CN110675297B - Computer digital teaching resource calling system and method - Google Patents
Computer digital teaching resource calling system and method Download PDFInfo
- Publication number
- CN110675297B CN110675297B CN201910952135.0A CN201910952135A CN110675297B CN 110675297 B CN110675297 B CN 110675297B CN 201910952135 A CN201910952135 A CN 201910952135A CN 110675297 B CN110675297 B CN 110675297B
- Authority
- CN
- China
- Prior art keywords
- resources
- teaching
- points
- question bank
- resource
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000013598 vector Substances 0.000 claims abstract description 50
- 239000011159 matrix material Substances 0.000 claims abstract description 44
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000007726 management method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims 1
- 239000000284 extract Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 5
- 230000009897 systematic effect Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 13
- 238000013507 mapping Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
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
- G06Q50/2053—Education institution selection, admissions, or financial aid
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A system and a method for calling computer digital teaching resources are provided. The invention establishes corresponding mark vector Q (Q) for teaching resources and question bank resources according to a subject knowledge system1,q2,…,q|N|And identifying the correlation degree between the resource and the corresponding numbered point by using the vector. After the user logs in the system, according to the final result of the user teaching progress matrix K ═ N, R, G, the convolutional neural network model CNN is used for confirming the teaching resources or question bank resources which the user needs to learn or train further, and the user's mastery conditions of each point in the subject knowledge system are updated according to the training result. The invention realizes the representation of the logical connection between knowledge points in the discipline by utilizing the matrix, and screens suitable teaching resources and question bank resources for learning through a convolutional neural network model CNN according to the internal logic of the discipline and the characteristics of a user. The invention can make the learning process of the user more systematic, and can guide the user to know the logical relation among the knowledge points in the subject, thereby having better teaching effect.
Description
Technical Field
The invention relates to the field of computer digital resource application, in particular to a system and a method for calling computer digital teaching resources.
Background
The existing teaching resources comprise various media material libraries, question libraries, case libraries, class libraries and the like. Various teaching resources have different resource types and storage modes, which cause difficulty in management and retrieval. At present, aiming at various teaching resources, a management and calling mode is generally adopted, and a file directory is mainly established for management. This management has the following problems:
1. the selection of keywords in a file directory can significantly affect the efficiency of retrieval. Because the amount of teaching resource information is huge, it is difficult to make the knowledge points corresponding to the teaching resources clear through a plurality of keywords. In particular, for resources such as courseware and cases, knowledge points covered in a single resource are often dense, and it is difficult to accurately correspond to an accurate position corresponding to a keyword in the comprehensive teaching resource through the limited keyword. Therefore, the existing teaching resource management mode is not beneficial to retrieval and comprehensive application of teaching resources.
2. The existing file directory can not clearly determine the corresponding knowledge points in the teaching resources, and is difficult to comprehensively and systematically demonstrate, teach and train the related knowledge points. The logical connection between teaching resources and the combing of a knowledge system still depend on the literacy of educators to a great extent. The existing teaching resources have great individual difference of teaching effects, and the difficulty of a student class after-clearing, reviewing and carding knowledge system is great.
Disclosure of Invention
The invention provides a system and a method for calling computer digital teaching resources, aiming at the defects of the prior art, the invention utilizes a matrix to represent the relation among all key points in a subject knowledge system, and screens proper resources for a user to learn through a convolutional neural network according to the relation and the user condition, thereby leading the school to be more systematic and efficient. The invention specifically adopts the following technical scheme.
Firstly, in order to achieve the above object, a method for calling a computer digital teaching resource is provided, which comprises the steps of: firstly, logging in an account; secondly, calling a teaching progress matrix K corresponding to the current account number as (N, R, G); wherein N ═ { N ═ N1,n2,…,n|N|Denotes a set of individual points in the subject knowledge system, with subscripts denoting the number of points, where | N | denotes the total number of points, and R ═ R1,r2,…,r|N|Represents a logical relationship matrix between the points in the subject knowledge system, G ═ G1,g2,…,g|N|Representing the mastery condition of the current account on each point in the subject knowledge system; second, according to G ═ G1,g2,…,g|N|Displaying the grasping conditions of the current account on all points in the subject knowledge system, and extracting the grasping conditions G of the current account on all points in the subject knowledge system by adopting a convolutional neural network model CNN according to a logic relation matrix R among all the pointsCharacteristic information of
Thirdly, the characteristic information extracted in the second step is processed
Performing max-posing processing to obtain a feature vector, extracting the numerical values of elements in the feature vector according to a Softmax function, and extracting the key points g corresponding to the elements in the extracted feature vectoriI is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, calling corresponding question bank resources for training and scoring a training result; fourthly, according to the training scoring result a ═ a1,a2,…,a|N|And updating the grasping conditions G-G of the current account number on all points in the subject knowledge system1,g2,…,g|N|}+{a1,a2,…,a|N|}; and fifthly, repeating the first step to the fourth step until the current account quits logging in.
Optionally, in the method for calling digital computer teaching resources, any element in a logical connection matrix R between each point in the subject knowledge system
Wherein any one of
Representing the degree of association between the key point with the number k and the key point with the number l; the training scoring result a ═ { a ═ a1,a2,…,al,…,a|N|In which any element alRepresents the scoring of the corresponding point with the number l in the question bank resources called by the training.
Optionally, in the method for calling any computer digital teaching resource, in the second step, the current account is extracted from each item in the subject knowledge system by using a convolutional neural network model CNN according to a logical link matrix R between each itemFeature information { c) corresponding to the grasping condition G of a pointg1,cg2,…,cg|N|The method specifically comprises the following steps: step 201, setting convolution layers according to the logic relation matrix R among the key points, wherein each convolution layer corresponds to a convolution kernel w and a coefficient corresponding to the logic relation matrix R
Wherein | W | represents the size of the convolution kernel W; step 202, each convolution layer is according to cj＝f(w×xj，j+h-1+ β b) and outputting the calculation result of the convolution layer as the input of the next convolution layer; wherein x isj，j+h-1Grasping conditions G ═ G indicating respective points1,g2,…,g|N|J element to j + h-1 element in the previous convolution layer, or j element to j + h-1 element in the calculation result of the previous convolution layer; h represents the window length, and h is a set value; b is a bias term; f is an activation function, and a ReLu function can be adopted as the activation function; step 203, superposing the calculation results of the convolution layers and outputting the feature information corresponding to the grasping condition G of each point
Optionally, in any of the methods for invoking digital teaching resources of a computer, the teaching resources and the question bank resources respectively correspond to their label vectors Q ═ Q1,q2,…,q|N|In which any element q islAnd expressing the degree of correlation between the teaching resource or question bank resource and the corresponding key point with the number l.
Optionally, in the third step, the feature vector is extracted according to the key point g corresponding to the element in the extracted feature vectoriAnd i is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, and calling corresponding question bank resources for training specifically comprises the following steps: calculating the mark vector Q ═ Q corresponding to each teaching resource and each question bank resource respectively1,q2,…,q|N|Selecting the teaching resources and question bank resources with the minimum Hamming distance from the Hamming distance of the feature vectors; outputting corresponding points g in the marked vectors Q from the screened teaching resources and question bank resourcesiThe element of (1) is the largest teaching resource and the question bank resource.
Meanwhile, in order to achieve the above object, the present invention further provides a system for calling computer digital teaching resources, comprising: the login management unit is used for storing an account number, a password and a corresponding teaching progress matrix K ═ N, R and G for each account number; logging in the account when the account and the password are verified to be correct, and after a login quitting instruction is received, exiting the currently logged-in account to update a teaching progress matrix K of the account to be (N, R, G); a display unit for displaying a display image according to G ═ G1,g2,…,g|N|Displaying the mastery condition of each point in the subject knowledge system by the current account, and the corresponding teaching resources and question bank resources; a storage unit for storing each teaching resource and question bank resource and the mark vector Q corresponding to each teaching resource and question bank resource { Q ═ Q }1,q2,…,q|N|Outputting corresponding teaching resources and question bank resources to the display unit according to the calling instruction of the control unit; the control unit is used for extracting feature information corresponding to the mastery condition G of each point in the subject knowledge system by the current account by adopting a convolutional neural network model CNN according to the logical link matrix R among the points
For the extracted characteristic information
Performing max-posing processing to obtain a feature vector, extracting the numerical values of elements in the feature vector according to a Softmax function, and extracting the key points g corresponding to the elements in the extracted feature vectoriI is more than or equal to 1 and less than or equal to | N |, and outputting an instruction for calling corresponding teaching resources and question bank resources; the control unit is also used for scoring the training resultAccording to the training scoring result a ═ { a ═ a1,a2,…,a|N|And updating the grasping conditions G-G of the current account number on all points in the subject knowledge system1,g2,…,g|N|}+{a1,a2,…,a|N|}。
Optionally, in the system for calling digital teaching resources from a computer, a format conversion module is further disposed between the storage unit and the control unit; the storage unit is also used for respectively storing attribute labels corresponding to the teaching resources; and when the storage unit outputs the teaching resources, the format conversion module inquires the corresponding attribute labels, generates an xml description file, and packages and outputs the teaching resources and the xml description file.
Optionally, in the system for invoking digital teaching resources of any computer, the storage unit is a server or a cloud platform with a data storage function, which is remotely connected through a network.
Optionally, in the system for invoking digital teaching resources by any computer, the storage unit is further configured to store the account and a password corresponding to the account, so that the login management unit invokes or verifies the account and the password.
Advantageous effects
The invention establishes corresponding mark vector Q (Q) for teaching resources and question bank resources according to a subject knowledge system1,q2,…,q|N|And identifying the correlation degree between the resource and the corresponding numbered point by using the vector. After the user logs in the system, according to the final result of the user teaching progress matrix K ═ N, R, G, the convolutional neural network model CNN is used for confirming the teaching resources or question bank resources which the user needs to learn or train further, and the user's mastery conditions of each point in the subject knowledge system are updated according to the training result. The invention realizes the representation of the logical connection between knowledge points in the discipline by utilizing the matrix, and screens suitable teaching resources and question bank resources for learning through a convolutional neural network model CNN according to the internal logic of the discipline and the characteristics of a user. The invention can make the learning process of the user betterThe teaching aid is systematized, and can guide a user to know the logical relation among knowledge points in the discipline, so that the teaching effect is better.
Further, in the convolutional neural network model CNN used in the present invention, each convolutional layer has a logical relation matrix R ═ { R ═ R corresponding to the discipline1,r2,…,r|N|Design is carried out. Therefore, the invention can be applied by training the logic relation matrix R ═ R without training the convolutional neural network model in a large scale1,r2,…,r|N|Design of the convolutional neural network model such that the convolutional neural network model matches the discipline. Therefore, the invention can adaptively transfer relevant teaching resources and question banks to learn and train according to the learning condition of the user per se accurately according to the characteristics of disciplines.
On the basis, in order to realize the effective storage, filing and calling of teaching resources and question bank resources, the invention carries out the pure and transmission of various resources by using the xml mode. By establishing a token vector Q ═ Q1,q2,…,q|N|And marking the knowledge points corresponding to the resources and the relation between the knowledge points, so that the resources matching with the CNN screening requirement can be accurately searched. And when the resources are output, calling the xml description file corresponding to the resources, and packaging and outputting the teaching resources and the xml description file. Therefore, the invention can effectively manage and output various resources with different forms and different formats, ensure that the resources can be correctly read, reduce the complexity of format conversion when displaying the resources and improve the resource acquisition efficiency.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method of invoking a computer digitized instructional resource of the present invention;
FIG. 2 is a block diagram of a computer digital teaching resource retrieval system of the present invention;
fig. 3 is a schematic diagram of a data retrieval process in the system of the present invention.
Detailed Description
In order to make the purpose and technical solution of the embodiments of the present invention clearer, the technical solution of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention without any inventive step, are within the scope of protection of the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
FIG. 1 is a method for calling a computer digital teaching resource according to the present invention, which includes the following steps:
firstly, logging in an account;
secondly, calling a teaching progress matrix K corresponding to the current account number as (N, R, G); wherein N ═ { N ═ N1,n2,…,n|N|Denotes a set of individual points in the subject knowledge system, with subscripts denoting the number of points, where | N | denotes the total number of points, and R ═ R1,r2,…,r|N|Represents a logical relationship matrix between the points in the subject knowledge system, G ═ G1,g2,…,g|N|Representing the mastery condition of the current account on each point in the subject knowledge system;
second, according to G ═ G1,g2,…,g|N|Displaying the grasping conditions of the current account on all points in the subject knowledge system, and extracting characteristic information corresponding to the grasping conditions G of the current account on all points in the subject knowledge system by adopting a convolutional neural network model CNN according to a logic relation matrix R between all points
Thirdly, the characteristic information extracted in the second step is processed
Performing max-posing processing to obtain a feature vector, extracting the numerical values of elements in the feature vector according to a Softmax function, and extracting the key points g corresponding to the elements in the extracted feature vectoriI is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, calling corresponding question bank resources for training and scoring a training result;
wherein, the max-posing treatment process comprises the following steps: the feature information is divided at different division depths, and the small blocks (posing sizes) with the same size obtained by division are only selected as the maximum value in each small block, other values are discarded, and then the original data structure is kept and output. Redundant information in the feature information can be further removed, and a feature vector can be obtained.
The step of extracting the numerical values of the elements in the feature vector according to a Softmax function comprises the following steps: expressing the numerical value of each element in the feature vector as an array V ═ V1,V2,…,Vi… }, calculating any element V in the arrayiSoftmax function value of
According to Softmax function SiAnd extracting each element in the feature vector according to the corresponding probability.
Fourthly, according to the training scoring result a ═ a1,a2,…,a|N|Updating each requirement in the subject knowledge system of the current accountGrasping condition of point G ═ G1,g2,…,g|N|}+{a1,a2,…,a|N|}；
And fifthly, repeating the first step to the fourth step until the current account quits logging in.
The above steps may be implemented by the system shown in fig. 2. The system comprises:
the login management unit is used for storing an account number, a password and a corresponding teaching progress matrix K ═ N, R and G for each account number; logging in the account when the account and the password are verified to be correct, and after a login quitting instruction is received, exiting the currently logged-in account to update a teaching progress matrix K of the account to be (N, R, G);
a display unit for displaying a display image according to G ═ G1,g2,…,g|N|Displaying the mastery condition of each point in the subject knowledge system by the current account, and the corresponding teaching resources and question bank resources;
a storage unit for storing each teaching resource and question bank resource and the mark vector Q corresponding to each teaching resource and question bank resource { Q ═ Q }1,q2,…,q|N|In which any element q islThe degree of correlation between the teaching resource or question bank resource and the key point with the corresponding number l is shown, so that the key point g corresponding to the element in the extracted feature vector can be output according to the calling instruction of the control unitiThe corresponding teaching resources and question bank resources are transmitted to the display unit;
the control unit is used for extracting feature information corresponding to the mastery condition G of each point in the subject knowledge system by the current account by adopting a convolutional neural network model CNN according to the logical link matrix R among the points
For the extracted characteristic information
Performing max-posing treatment to obtain a feature vector, wherein the numerical value of each element in the feature vector is SofExtracting the tmax function according to the points g corresponding to the elements in the extracted feature vectoriI is more than or equal to 1 and less than or equal to | N |, and outputting an instruction for calling corresponding teaching resources and question bank resources; the control unit is also used for scoring the training result and scoring according to the training result a ═ a1,a2,…,a|N|And updating the grasping conditions G-G of the current account number on all points in the subject knowledge system1,g2,…,g|N|}+{a1,a2,…,a|N|}。
A format conversion module can be further arranged between the storage unit and the control unit in the system: therefore, in the storage unit, the attribute labels corresponding to the teaching resources and the data content of the teaching resources can be stored separately, and the mapping relationship between the attribute labels and the data content of the teaching resources, such as the mapping relationship between storage addresses or a mapping table, can be called uniformly. In this way, when the storage unit outputs the teaching resource, the format conversion module firstly queries the attribute label corresponding to the teaching resource, generates an xml description file corresponding to the attribute label, and packages and outputs the data content of the teaching resource and the xml description file. And the display unit identifies data content according to the xml description file and then displays the data content on corresponding display equipment, such as a computer, a notebook, mobile equipment, projection equipment or tablet equipment, so that cross-system data reading and output are realized. Therefore, the method can be applied to different occasions such as computers, notebooks, mobile equipment, projection equipment or tablet equipment and the like, and is convenient for users.
The storage unit in the system can be selectively set as a server or a cloud platform with a data storage function connected remotely through a network, and can also be realized by using local storage resources. The server or the cloud platform can conveniently update various stored resources, ensure that the resources can correctly establish the relation with the knowledge points, and update the resources in real time, so that a user can obtain new resources in time. The storage unit can also be reused for storing the account and the password corresponding to the account for the login management unit to call or verify.
Wherein, Ginseng radixReferring to FIG. 3, in the system, the logical relationship matrix R is used to identify the relationship between the points in the subject knowledge system. Any element in the matrix
Wherein the content of the first and second substances,
indicates the degree of association between the point numbered k and the point numbered l.
In order to realize accurate characterization of the training result, considering that training contents in the question bank can simultaneously use different knowledge points to carry out comprehensive training, the training scoring result is designed to be a ═ { a ═1,a2,…,a|N|}. Using any of the elements alAnd expressing the degree of the relation between the question bank resources called by the training and the corresponding key point with the number l, so that the grasping degree of the key point by the user in the training is reflected by the grading of the element.
In fig. 3, in order to accurately screen the question bank resources and teaching resources suitable for the learning condition of the user, the feature information corresponding to the grasping condition G of each point in the subject knowledge system by the current account is extracted by using the convolutional neural network model CNN according to the logical link matrix R between the points
The method specifically comprises the following steps:
step 201, setting convolution layers according to the logic relation matrix R among the key points, wherein each convolution layer corresponds to a convolution kernel w and a coefficient corresponding to the logic relation matrix R
Wherein | W | represents the size of the convolution kernel W;
step 202, each convolution layer is according to cj＝f(w×xj，j+h-1+ beta b) and outputting the calculation result of the convolution layer as the next convolution layerInputting; wherein x isj，j+h-1Grasping conditions G ═ G indicating respective points1,g2,…,g|N|J element to j + h-1 element in the previous convolution layer, or j element to j + h-1 element in the calculation result of the previous convolution layer; h represents that the window length is a set value; b is a bias term; f can be selected as ReLu activation function;
step 203, superposing the calculation results of the convolution layers and outputting the feature information corresponding to the grasping condition G of each point
In the system, in order to accurately call the appropriate question bank resources and teaching resources, the key points g corresponding to the elements in the extracted feature vectors are usediAnd i is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, and the specific steps of calling and training corresponding question bank resources are designed as follows:
calculating the mark vector Q ═ Q corresponding to each teaching resource and each question bank resource respectively1,q2,…,q|N|Selecting the teaching resources and question bank resources with the minimum Hamming distance from the Hamming distance of the feature vectors;
outputting corresponding points g in the marked vectors Q from the screened teaching resources and question bank resourcesiThe element of (1) is the largest teaching resource and the question bank resource.
Therefore, according to the characteristics of the user and the subject, the corresponding teaching resources and question bank resources can be output on different learning platforms for the user to learn. The learning process can help the user to master the logic relation among all knowledge points in the subject, thereby obtaining better learning effect.
The above are merely embodiments of the present invention, which are described in detail and with particularity, and therefore should not be construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, various changes and modifications can be made without departing from the spirit of the present invention, and these changes and modifications are within the scope of the present invention.
Claims (5)
1. A method for calling a computer digital teaching resource is characterized by comprising the following steps:
firstly, logging in an account;
secondly, calling a teaching progress matrix K corresponding to the current account number as (N, R, G); wherein N ═ { N ═ N1,n2,…,n|N|Denotes a set of points in the subject knowledge system, where | N | denotes the total number of points, and R ═ R1,r2,…,r|N|Represents a logical relationship matrix between the points in the subject knowledge system, G ═ G1,g2,…,g|N|Representing the mastery condition of the current account on each point in a subject knowledge system, wherein any element in a logic relation matrix R between the points in the subject knowledge system
And l is more than or equal to 1 and less than or equal to | N |, wherein,
representing the degree of association between the key point with the number k and the key point with the number l;
according to G ═ G1,g2,…,g|N|Displaying the grasping conditions of the current account on all points in the subject knowledge system, and extracting characteristic information corresponding to the grasping conditions G of the current account on all points in the subject knowledge system by adopting a convolutional neural network model CNN according to a logic relation matrix R between all points
Thirdly, the characteristic information extracted in the second step is processed
Performing max-posing treatment to obtain a feature vector, and performing numerical value treatment on each element in the feature vectorExtracting according to a Softmax function, and extracting according to the key points g corresponding to the elements in the extracted feature vectorsiI is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, calling corresponding question bank resources for training and scoring a training result;
fourthly, according to the training scoring result a ═ a1,a2,…,a|N|And updating the grasping conditions G-G of the current account number on all points in the subject knowledge system1,g2,…,g|N|}+{a1,a2,…,a|N|Wherein the training scoring result a ═ a }1,a2,…,a|N|In which any element alThe evaluation of the key points with the number l corresponding to the question bank resources called by the training is shown;
fifthly, repeating the first step to the fourth step until the current account quits logging in;
in the second step, extracting feature information corresponding to the mastery condition G of the current account on each main point in the subject knowledge system by adopting a convolutional neural network model CNN according to a logical relation matrix R between the main points
The method specifically comprises the following steps:
step 201, setting convolution layers according to the logic relation matrix R among the key points, wherein each convolution layer corresponds to a convolution kernel w and a coefficient corresponding to the logic relation matrix R
Wherein | W | represents the size of the convolution kernel W;
step 202, each convolution layer is according to cj＝f(w×xj，j+h-1+ β b) and outputting the calculation result of the convolution layer as the input of the next convolution layer; wherein x isj，j+h-1Grasping conditions G ═ G indicating respective points1,g2,…,g|N|J (th) to j + h-1 (th)Elements, or the jth element to the j + h-1 element in the calculation result of the previous convolution layer; h represents that the window length is a set value; b is a bias term; f is an activation function;
step 203, superposing the calculation results of the convolution layers and outputting the feature information corresponding to the grasping condition G of each point
The teaching resources and the question bank resources respectively correspond to the mark vectors Q ═ { Q ═ Q1,q2,…,q|N|In which any element q islExpressing the correlation degree of the teaching resource or question bank resource and the key point with the corresponding serial number l;
wherein, in the third step, the key points g corresponding to the elements in the extracted feature vector are determinediAnd i is more than or equal to 1 and less than or equal to | N |, calling and outputting corresponding teaching resources, and calling corresponding question bank resources for training specifically comprises the following steps:
calculating the mark vector Q ═ Q corresponding to each teaching resource and each question bank resource respectively1,q2,…,q|N|Selecting the teaching resources and question bank resources with the minimum Hamming distance from the Hamming distance of the feature vectors;
outputting corresponding points g in the marked vectors Q from the screened teaching resources and question bank resourcesiThe element of (1) is the largest teaching resource and the question bank resource.
2. A computer digital teaching resource retrieval system, comprising:
the login management unit is used for storing an account number, a password and a corresponding teaching progress matrix K ═ N, R and G for each account number; logging in the account when the account and the password are verified to be correct, and updating a teaching progress matrix K of the account after receiving a log-out instruction and exiting the currently logged-in account, wherein the teaching progress matrix K is (N, R, G), and N is { N ═ N }1,n2,…,n|N|Denotes a set of individual points in a subject knowledge system, where | N | denotes a pointTotal number, R ═ R1,r2,…,r|N|Represents a logical relationship matrix between the points in the subject knowledge system, G ═ G1,g2,…,g|N|Representing the mastery condition of the current account on each point in a subject knowledge system, wherein any element in a logic relation matrix R between the points in the subject knowledge system
And l is more than or equal to 1 and less than or equal to | N |, wherein,
representing the degree of association between the key point with the number k and the key point with the number l;
a display unit for displaying a display image according to G ═ G1,g2,…,g|N|Displaying the mastery condition of each point in the subject knowledge system by the current account, and the corresponding teaching resources and question bank resources;
a storage unit for storing each teaching resource and question bank resource and the mark vector Q corresponding to each teaching resource and question bank resource { Q ═ Q }1,q2,…,q|N|Outputting corresponding teaching resources and question bank resources to the display unit according to the calling instruction of the control unit;
the control unit is used for extracting feature information corresponding to the mastery condition G of each point in the subject knowledge system by the current account by adopting a convolutional neural network model CNN according to the logical link matrix R among the points
For the extracted characteristic information
Performing max-posing processing to obtain a feature vector, extracting the numerical values of elements in the feature vector according to a Softmax function, and extracting the key points g corresponding to the elements in the extracted feature vectori，1≤i≤I, outputting an instruction for calling corresponding teaching resources and question bank resources; the control unit is also used for scoring the training result and scoring according to the training result a ═ a1,a2,…,a|N|And updating the grasping conditions G-G of the current account number on all points in the subject knowledge system1,g2,…,g|N|}+{a1,a2,…,a|N|}；
The control unit extracts feature information corresponding to the mastery condition G of the current account on each main point in the subject knowledge system by adopting a convolutional neural network model CNN according to a logical link matrix R between the main points
The method specifically comprises the following steps:
step 201, setting convolution layers according to the logic relation matrix R among the key points, wherein each convolution layer corresponds to a convolution kernel w and a coefficient corresponding to the logic relation matrix R
Wherein | W | represents the size of the convolution kernel W;
step 202, each convolution layer is according to cj＝f(w×xj，j+h-1+ β b) and outputting the calculation result of the convolution layer as the input of the next convolution layer; wherein x isj，j+h-1Grasping conditions G ═ G indicating respective points1,g2,…,g|N|J element to j + h-1 element in the previous convolution layer, or j element to j + h-1 element in the calculation result of the previous convolution layer; h represents that the window length is a set value; b is a bias term; f is an activation function;
step 203, superposing the calculation results of the convolution layers and outputting the feature information corresponding to the grasping condition G of each point
According to the liftingThe point g corresponding to the element in the feature vector is takeniAnd i is more than or equal to 1 and less than or equal to | N |, and the step of outputting the instruction for calling the corresponding teaching resources and question bank resources specifically comprises the following steps: calculating the mark vector Q ═ Q corresponding to each teaching resource and each question bank resource respectively1,q2,…,q|N|The Hamming distance between the resource and the characteristic vector, and the teaching resource and the question bank resource with the minimum Hamming distance are screened out, wherein any element Q in a marking vector QlExpressing the correlation degree of the teaching resource or question bank resource and the key point with the corresponding serial number l;
outputting corresponding points g in the marked vectors Q from the screened teaching resources and question bank resourcesiThe element of (1) is the largest teaching resource and the question bank resource.
3. The system for invoking computer digital teaching resources as claimed in claim 2, wherein a format conversion module is further disposed between said storage unit and said control unit;
the storage unit is also used for respectively storing attribute labels corresponding to the teaching resources;
and when the storage unit outputs the teaching resources, the format conversion module inquires the corresponding attribute labels, generates an xml description file, and packages and outputs the teaching resources and the xml description file.
4. The system for invoking computer digital teaching resources as claimed in claim 3, wherein said storage unit is a server or cloud platform with data storage function connected remotely through network.
5. The system for invoking computer digital teaching resources of claim 4, wherein the storage unit is further configured to store the account number and the password corresponding thereto for the login management unit to invoke or perform authentication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952135.0A CN110675297B (en) | 2019-10-09 | 2019-10-09 | Computer digital teaching resource calling system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952135.0A CN110675297B (en) | 2019-10-09 | 2019-10-09 | Computer digital teaching resource calling system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110675297A CN110675297A (en) | 2020-01-10 |
| CN110675297B true CN110675297B (en) | 2022-02-01 |
Family
ID=69081077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910952135.0A Active CN110675297B (en) | 2019-10-09 | 2019-10-09 | Computer digital teaching resource calling system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110675297B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116657A (en) * | 2013-03-11 | 2013-05-22 | 中国科学院自动化研究所 | Individual searching method of network teaching resource |
| CN104834747A (en) * | 2015-05-25 | 2015-08-12 | 中国科学院自动化研究所 | Short text classification method based on convolution neutral network |
| US9390370B2 (en) * | 2012-08-28 | 2016-07-12 | International Business Machines Corporation | Training deep neural network acoustic models using distributed hessian-free optimization |
| CN107403398A (en) * | 2017-07-18 | 2017-11-28 | 广州市沃迩德文化教育咨询服务有限公司 | A kind of English education internet platform and its application method |
| CN107895000A (en) * | 2017-10-30 | 2018-04-10 | 昆明理工大学 | A kind of cross-cutting semantic information retrieval method based on convolutional neural networks |
| CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
-
2019
- 2019-10-09 CN CN201910952135.0A patent/CN110675297B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9390370B2 (en) * | 2012-08-28 | 2016-07-12 | International Business Machines Corporation | Training deep neural network acoustic models using distributed hessian-free optimization |
| CN103116657A (en) * | 2013-03-11 | 2013-05-22 | 中国科学院自动化研究所 | Individual searching method of network teaching resource |
| CN104834747A (en) * | 2015-05-25 | 2015-08-12 | 中国科学院自动化研究所 | Short text classification method based on convolution neutral network |
| CN107403398A (en) * | 2017-07-18 | 2017-11-28 | 广州市沃迩德文化教育咨询服务有限公司 | A kind of English education internet platform and its application method |
| CN107895000A (en) * | 2017-10-30 | 2018-04-10 | 昆明理工大学 | A kind of cross-cutting semantic information retrieval method based on convolutional neural networks |
| CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
Non-Patent Citations (1)
| Title |
|---|
| "教学资源平台中的图像检索技术研究";王会朴;《中国优秀硕士学位论文全文数据库信息科技辑》;20170215(第2期);第I138-3891页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110675297A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11631338B2 (en) | Deep knowledge tracing with transformers | |
| CN108399414A (en) | Method of Sample Selection and device | |
| CN114020929B (en) | Intelligent education system platform design method based on course knowledge graph | |
| CN104021326B (en) | A kind of Teaching Methods and foreign language teaching aid | |
| CN111291940B (en) | Student class dropping prediction method based on Attention deep learning model | |
| CN104008453A (en) | Vocational ability evaluation simulation system | |
| CN109816265B (en) | Knowledge characteristic mastery degree evaluation method, question recommendation method and electronic equipment | |
| CN107403398A (en) | A kind of English education internet platform and its application method | |
| CN112559749B (en) | Intelligent matching method, device and storage medium for online education teachers and students | |
| CN114780723B (en) | Portrayal generation method, system and medium based on guide network text classification | |
| Li et al. | [Retracted] Application of Artificial Intelligence Technology in the Teaching of Complex Situations of Folk Music under the Vision of New Media Art | |
| CN111552796A (en) | Volume assembling method, electronic device and computer readable medium | |
| Swamy et al. | Deep knowledge tracing for free-form student code progression | |
| CN113283488B (en) | Learning behavior-based cognitive diagnosis method and system | |
| Xie | [Retracted] University Piano Education Visualization System under the Background of Distance Education Based on 5G Network | |
| CN110675297B (en) | Computer digital teaching resource calling system and method | |
| CN109471927A (en) | A kind of knowledge base and its foundation, answering method and application apparatus | |
| CN116402166A (en) | Training method and device of prediction model, electronic equipment and storage medium | |
| CN110210035A (en) | The training method of sequence labelling method, apparatus and sequence labelling model | |
| Wang et al. | [Retracted] Research on the Construction of Intelligent Media Ideological and Political Learning Platform Based on Artificial Intelligence Technology | |
| Chen et al. | [Retracted] Application of Network Information Technology in Physical Education and Training System under the Background of Big Data | |
| CN112785039B (en) | Prediction method and related device for answer score rate of test questions | |
| CN1869969A (en) | Intelligent language learning method and its system | |
| CN113254752A (en) | Lesson preparation method and device based on big data and storage medium | |
| CN113935869A (en) | Student subjective and objective factor combined score prediction method and system |
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 |