre-determined distance value and after the knowledge point
Aposterior knowledge point；
S304. it is directed to each aposterior knowledge point, if user is lower than the target capability in the current power of the aposterior knowledge point
Value, then push to human-computer interaction interface for the aposterior knowledge point, if confirmation will learn the aposterior knowledge point by human-computer interaction,
Then the aposterior knowledge point is added in the target learning knowledge point set.
3. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
In step S105, the current adaptation degree of each examination question is calculated as follows：
S501. according to the current preference learning knowledge point, the target power value, the knowledge point master data, the use
The examination question master data of the current learning data in family and corresponding examination question, calculates separately the following index of corresponding examination question：Target in examination question
The ratio F of knowledge point quantity in outer knowledge point quantity and examination question1, knowledge point quantity in knowledge point topological order span and library in examination question
Ratio F2, user do not grasp the ratio F of knowledge point quantity in knowledge point quantity and examination question in examination question3, user do not grasp in examination question
The ratio F of knowledge point quantity in knowledge point topological order most posteriority position and library4, step weight and examination question are answered in examination question outside target
The ratio F of interior answer step weight5And/or the probability ratio F of user's mistake knowledge point outside target6；
S502. a column vector will be spliced into all indexs obtained in step S501；
S503. column vector is subtracted each other with the corresponding ideal column vector for being most adapted to examination question, obtains error vector, wherein the ideal
Column vector is 0 vector or is preset according to experience with students；
S504. using two norms of error vector as the current adaptation degree of corresponding examination question.
4. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
It further include following steps before step S107：
If the model answer of answer result and the corresponding preferential teaching examination question that S700. obtain for the first time is inconsistent, will be described
The item content of preferential teaching examination question and examination point prompt are sent to human-computer interaction interface, and by human-computer interaction, obtain use again
The result of answering at family, wherein the examination point prompt is stored in advance in the examination question master data of the preferential teaching examination question.
5. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
In step S108, step is answered in this error of estimating answered of positioning user as follows：
S801. for each answer step of the preferential teaching examination question, according to the current learning data of the user and the examination
Master data is inscribed, is calculated and individually does to prediction probability accordingly；
S802. in all answer steps of unmarked human-computer interaction result, it will individually do the answer minimum to prediction probability and walk
Rapid be used as estimates error answer step.
6. a kind of method for realizing individualized teaching by human-computer interaction as claimed in claim 5, which is characterized in that described
In step S801, according to the current learning data of the user and the examination question master data, the independent of answer step is calculated
It does and the method for prediction probability is included the following steps：
Knowledge point, difficulty of knowledge points value and the knowledge point that the corresponding answer step is found from the examination question master data are distinguished
Angle value, finds user in the current power of the knowledge point of the corresponding answer step from the current learning data of the user,
Then angle value is distinguished into the current power, the difficulty of knowledge points value and the knowledge point and inputs IRT mathematical model, by this
The output probability of IRT mathematical model is individually done to prediction probability as the corresponding answer step.
7. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
In step S110, display answer step is explained as follows：
S1101. the first writing on the blackboard information is generated, wherein the first writing on the blackboard information includes corresponding with display answer step
All knowledge points；
S1102. by the first writing on the blackboard information and be used to explain it is described display answer step first explanation material send to man-machine
Interactive interface carries out output and shows, wherein it is described first explanation material include picture file, text file, voice document and/or
Video file, and the examination question basic number for being stored in the preferential teaching examination question is bound together with corresponding display answer step in advance
In；
If S1103. user feedback is not understood, S1104 is thened follow the steps, otherwise terminates the explanation to the display answer step；
S1104. the first knowledge point set to be explained is generated, and all knowledge points corresponding with display answer step are included in
The first knowledge point set to be explained；
S1105. for each knowledge point to be explained in the described first knowledge point set to be explained, according to first topological order
Sequential search be located at the knowledge point to be explained before all priori knowledge points；
S1106. it is directed to each priori knowledge point, if user is lower than the target capability in the current power of the priori knowledge point
The priori knowledge point, then be added in the described first knowledge point set to be explained by value；
S1107. it according to first topological order from elder generation to rear sequence, is explained in the described first knowledge point set to be explained one by one
Knowledge point to be explained.
8. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that described
In step S110, calculus technique is explained as follows：
S1111. the second writing on the blackboard information is generated, wherein the second writing on the blackboard information includes all solutions of the corresponding calculus technique
Answer step and all knowledge points corresponding with these answer steps；
S1112. by the second writing on the blackboard information and be used to explain the calculus technique second explanation material send to human-computer interaction
Interface carries out output and shows, wherein the second explanation material includes picture file, text file, voice document and/or video
File, and binding is stored in the examination question master data of the preferential teaching examination question together with corresponding calculus technique in advance；
If S1113. user feedback is not understood, S1114 is thened follow the steps, otherwise terminates the explanation to the calculus technique；
S1114. generate the second knowledge point set to be explained, and by all answer steps of the correspondence calculus technique with this
It is included in the described second knowledge point set to be explained in a little corresponding all knowledge points of step of answering；
S1115. for each knowledge point to be explained in the described second knowledge point set to be explained, according to first topological order
Sequential search be located at the knowledge point to be explained before all priori knowledge points；
S1116. it is directed to each priori knowledge point, if user is lower than the target capability in the current power of the priori knowledge point
The priori knowledge point, then be added in the described second knowledge point set to be explained by value；
S1117. it according to first topological order from elder generation to rear sequence, is explained in the described second knowledge point set to be explained one by one
Knowledge point to be explained.
9. a kind of method for realizing individualized teaching by human-computer interaction as claimed in claim 7 or 8, which is characterized in that press
Knowledge point to be explained is explained according to such as under type：
S1121. the current power according to user in the knowledge point to be explained determines that difficulty is explained in knowledge point；
S1122. according to user the knowledge point to be explained study number to the knowledge point explanation difficulty carry out upwards or
Downward revision, the study number are stored in the user wait explaining together with knowledge point binding and currently learn number with corresponding in advance
In；
S1123. third explanation material that is difficulty being explained into the correspondence knowledge point and being used to explain the knowledge point to be explained
Send and carry out output to human-computer interaction interface and show, and make the study number of the knowledge point to be explained from plus 1, wherein described the
Three explanation materials include picture file, text file, voice document and/or video file, and are known in advance with corresponding wait explain
Knowing point, binding is stored in the knowledge point master data together；
If S1124. user feedback is not understood, S1125 is thened follow the steps, otherwise terminates the explanation to the knowledge point to be explained；
If being S1125. stored with other thirds explanation that explanation difficulty is just below the knowledge point explanation difficulty in the database
Third explanation material is then sent carry out output to human-computer interaction interface and show, and make the knowledge point to be explained by material
Number is practised from adding 1, then returns to step S1124, it is no to then follow the steps S1126；
If S1126. existing in first topological order described in being located at wait before explaining knowledge point and user's current power
Lower than the priori knowledge point of the target power value, then using the priori knowledge point as the new knowledge point to be explained preferentially explained,
Otherwise wait all priori knowledge points before explaining knowledge point all as the new knowledge point to be explained preferentially explained described in being located at；
S1127. according to first topological order from elder generation to rear sequence, one by one according to step S1121~S1127 explanation newly to
Explain knowledge point.
10. a kind of method for realizing individualized teaching by human-computer interaction as described in claim 1, which is characterized in that in institute
It further include following steps after stating step S110：
S1131. after terminating some display answer step or showing the explanation for answering the calculus technique of step comprising some, according to
The second topological order sequence is collectively labeled as nothing if all priori before discovery is located at display answer step answer step
Display answer step is then answered step labeled as really doing wrong, then executes step S1132, otherwise continue subsequent by query
Explanation；
If S1132. user is less than preset value in the number of answering of the preferential teaching examination question and is wanted by human-computer interaction confirmation
Continue to answer, then terminate subsequent explanation, then return to step S106, otherwise continues subsequent explanation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810725586.6A CN108897879B (en) | 2018-07-04 | 2018-07-04 | Method for realizing personalized teaching through man-machine interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810725586.6A CN108897879B (en) | 2018-07-04 | 2018-07-04 | Method for realizing personalized teaching through man-machine interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108897879A true CN108897879A (en) | 2018-11-27 |
| CN108897879B CN108897879B (en) | 2020-11-10 |
Family
ID=64347911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810725586.6A Active CN108897879B (en) | 2018-07-04 | 2018-07-04 | Method for realizing personalized teaching through man-machine interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108897879B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN110378818A (en) * | 2019-07-22 | 2019-10-25 | 广西大学 | Personalized exercise recommended method, system and medium based on difficulty |
| CN111311998A (en) * | 2020-04-10 | 2020-06-19 | 江苏现代职教图书发行有限公司 | Modern cloud classroom online education platform |
| CN111475627A (en) * | 2019-01-23 | 2020-07-31 | 北京字节跳动网络技术有限公司 | Method and device for checking solution deduction questions, electronic equipment and storage medium |
| CN111638788A (en) * | 2020-05-29 | 2020-09-08 | 广东小天才科技有限公司 | Learning data output method and terminal equipment |
| CN111681479A (en) * | 2020-06-24 | 2020-09-18 | 中国科学院自动化研究所 | Self-adaptive situational artificial intelligence teaching system, method and device |
| CN111753077A (en) * | 2020-06-28 | 2020-10-09 | 华侨大学 | Chinese intelligent teaching question bank generation method based on student knowledge portrait |
| CN112541493A (en) * | 2020-12-17 | 2021-03-23 | 北京字节跳动网络技术有限公司 | Topic explaining method and device and electronic equipment |
| CN113065986A (en) * | 2021-03-22 | 2021-07-02 | 深圳童年科技有限公司 | Educational resource generation method based on intelligent interaction |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030037960A (en) * | 2001-11-07 | 2003-05-16 | 김성주 | Method for brokerage of personal teaching and for appraising teacher using internet and computer readable medium having thereon computer executable instruction for performing the same |
| CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
| CN103077178A (en) * | 2011-10-26 | 2013-05-01 | 财团法人资讯工业策进会 | Learning diagnosis and dynamic learning resource recommendation method and system |
| US20160035238A1 (en) * | 2013-03-14 | 2016-02-04 | Educloud Co. Ltd. | Neural adaptive learning device using questions types and relevant concepts and neural adaptive learning method |
| CN105447573A (en) * | 2015-11-25 | 2016-03-30 | 杨会志 | Method and system for interactively completing solving process of mathematic question |
| CN107038508A (en) * | 2017-06-06 | 2017-08-11 | 海南大学 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
| CN108122444A (en) * | 2016-11-28 | 2018-06-05 | 北京狸米科技有限公司 | A kind of adaptive and learning system and method |
-
2018
- 2018-07-04 CN CN201810725586.6A patent/CN108897879B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030037960A (en) * | 2001-11-07 | 2003-05-16 | 김성주 | Method for brokerage of personal teaching and for appraising teacher using internet and computer readable medium having thereon computer executable instruction for performing the same |
| CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
| CN103077178A (en) * | 2011-10-26 | 2013-05-01 | 财团法人资讯工业策进会 | Learning diagnosis and dynamic learning resource recommendation method and system |
| US20160035238A1 (en) * | 2013-03-14 | 2016-02-04 | Educloud Co. Ltd. | Neural adaptive learning device using questions types and relevant concepts and neural adaptive learning method |
| CN105447573A (en) * | 2015-11-25 | 2016-03-30 | 杨会志 | Method and system for interactively completing solving process of mathematic question |
| CN108122444A (en) * | 2016-11-28 | 2018-06-05 | 北京狸米科技有限公司 | A kind of adaptive and learning system and method |
| CN107123068A (en) * | 2017-04-26 | 2017-09-01 | 北京航空航天大学 | A kind of programming-oriented language course individualized learning effect analysis system and method |
| CN107038508A (en) * | 2017-06-06 | 2017-08-11 | 海南大学 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
Non-Patent Citations (1)
| Title |
|---|
| 李伟铭: "个性化教育平台的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111475627B (en) * | 2019-01-23 | 2021-06-18 | 北京字节跳动网络技术有限公司 | Method and device for checking solution deduction questions, electronic equipment and storage medium |
| CN111475627A (en) * | 2019-01-23 | 2020-07-31 | 北京字节跳动网络技术有限公司 | Method and device for checking solution deduction questions, electronic equipment and storage medium |
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN110378818A (en) * | 2019-07-22 | 2019-10-25 | 广西大学 | Personalized exercise recommended method, system and medium based on difficulty |
| CN110378818B (en) * | 2019-07-22 | 2022-03-11 | 广西大学 | Personalized exercise recommendation method, system and medium based on difficulty |
| CN111311998A (en) * | 2020-04-10 | 2020-06-19 | 江苏现代职教图书发行有限公司 | Modern cloud classroom online education platform |
| CN111638788A (en) * | 2020-05-29 | 2020-09-08 | 广东小天才科技有限公司 | Learning data output method and terminal equipment |
| CN111681479A (en) * | 2020-06-24 | 2020-09-18 | 中国科学院自动化研究所 | Self-adaptive situational artificial intelligence teaching system, method and device |
| CN111753077A (en) * | 2020-06-28 | 2020-10-09 | 华侨大学 | Chinese intelligent teaching question bank generation method based on student knowledge portrait |
| CN111753077B (en) * | 2020-06-28 | 2022-06-07 | 华侨大学 | Chinese intelligent teaching question bank generation method based on student knowledge portrait |
| CN112541493A (en) * | 2020-12-17 | 2021-03-23 | 北京字节跳动网络技术有限公司 | Topic explaining method and device and electronic equipment |
| CN112541493B (en) * | 2020-12-17 | 2022-09-30 | 北京字节跳动网络技术有限公司 | Topic explaining method and device and electronic equipment |
| CN113065986A (en) * | 2021-03-22 | 2021-07-02 | 深圳童年科技有限公司 | Educational resource generation method based on intelligent interaction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108897879B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108897879A (en) | A method of individualized teaching is realized by human-computer interaction | |
| Holmes et al. | Introductory physics labs: We can do better | |
| Falloon | An analysis of young students' thinking when completing basic coding tasks using Scratch Jnr. On the iPad | |
| CN110070295A (en) | The evaluation and analysis method, apparatus and computer equipment of Classroom Teaching | |
| CN107067879A (en) | A kind of intelligent Piano Teaching system | |
| CN108536672A (en) | Intelligent robot Training Methodology, device, computer equipment and storage medium | |
| Roback et al. | Applying Japanese lesson study principles to an upper-level undergraduate statistics course | |
| CN101630451A (en) | Computer assisted instruction (CAI) expert system | |
| Armitage et al. | Applying a “theory of change” process to facilitate transdisciplinary sustainability education | |
| US20160035238A1 (en) | Neural adaptive learning device using questions types and relevant concepts and neural adaptive learning method | |
| Sinclair et al. | Digital technology in mathematics teaching and learning: A decade focused on theorising and teaching | |
| CN105844991A (en) | Method and device for processing answer data | |
| Chen et al. | Education 4.0 using artificial intelligence for students performance analysis | |
| CN107644572A (en) | A kind of tutoring system based on thought process | |
| CN110189238A (en) | Method, apparatus, medium and the electronic equipment of assisted learning | |
| CN114491057A (en) | Learning path recommendation method, system, computer and medium based on knowledge graph | |
| CN114021722A (en) | Attention knowledge tracking method integrating cognitive portrayal | |
| CN109814787A (en) | Key message determines method, apparatus, equipment and storage medium | |
| Khan et al. | Automatic student modelling for detection of learning styles and affective states in web based learning management systems | |
| WO2022009875A1 (en) | Program for determining concentration level | |
| CN109840867A (en) | A kind of method of intelligent tutoring, equipment and device | |
| Permana et al. | Analysis of Students’ Work Readiness Based on Self-Efficacy of Vocational High School in The Building Information Modelling Technology Era | |
| CN115984059A (en) | Collaborative fusion education attention training method, system, device and medium | |
| CN110019862A (en) | A kind of courseware recommended method, device, equipment and storage medium | |
| Simmons | Investigation into the development of a quantitatively based summation conception of the definite integral |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 1 / F cb101-017, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing Patentee after: Beijing Sita Intelligent Technology Co.,Ltd. Address before: 1 / F cb101-017, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing Patentee before: BEIJING XIZI EDUCATION TECHNOLOGY Co.,Ltd. |