CN112419810A - Intelligent education method for accurate control based on adaptive cognitive interaction - Google Patents
Intelligent education method for accurate control based on adaptive cognitive interaction Download PDFInfo
- Publication number
- CN112419810A CN112419810A CN202011273387.XA CN202011273387A CN112419810A CN 112419810 A CN112419810 A CN 112419810A CN 202011273387 A CN202011273387 A CN 202011273387A CN 112419810 A CN112419810 A CN 112419810A
- Authority
- CN
- China
- Prior art keywords
- information
- constructing
- interactive
- sequence
- fusion
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000003993 interaction Effects 0.000 title claims abstract description 42
- 230000001149 cognitive effect Effects 0.000 title claims abstract description 34
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 25
- 230000004927 fusion Effects 0.000 claims abstract description 62
- 230000002452 interceptive effect Effects 0.000 claims abstract description 50
- 230000019771 cognition Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000010354 integration Effects 0.000 claims abstract description 6
- 230000009471 action Effects 0.000 claims description 22
- 230000000007 visual effect Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000007418 data mining Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000010387 memory retrieval Effects 0.000 claims description 5
- 230000008901 benefit Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005215 recombination Methods 0.000 claims description 3
- 230000006798 recombination Effects 0.000 claims description 3
- 241000282414 Homo sapiens Species 0.000 abstract description 6
- 230000004044 response Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036992 cognitive tasks Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
- G09B5/14—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations with provision for individual teacher-student communication
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a self-adaptive cognitive interaction-based intelligent education precise control method, which comprises the following steps of: constructing an interactive interface cognition module of an intelligent education platform based on ACT-R; constructing a cognitive interaction mode library; constructing a global integration set of the interactive information; and constructing an interactive interface information control feedback process based on the fuzzy self-adaptive PID controller. The method applies a reasoning adaptive control interactive behavior cognition model to an intelligent education platform, and establishes an interactive mode library from the cognition angle of human; describing an object and an information source of input information of an interactive interface into a knowledge element, and solving a local fusion value and a global fusion value of an interactive information sequence through entropy weight method weighting and linear weighting on the basis of obtaining an interactive information fusion set. And finally, the global fusion value of the interactive information is used as the input of a PID controller, the information interactive control process of the human-computer interface is completed through a fuzzy self-adaptive PID control algorithm, and the result is fed back, so that the control precision and the response rate are optimized.
Description
Technical Field
The invention relates to the technical field of intelligent education and intelligent teaching, in particular to a method for accurately controlling intelligent education based on self-adaptive cognitive interaction.
Background
With the gradual development of industrial internet, new-generation information technologies such as cloud computing, big data, internet of things and mobile internet promote the transformation of education modes, and education begins to trend to intellectualization and networking. The key point and key point of comprehensive application intelligent education lies in that people and objects are connected to carry out effective intelligent interaction. The quality of intelligent teaching interaction directly influences the effect of course learning. Therefore, under the background of intelligent education, research on an interaction control method becomes an important direction for improving human-computer information interaction experience.
In the intelligent teaching platform, the implementation of diversified interactive behaviors can provide two-aspect services for learners: firstly, the learner and the system resource are interacted independently, and secondly, the learner and the two parties can carry out real-time interconnected remote dynamic interaction. However, the existing interface information interaction control method suitable for intelligent education has limitations, and has the problems of long feedback time of control results, low control precision and the like, so that it is difficult to satisfy individual chemical habit complaints of users and realize a good teaching interaction process.
Disclosure of Invention
The invention aims to provide an intelligent education information precise Control method based on self-Adaptive cognitive interaction, aiming at the challenges and problems in the information interaction Control method of a teaching platform, researching the interaction mode of a human and an intelligent education platform from a cognition angle based on an Adaptive Control of high-speed-ratio (ACT-R) cognitive model, and designing the intelligent education information precise Control method based on fuzzy PID so as to realize a good information interaction process in intelligent education.
To solve the above technical problem, an embodiment of the present invention provides the following solutions:
a smart education method based on adaptive cognitive interaction for precise control comprises the following steps:
constructing an interactive interface cognition module of an intelligent education platform based on ACT-R;
constructing a cognitive interaction mode library;
constructing a global integration set of the interactive information;
and constructing an interactive interface information control feedback process based on the fuzzy self-adaptive PID controller.
Preferably, the step of constructing an interactive interface cognition module of the intelligent education platform based on ACT-R comprises the following steps:
constructing a target module based on a learning analysis technology of data mining;
constructing a visual module according to the structural layout of the teaching content;
constructing an action memory module according to the target action income and the execution action of the associated user;
constructing a descriptive memory module according to memory retrieval and information extraction;
based on the constructed target module, the visual module, the action memory module and the descriptive memory module, learning progress is dynamically perceived through a deep learning recommendation algorithm based on behavior data, a learning sequence is adaptively optimized, and learning knowledge points are accurately pushed according to different student conditions.
Preferably, the step of constructing the target module based on the learning analysis technology of data mining specifically includes:
performing optimization and recombination on excellent education resources around the world through a learning analysis technology based on data mining, and establishing a target hierarchical system to store learning resources in various forms;
classifying different types of teaching contents, and storing the teaching contents into a database so as to meet the current target and intention of a user;
user preference and knowledge level information are collected, and a network course content system, a learning mode and teaching management which are exclusive to users are designed adaptively, so that targeted education is performed.
Preferably, the step of constructing the visual module according to the teaching content structure layout specifically includes:
using typesetting layout, dynamic effect and visual contrast means for the learning picture in the interactive process;
a network knowledge structure is formed through information navigation design, and a user preference access index table is established, so that the teaching content structure layout is balanced, and the arrangement of knowledge points is reasonable.
Preferably, the step of constructing the action memory module according to the target action revenue and the associated user execution action specifically includes:
according to the utility formula, the utility of an example i is:
wherein u isiShowing the utility of the example i,
initial value, P, representing the utility of instance iiRepresenting the probability of the current target being achieved, GiRepresents the yield after the current goal is completed, CiRepresenting an estimate of the cost required in achieving the goal.
Preferably, the step of constructing the descriptive memory module according to memory retrieval and information extraction specifically includes:
and extracting the learned information from the memory, and adding the learned information to a cache space, wherein the ACT-R model descriptive knowledge activation quantity is expressed as:
wherein, BiRepresenting a basic activation quantity of information, wjWeight of interest, S, representing informationjiIndicating the strength of the correlation.
Preferably, the step of constructing the cognitive interaction pattern library comprises:
and integrating the cache information of the target module, the vision module, the action memory module and the descriptive memory module to generate coherent cognition and construct an intelligent education cognition interaction pattern library.
Preferably, the step of constructing a global integration set of interaction information includes:
acquiring an interactive information fusion set;
solving the objective weight of the information sequence;
and solving a global fusion result of the information.
Preferably, the step of obtaining the interaction information fusion set specifically includes:
suppose that the input interactive information includes n objects to be fused with the same character, and the n objects are described as the knowledge elements of the fused object and recorded as the knowledge elements
The object to be fused has m associated attributes, and the associated attributes are described as attribute knowledge elements and are recorded as attribute knowledge elements
P associated information sources of the object to be fused are recorded as
The corresponding expression is:
wherein o isiRepresents the object to be fused and is to be fused,
and
each represents oiName set, attribute set, association set and feature set;
represents a pair oiAttribute ajDescription of (1);
represents a pair oiAttribute ajThe measurable characteristics comprise membership, linearity and nonlinearity, ambiguity and random probability;
represents ajA corresponding measurement of the balance;
for the description of ajA function of a time-varying law;
represents ajThe nature of (a) to (b) is,
C-in which C is+Representing attributes including security, benefit, C-Representing attributes including time-consuming, cost; skOn behalf of the source of the information,
represents skThe concept and name set of (1);
represents skThe attribute set of (2);
represents skThe association set of (2);
represents skA set of features of;
the information unit is an instantiated knowledge element and is recorded as
The expression is as follows:
wherein the content of the first and second substances,
representing an element of knowledge, is represented by skThe resulting object oiCorresponding attribute ajThe value of (2) is obtained through instantiation processing and mapping between information and objects is realized;
the step of solving the objective weight of the information sequence specifically includes:
assuming that the number of information sequences in the fusion set is m, each sequence comprises n information units, and the n information units are in one-to-one correspondence with n fusion objects in the sequence, and the calculation process of the distance entropy value of each sequence is as follows:
setting the optimal information unit value in the jth information sequence as
To be provided with
As a reference value, an information element d describing the i (i ═ 1, 2, …, n) -th fusion object in the sequence is calculatedijThe euclidean distance from the reference value, namely:
aiming at the Euclidean distance, the sum of the Euclidean distances of all information units in the corresponding sequence is used
The distance entropy of the sequence is calculated on the basis of the ratio of the sequence to the sequence, and the expression is as follows:
calculating the objective weight of the information sequence j according to an entropy weight method as follows:
wherein e isjRepresenting the decision entropy value of the sequence j after normalization processing; the resulting weight wjSatisfies the following conditions: w is not less than 0jIs less than or equal to 1, and
the step of solving the global fusion result of the information specifically includes:
the local fusion weight of the information obtained by the solution is set as
And obtaining a local fusion result of the mutual information by combining linear weighting, wherein the local fusion result is expressed as follows:
wherein k is 1, 2, … p;
obtaining the local fusion result of each fusion object according to the formula, wherein the local fusion result of all the fusion objects is Zk＝{zk1，zk2，…zkn}；
Setting the calculated global fusion weight as
Local fusion result Z of combined informationkObtaining a global fusion result Z of the information by linear weighting, and expressingThe following were used:
preferably, the step of constructing the interactive interface information control feedback process based on the fuzzy adaptive PID controller specifically includes:
for each adaptive parameter K of the PID controllerp、KiAnd KdIs represented as follows:
Kp＝Kp0+ΔKp＝Kp0+{e，ec}Kp0
Ki＝Ki0+ΔKi＝Ki0+{e，ec}Ki0
Kd＝Kd0+ΔKd＝Kd0+ { e element ec}Kd0
Wherein, Kp0、Ki0And Kd0Representing the initial value of each parameter of the PID controller;
according to the selected membership degree of the PID controller, a control feedback result is obtained,
wherein c is an initial constant, e is a controlled amount deviation, ecIs the rate of change of deviation
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the embodiment of the invention, a reasoning adaptive control interactive behavior cognition model is applied to an intelligent education platform, and an interactive mode library is constructed from the cognition angle of human; describing an object and an information source of input information of an interactive interface into a knowledge element, and solving a local fusion value and a global fusion value of an interactive information sequence through entropy weight method weighting and linear weighting on the basis of obtaining an interactive information fusion set. And finally, taking the global fusion value of the interactive information as the input of a PID controller, completing the information interactive control process of the human-computer interface through a fuzzy self-adaptive PID control algorithm and feeding back the result. The method can optimize the control precision and the response rate.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for precisely controlling intelligent education based on adaptive cognitive interaction according to an embodiment of the present invention;
FIG. 2 is a basic framework diagram of an ACT-R cognitive model according to an embodiment of the present invention;
fig. 3 is a flowchart for solving a global fusion result of interactive information according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an information control refinement structure based on a fuzzy adaptive PID controller according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
An embodiment of the present invention provides a method for precisely controlling intelligent education based on adaptive cognitive interaction, as shown in fig. 1, the method including the steps of:
101, constructing an intelligent education platform interactive interface cognition module based on ACT-R;
102, constructing a cognitive interaction mode library;
103, constructing a global integration set of the interactive information;
and step 104, constructing an interactive interface information control feedback process based on the fuzzy self-adaptive PID controller.
Specifically, step 101 is to construct an interactive interface cognition module of the intelligent education platform based on ACT-R, and to study the intelligent education platform according to the cognitive habits and behavior tendencies of human beings, so that the system can execute various cognitive tasks of human beings.
FIG. 2 is a basic framework of an ACT-R cognitive model according to an embodiment of the present invention. As shown in fig. 2, the method for constructing the interactive interface cognition module of the intelligent education platform based on ACT-R mainly comprises the following steps:
step 201, constructing a target module based on a learning analysis technology of data mining.
Performing optimization and recombination on excellent education resources around the world through a learning analysis technology based on data mining, and establishing a target hierarchical system to store learning resources in various forms;
classifying different types of teaching contents, and storing the teaching contents into a database so as to meet the current target and intention of a user;
user preference and knowledge level information are collected, and a network course content system, a learning mode and teaching management which are exclusive to users are designed adaptively, so that targeted education is performed.
Step 202, constructing a visual module according to the teaching content structure layout.
Using means such as typesetting layout, dynamic effect, visual contrast and the like for the learning picture in the interactive process;
a network knowledge structure is formed through information navigation design, and a user preference access index table is established, so that the teaching content structure layout is balanced, and the arrangement of knowledge points is reasonable.
And step 203, constructing an action memory module according to the target action income and the execution action of the associated user.
According to the utility formula, the utility of an example i is:
wherein u isiShowing the utility of the example i,
initial value, P, representing the utility of instance iiRepresenting the probability of the current target being achieved, GiRepresents the yield after the current goal is completed, CiRepresenting an estimate of the cost required in achieving the goal.
And step 204, constructing a descriptive memory module according to memory retrieval and information extraction.
If the user wants to successfully extract the learned information from the memory, i.e. increase the information extracted into the cache space, the ACT-R model descriptive knowledge activation quantity is expressed as:
wherein, BiRepresenting a basic activation quantity of information, wjWeight of interest, S, representing informationjiIndicating the strength of the correlation.
Furthermore, based on the constructed target module, the visual module, the action memory module and the descriptive memory module, learning progress is dynamically perceived through a deep learning recommendation algorithm based on behavior data, and a learning sequence is adaptively optimized. The data of numerous students can be grabbed and counted, the characteristics of the students are measured and quantized to form a learning model, and therefore accurate pushing of different learning knowledge points is conducted according to different student conditions.
Further, the step 102 of constructing the cognitive interaction pattern library includes:
and integrating the cache information of the target module, the vision module, the action memory module and the descriptive memory module to generate coherent cognition and construct an intelligent education cognition interaction pattern library.
Further, as shown in fig. 3, the constructing a global integration set of interaction information in step 103 includes:
and 301, acquiring an interactive information fusion set.
Suppose that the input interactive information includes n objects to be fused with the same character, and the n objects are described as the knowledge elements of the fused object and recorded as the knowledge elements
The object to be fused has m associated attributes, and the associated attributes are described as attribute knowledge elements and are recorded as attribute knowledge elements
P associated information sources of the object to be fused are recorded as
The corresponding expression is:
wherein o isiRepresents the object to be fused and is to be fused,
and
each represents oiName set, attribute set, association set and feature set;
represents a pair oiAttribute ajDescription of (1);
represents a pair oiAttribute ajThe measurable characteristics comprise membership, linearity and nonlinearity, ambiguity and random probability;
represents ajA corresponding measurement of the balance;
for the description of ajA function of a time-varying law;
represents ajThe nature of (a) to (b) is,
C-in which C is+Representing attributes including security, benefit, C-Representing attributes including time-consuming, cost; skOn behalf of the source of the information,
represents skThe concept and name set of (1);
represents skThe attribute set of (2);
represents skThe association set of (2);
represents skA set of features of;
the information unit is an instantiated knowledge element and is recorded as
The expression is as follows:
wherein the content of the first and second substances,
representing an element of knowledge, is represented by skThe resulting object oiCorresponding attribute ajThe information unit is obtained through instantiation processing, and mapping between the information and the object is realized.
And step 302, solving the objective weight of the information sequence.
Assuming that the number of information sequences in the fusion set is m, each sequence comprises n information units, and the n information units are in one-to-one correspondence with n fusion objects in the sequence, and the calculation process of the distance entropy value of each sequence is as follows:
setting the optimal information unit value in the jth information sequence as
To be provided with
As a reference value, an information element d describing the i (i ═ 1, 2, …, n) -th fusion object in the sequence is calculatedijThe euclidean distance from the reference value, namely:
aiming at the Euclidean distance, the sum of the Euclidean distances of all information units in the corresponding sequence is used
The distance entropy of the sequence is calculated on the basis of the ratio of the sequence to the sequence, and the expression is as follows:
calculating the objective weight of the information sequence j according to an entropy weight method as follows:
wherein e isjRepresenting the decision entropy value of the sequence j after normalization processing; the resulting weight wjSatisfies the following conditions: w is not less than 0jIs less than or equal to 1, and
and step 303, solving a global fusion result of the information.
The local fusion weight of the information obtained by the solution is set as
And obtaining a local fusion result of the mutual information by combining linear weighting, wherein the local fusion result is expressed as follows:
wherein k is 1, 2, … p;
obtaining the local fusion result of each fusion object according to the formula, wherein the local fusion result of all the fusion objects is Zk＝{zk1，zk2，…zkn}；
Setting the calculated global fusion weight as
Local fusion result Z of combined informationkAnd obtaining a global fusion result Z of the information by linear weighting, wherein the expression is as follows:
further, as shown in fig. 4, the step 104 of constructing the interactive interface information control feedback process based on the fuzzy adaptive PID controller specifically includes:
for each adaptive parameter K of the PID controllerp、KiAnd KdIs represented as follows:
Kp＝Kp0+ΔKp＝Kp0+{e，ec}Kp0
Ki＝Ki0+ΔKi＝Ki0+{e，ec}Ki0
Kd＝Kd0+ΔKd＝Kd0+{e，ec}Kd0
wherein, Kp0、Ki0And Kd0Representing the initial value of each parameter of the PID controller;
according to the selected membership degree of the PID controller, a control feedback result is obtained,
wherein c is an initial constant, e is a controlled amount deviation, ecIs the rate of change of deviation.
In conclusion, by analyzing the basic framework and the cognitive mechanism of the ACT-R cognitive model, in the interactive mode of the intelligent education platform, according to the respective processing and caching characteristics of the target module, the vision module, the action memory module and the descriptive memory module, the design requirement is completed, and finally, an interactive cognitive mode library which accords with the cognitive habits and behavior modes of the human is obtained; the object to be fused obtains an information unit by combining knowledge instantiation processing through an improved knowledge meta-model, mapping between information and the object is realized, and an interactive information fusion set is obtained; defining the distance entropy value of each information unit by using Euclidean distance, and solving the local and global fusion result of the information through entropy weight method weighting and linear weighting; the global fusion result of the interactive information is used as an input value, the controllable quantity error and the error change rate are used as input variables, fuzzy reasoning is carried out through a fuzzy theory, parameters of the PID controller are adjusted in an online self-adaptive mode by inquiring a fuzzy matrix table, controller optimization is achieved, the controlled object is controlled by combining a fuzzy control rule and an extreme value control strategy, and learning information is fed back to the intelligent education platform interactive interface in real time. The method can obviously improve the control precision and the response rate.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A smart education method based on adaptive cognitive interaction for accurate control is characterized by comprising the following steps:
constructing an interactive interface cognition module of an intelligent education platform based on ACT-R;
constructing a cognitive interaction mode library;
constructing a global integration set of the interactive information;
and constructing an interactive interface information control feedback process based on the fuzzy self-adaptive PID controller.
2. The method for smart education based on adaptive cognitive interaction according to claim 1, wherein the step of constructing an interactive interface cognitive module of the smart education platform based on ACT-R includes:
constructing a target module based on a learning analysis technology of data mining;
constructing a visual module according to the structural layout of the teaching content;
constructing an action memory module according to the target action income and the execution action of the associated user;
constructing a descriptive memory module according to memory retrieval and information extraction;
based on the constructed target module, the visual module, the action memory module and the descriptive memory module, learning progress is dynamically perceived through a deep learning recommendation algorithm based on behavior data, a learning sequence is adaptively optimized, and learning knowledge points are accurately pushed according to different student conditions.
3. The method for intelligent education of precise control based on adaptive cognitive interaction as claimed in claim 2, wherein the step of building the target module based on learning analysis technique of data mining specifically comprises:
performing optimization and recombination on excellent education resources around the world through a learning analysis technology based on data mining, and establishing a target hierarchical system to store learning resources in various forms;
classifying different types of teaching contents, and storing the teaching contents into a database so as to meet the current target and intention of a user;
user preference and knowledge level information are collected, and a network course content system, a learning mode and teaching management which are exclusive to users are designed adaptively, so that targeted education is performed.
4. The method for intelligent education of precise control based on adaptive cognitive interaction as claimed in claim 2, wherein the step of constructing the visual module based on the structural layout of the instructional content includes:
using typesetting layout, dynamic effect and visual contrast means for the learning picture in the interactive process;
a network knowledge structure is formed through information navigation design, and a user preference access index table is established, so that the teaching content structure layout is balanced, and the arrangement of knowledge points is reasonable.
5. The adaptive cognitive interaction-based smart educational method for precise control based on, according to claim 2, wherein the step of constructing an action memory module based on the target action revenue and the associated user execution action specifically comprises:
according to the utility formula, the utility of an example i is:
wherein u isiShowing the utility of the example i,
initial value, P, representing the utility of instance iiRepresenting the probability of the current target being achieved, GiRepresents the yield after the current goal is completed, CiRepresenting an estimate of the cost required in achieving the goal.
6. The adaptive cognitive interaction-based smart educational method for precise control based on, according to claim 2, wherein the step of constructing the descriptive memory module based on memory retrieval and information extraction specifically comprises:
and extracting the learned information from the memory, and adding the learned information to a cache space, wherein the ACT-R model descriptive knowledge activation quantity is expressed as:
wherein, BiRepresenting a basic activation quantity of information, wjWeight of interest, S, representing informationjiIndicating the strength of the correlation.
7. The method for smart education based on adaptive cognitive interaction according to claim 2, wherein the step of constructing a cognitive interaction pattern library includes:
and integrating the cache information of the target module, the vision module, the action memory module and the descriptive memory module to generate coherent cognition and construct an intelligent education cognition interaction pattern library.
8. The adaptive cognitive interaction-based smart educational method for precise control according to claim 1, wherein the step of constructing a global integrated set of interaction information comprises:
acquiring an interactive information fusion set;
solving the objective weight of the information sequence;
and solving a global fusion result of the information.
9. The method for smart education based on adaptive cognitive interaction of claim 8, wherein the step of obtaining a fusion set of interaction information includes:
assuming that n objects to be fused with the same characters are included in the input interactive information, the input interactive information will beIt is described as a fusion object knowledge element, noted
The object to be fused has m associated attributes, and the associated attributes are described as attribute knowledge elements and are recorded as attribute knowledge elements
P associated information sources of the object to be fused are recorded as
The corresponding expression is:
wherein o isiRepresents the object to be fused and is to be fused,
and
each represents oiName set, attribute set, association set and feature set;
represents a pair oiAttribute ajDescription of (1);
represents a pair oiAttribute ajThe measurable characteristics comprise membership, linearity and nonlinearity, ambiguity and random probability;
represents ajA corresponding measurement of the balance;
for the description of ajA function of a time-varying law;
represents ajThe nature of (a) to (b) is,
C-in which C is+Representing attributes including security, benefit, C-Representing attributes including time-consuming, cost; skOn behalf of the source of the information,
represents skThe concept and name set of (1);
represents skThe attribute set of (2);
represents skThe association set of (2);
represents skA set of features of;
the information unit is an instantiated knowledge element and is recorded as
The expression is as follows:
wherein the content of the first and second substances,
representing an element of knowledge, is represented by skThe resulting object oiCorresponding attribute ajThe value of (2) is obtained through instantiation processing and mapping between information and objects is realized;
the step of solving the objective weight of the information sequence specifically includes:
assuming that the number of information sequences in the fusion set is m, each sequence comprises n information units, and the n information units are in one-to-one correspondence with n fusion objects in the sequence, and the calculation process of the distance entropy value of each sequence is as follows:
setting the optimal information unit value in the jth information sequence as
To be provided with
As a reference value, an information element d describing the i (i ═ 1, 2, …, n) -th fusion object in the sequence is calculatedijThe euclidean distance from the reference value, namely:
aiming at the Euclidean distance, the sum of the Euclidean distances of all information units in the corresponding sequence is used
The distance entropy of the sequence is calculated on the basis of the ratio of the sequence to the sequence, and the expression is as follows:
calculating the objective weight of the information sequence j according to an entropy weight method as follows:
wherein e isjRepresenting the decision entropy value of the sequence j after normalization processing; the resulting weight wjSatisfies the following conditions: w is not less than 0jIs less than or equal to 1, and
the step of solving the global fusion result of the information specifically includes:
the local fusion weight of the information obtained by the solution is set as
And obtaining a local fusion result of the mutual information by combining linear weighting, wherein the local fusion result is expressed as follows:
wherein k is 1, 2, … p;
obtaining the local fusion result of each fusion object according to the formula, wherein the local fusion result of all the fusion objects is Zk＝{zk1，zk2，…zkn}；
Setting the calculated global fusion weight as
Local fusion result Z of combined informationkAnd obtaining a global fusion result Z of the information by linear weighting, wherein the expression is as follows:
10. the method for smart education based on adaptive cognitive interaction of claim 1 wherein the step of constructing the feedback process of interactive interface information control based on fuzzy adaptive PID controller includes:
for each adaptive parameter K of the PID controllerp、KiAnd KdIs represented as follows:
Kp＝Kp0+ΔKp＝Kp0+{e，ec}Kp0
Ki＝Ki0+ΔKi＝Ki0+{e，ec}Ki0
Kd＝Kd0+ΔKd＝Kd0+{e，ec}Kd0
wherein, Kp0、Ki0And Kd0Representing the initial value of each parameter of the PID controller;
according to the selected membership degree of the PID controller, a control feedback result is obtained,
wherein c is an initial constant, e is a controlled amount deviation, ecIs the rate of change of deviation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011273387.XA CN112419810B (en) | 2020-11-13 | 2020-11-13 | Intelligent education method for accurate control based on adaptive cognitive interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011273387.XA CN112419810B (en) | 2020-11-13 | 2020-11-13 | Intelligent education method for accurate control based on adaptive cognitive interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112419810A true CN112419810A (en) | 2021-02-26 |
| CN112419810B CN112419810B (en) | 2023-01-20 |
Family
ID=74831277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011273387.XA Active CN112419810B (en) | 2020-11-13 | 2020-11-13 | Intelligent education method for accurate control based on adaptive cognitive interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112419810B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113495930A (en) * | 2021-05-21 | 2021-10-12 | 牟善军 | Global brain map construction method and system based on system thinking |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04122977A (en) * | 1990-09-14 | 1992-04-23 | Nippon Telegr & Teleph Corp <Ntt> | Simulator for operator training for small-diameter tunnel robot |
| CN102646200A (en) * | 2012-03-08 | 2012-08-22 | 武汉大学 | Image classifying method and system for self-adaption weight fusion of multiple classifiers |
| CN106205248A (en) * | 2016-08-31 | 2016-12-07 | 北京师范大学 | A kind of representative learning person generates system and method at the on-line study cognitive map of domain-specific knowledge learning and mastering state |
| CN107609651A (en) * | 2017-08-15 | 2018-01-19 | 华中师范大学 | A kind of design item appraisal procedure based on learner model |
| CN111179666A (en) * | 2020-02-17 | 2020-05-19 | 浙江创课网络科技有限公司 | Self-adaptive education system based on artificial intelligence |
-
2020
- 2020-11-13 CN CN202011273387.XA patent/CN112419810B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04122977A (en) * | 1990-09-14 | 1992-04-23 | Nippon Telegr & Teleph Corp <Ntt> | Simulator for operator training for small-diameter tunnel robot |
| CN102646200A (en) * | 2012-03-08 | 2012-08-22 | 武汉大学 | Image classifying method and system for self-adaption weight fusion of multiple classifiers |
| CN106205248A (en) * | 2016-08-31 | 2016-12-07 | 北京师范大学 | A kind of representative learning person generates system and method at the on-line study cognitive map of domain-specific knowledge learning and mastering state |
| CN107609651A (en) * | 2017-08-15 | 2018-01-19 | 华中师范大学 | A kind of design item appraisal procedure based on learner model |
| CN111179666A (en) * | 2020-02-17 | 2020-05-19 | 浙江创课网络科技有限公司 | Self-adaptive education system based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| 康晶晶，杨怀卿: "可视化编程环境下人机界面信息交互控制仿真", 《计算机仿真》 * |
| 张艳凤，王婷，曾佳俊: "基于推理思维自适应控制认知模型的移动阅读平台交互模式研究", 《人类工效学》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113495930A (en) * | 2021-05-21 | 2021-10-12 | 牟善军 | Global brain map construction method and system based on system thinking |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112419810B (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Asselman et al. | Enhancing the prediction of student performance based on the machine learning XGBoost algorithm | |
| CN108172047B (en) | A kind of network on-line study individualized resource real-time recommendation method | |
| Zhong et al. | Design of a personalized recommendation system for learning resources based on collaborative filtering | |
| Wenyan | Construction of network open teaching platform of analytical chemistry based on facial recognition and artificial intelligence | |
| Liu | The artistic design of user interaction experience for mobile systems based on context-awareness and machine learning | |
| CN112419810B (en) | Intelligent education method for accurate control based on adaptive cognitive interaction | |
| Xie et al. | Virtual reality primary school mathematics teaching system based on GIS data fusion | |
| Santhosh et al. | Machine learning based ideal job role fit and career recommendation system | |
| Li et al. | Practical Perception and Quality Evaluation for Teaching of Dynamic Visual Communication Design in the Context of Digital Media | |
| Deng et al. | Adaptive personalized recommendation based on adaptive learning | |
| Wang et al. | [Retracted] The Application of Motion Trajectory Acquisition and Intelligent Analysis Technology in Physical Education Teaching in Colleges and Universities | |
| Yang et al. | The Application of Interactive Humanoid Robots in the History Education of Museums Under Artificial Intelligence | |
| Lizarraga et al. | A new proposal for virtual academic advisories using chatbots | |
| Liu et al. | Framework Model of Personalized Learning Recommendation System Based on Deep Learning Under the Background of Big Data | |
| Huang et al. | Research and Design of College English Online Teaching based on Computer Aided Instruction Resource Library | |
| Shi et al. | Data Mining of English Language Instructional System Based on Improved Collaborative Filtering Algorithm | |
| Wu et al. | Digital Management of Teaching Cases in Colleges and Universities Based on Cluster Analysis. | |
| Liu et al. | The Optimization of Digital Art Teaching Platform based on Information Technology and Deep Learning | |
| Xiong | [Retracted] Construction of Teaching Mode of Film and TV Art in Institution of Higher Learning Using Virtual Simulation Technology | |
| Gao | Practice and Exploration of Completely Online Network Teaching with ID3 Algorithm | |
| Yang | Optimization of Physical Education Model Based on Cluster Analysis in the Context of Big Data | |
| Yu et al. | A AprioriAll Sequence Mining Algorithm Based on Learner Behavior | |
| Liu et al. | Optimization of Online Learning Resource Adaptation in Higher Education through Neural Network Approaches. | |
| Yuan et al. | Exploring the teaching practice of visual communication design in colleges and universities under the background of big data | |
| Mejia | A New Proposal for Virtual Academic Advisories Using ChatBots |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230703 Address after: Room 1901 (06), 19/F, Xingfu Building, No. 272, Huanghe North Road, Tianyuan District, Zhuzhou, Hunan Province, 412000 Patentee after: Hunan Runcheng Education Technology Co.,Ltd. Address before: 210042 Xuanwu Road, Xuanwu District, Nanjing, Jiangsu 699-1 Patentee before: LEIEN YOULI DATA TECHNOLOGY NANJING Co.,Ltd. |
|
| TR01 | Transfer of patent right |