CN117830046A - Online course data cloud management system based on Internet - Google Patents
Online course data cloud management system based on Internet Download PDFInfo
- Publication number
- CN117830046A CN117830046A CN202410251535.XA CN202410251535A CN117830046A CN 117830046 A CN117830046 A CN 117830046A CN 202410251535 A CN202410251535 A CN 202410251535A CN 117830046 A CN117830046 A CN 117830046A
- Authority
- CN
- China
- Prior art keywords
- feature
- course
- user
- integrity
- access
- 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
- 239000011159 matrix material Substances 0.000 claims abstract description 184
- 230000007246 mechanism Effects 0.000 claims abstract description 100
- 230000003993 interaction Effects 0.000 claims abstract description 20
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 36
- 238000007726 management method Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Technology (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An online course data cloud management system based on the Internet relates to the technical field of online data analysis, and comprises an online course platform, wherein the online course platform is in communication connection with a data analysis module and a mechanism matching module; the data analysis module is used for acquiring the user characteristic integrity and the course characteristic integrity of the access user; the mechanism matching module starts different feature recommending mechanisms according to the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix at the current moment to generate a learning resource recommending list of the access user, and when the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix do not meet the standard, the history interaction record of the access user is obtained according to the access ID of the access user, and the relation feature recommending mechanism is started according to the history interaction record of the access user, so that the quality of personalized course resource recommending is improved.
Description
Technical Field
The invention relates to the technical field of online data analysis, in particular to an online course data cloud management system based on the Internet.
Background
The prior art CN117351794a "cloud platform-based online course management system" includes: the judging module detects the user behavior data, judges whether to delete courses, and sends course detection instructions when the courses are not deleted; the cloud storage module stores preset contrast of an interface picture and preset signal-to-noise ratio of audio; the contrast comparison module receives the course detection instruction to detect the contrast of the interface picture, and compares the contrast with a preset contrast to obtain a comparison result; the instruction sending module sends a picture repairing instruction when the contrast is smaller than a preset contrast, and sends an audio detection instruction when the contrast is larger than or equal to the preset contrast; the audio comparison module receives an audio detection instruction, detects audio in real time and compares the audio with a preset signal to noise ratio to obtain a comparison result; the course repair module repairs the picture contrast when receiving a picture repair instruction; and when the real-time signal-to-noise ratio is greater than or equal to the preset signal-to-noise ratio, the audio frequency is repaired, and the problem of accuracy of the course repairing process is solved.
Prior art CN116308913a "an intelligent course management system based on a cloud platform" includes: the data acquisition module is used for acquiring a plurality of corresponding data in the course operation process; the data processing module is used for calculating characteristic parameters from a plurality of corresponding data in the course operation process, wherein the characteristic parameters comprise a non-standard user quantity ratio, an average class listening time length and a user quantity increasing speed; the storage module is used for storing parameters in the data acquisition module and the data processing module respectively; the central control module is used for adjusting the course recommendation frequency to a first corresponding recommendation frequency according to the non-standard user quantity ratio, and adjusting the repeated course quantity ratio to a corresponding ratio according to the average course listening time when the condition that repeated courses are listened to is preliminarily judged to be out of the allowable range; the improvement of the operation efficiency and the operation stability is realized.
With the vigorous development of online learning, more and more schools, teachers and students recognize and actively participate in online learning, and through an online learning system, learners can obtain high-quality learning resources, most of the current online learning systems adopt a method combining content recommendation and cluster analysis, a personalized learning resource recommendation frame facing a virtual learning community is provided, but the method of content recommendation and cluster analysis is difficult to generate recommendation for new users or new courses, because enough data is lacking, effective prediction cannot be performed, and on the other hand, when the number of users and courses is large, user-course clusters can be sparse, so that similar users or courses are difficult to find.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an online course data cloud management system based on the Internet, which comprises an online course platform, wherein the online course platform is in communication connection with a data analysis module and a mechanism matching module;
the data analysis module acquires the user characteristic integrity and the course characteristic integrity of the access user according to the access user fixed attribute and the historical access record;
the mechanism matching module starts different feature recommendation mechanisms according to the user feature integrity of the user feature matrix and the course feature integrity of the course feature matrix of the access user at the current moment to generate a learning resource recommendation list of the access user, wherein the feature recommendation mechanisms comprise a course feature recommendation mechanism, a user feature recommendation mechanism and a comprehensive feature recommendation mechanism, and when the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix do not meet the standard, the history interaction record of the access user is obtained according to the access ID of the access user, and the relation feature recommendation mechanism is started according to the history interaction record of the access user.
Further, the process of the data analysis module obtaining the user characteristic integrity and the course characteristic integrity of the access user according to the access user fixed attribute and the history access record comprises the following steps:
presetting a user characteristic index of a user characteristic matrix of an access user and a course characteristic index of a course characteristic matrix;
when an access user logs in an online course platform through an access ID and a password, acquiring fixed attributes and historical access records of the access user according to the access ID, acquiring a user feature set and a course feature set of the access user according to the fixed attributes and the historical access records of the access user, and constructing a user feature matrix and a course feature matrix of the access user at the current moment according to user features in the user feature set and course features in the course feature set;
and acquiring the user feature integrity of the user feature matrix of the current access user and the course feature integrity of the course feature matrix according to the user feature matrix, the user feature index, the course feature matrix and the course feature index.
Further, the process of obtaining the user feature integrity of the user feature matrix of the current access user and the course feature integrity of the course feature matrix includes:
presetting weight factors of various types of user features in user feature indexes and weight factors of various types of course features in course feature indexes, performing type matching on various types of user features in the user feature indexes and various types of user features in a user feature matrix to obtain a matching result, adding scalar tags for various types of user features in the user feature indexes according to the matching result, and obtaining the user feature integrity of the user feature matrix according to the scalar tags and the weight factors of various types of user features in the user feature indexes;
and in the same way, performing type matching on the various types of course characteristics in the course characteristic indexes and the various types of course characteristics in the course characteristic matrix to obtain a matching result, adding scalar labels for the various types of course characteristics in the course characteristic indexes according to the matching result, and obtaining the course characteristic integrity of the course characteristic matrix according to the scalar labels and the weight factors of the various types of course characteristics in the course characteristic indexes.
Further, the mechanism matching module starts different feature recommendation mechanisms according to the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix at the current moment, and the process of producing the learning resource recommendation list of the access user comprises the following steps:
presetting a user feature integrity threshold and a course feature integrity threshold, and comparing the user feature integrity of a user feature matrix accessed by a user at the current moment and the course feature integrity of a course feature matrix with the user feature integrity threshold and the course feature integrity threshold respectively;
if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a course feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is less than or equal to the course feature integrity threshold, starting a user feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a comprehensive feature recommendation mechanism;
and if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is smaller than the course feature integrity threshold, starting a relation feature recommendation mechanism.
Further, the process of starting the course feature recommending mechanism by the mechanism matching module comprises the following steps:
acquiring a course feature matrix of an access user at the current moment, then acquiring historical course feature matrices of other access users in a data storage module, presetting a course feature similarity threshold and a course feature similarity base threshold, comparing the course feature matrix with a plurality of historical course feature matrices in course feature similarity, acquiring course feature similarity of the course feature matrix and each historical course feature matrix, screening out historical course feature matrices with the course feature similarity greater than or equal to the course feature similarity threshold, counting the total number of the historical course feature matrices, and comparing the total number with the course feature similarity base threshold;
if the total number is greater than or equal to the threshold value of the course feature similarity base, sequentially arranging the history course feature matrixes subjected to screening according to the course feature similarity of the history course feature matrixes, obtaining a history course feature matrix linked list, and constructing a learning resource recommendation list according to the history course feature matrix linked list, wherein the learning resource recommendation list is composed of course IDs in the course feature matrixes;
and if the total number is smaller than the threshold of the similarity base of the course features, starting a relation feature recommendation mechanism.
Further, the process of starting the user feature recommendation mechanism by the mechanism matching module comprises the following steps:
acquiring a user feature matrix of an access user at the current moment, then acquiring user feature matrices of other access users in a data storage module, presetting a user feature similarity threshold, comparing the user feature matrix of the access user with the user feature matrices of other access users, and acquiring the user feature similarity of the user feature matrix of the access user and the user feature matrix of other access users;
screening out other access users with user feature similarity greater than or equal to a user feature similarity threshold, acquiring other access users with highest user feature similarity, acquiring a course feature matrix and course feature integrity of the other access users, judging whether the course feature integrity is greater than or equal to a course feature integrity threshold, acquiring course scoring matrixes of the other access users according to the course feature matrix of the other access users if the course feature integrity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes, acquiring the course feature matrix of the other access users with second high user feature similarity if the course scoring matrix is not greater than or equal to the course scoring matrix, acquiring the course feature matrix of the other access users with second high user feature similarity and the course feature integrity of the other access users with second high user feature similarity, judging whether the course feature integrity is greater than or equal to the course feature integrity threshold, if the course feature matrix of the other access users with second high user feature similarity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes of the other access users with second high user feature similarity, and acquiring other recommendation lists of the user feature similarity;
and if the user feature similarity is greater than or equal to the user feature similarity threshold, starting a relationship feature recommendation mechanism if the course feature integrity of other access users is smaller than the course feature integrity threshold.
Further, the process of starting the comprehensive feature recommendation mechanism by the mechanism matching module comprises the following steps:
respectively acquiring a learning resource recommendation list generated by a course feature recommendation mechanism and a learning resource recommendation list generated by a user feature recommendation mechanism, constructing a comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism into the first position of the comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the secondary position of the comprehensive learning resource recommendation list, pushing the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism and the course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the comprehensive learning resource recommendation list in turn, and filling the course ID in the comprehensive learning resource recommendation list until the completion of filling the course ID in the comprehensive learning resource recommendation list.
Further, the process of starting the relationship feature recommendation mechanism by the mechanism matching module comprises the following steps:
acquiring a history interaction record of an access user according to an access ID of the access user, acquiring a demand coefficient matrix between the access user and other access users according to the history interaction record of the access user, simultaneously acquiring course scoring matrices of other access users, performing matrix fusion on the demand coefficient matrix and the course scoring matrix to acquire a demand coefficient course scoring matrix of the access user, and acquiring a learning resource recommendation list of the access user according to the demand coefficient course scoring matrix.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the fixed attribute of the access user and the history access record, the user characteristic integrity and the course characteristic integrity of the access user are obtained, when the situation that the user characteristic of the access user is missing but the course characteristic is complete is faced, a course characteristic recommendation mechanism is adopted, otherwise, when the situation that the course characteristic of the access user is missing but the user characteristic is complete is faced, the user characteristic recommendation mechanism is adopted, the accuracy of course recommendation is used as a final target, the user characteristic recommendation mechanism and the course characteristic recommendation mechanism are flexibly switched, and compared with the traditional method of conducting course recommendation by means of the user characteristic and the course characteristic, the individual learning requirement of a learner is better met, meanwhile, the course recommendation calculation resource is reduced, and the course recommendation accuracy is improved.
2. When the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix do not meet the standard, acquiring a history interaction record of the access user according to the access ID of the access user, acquiring a demand coefficient matrix between the access user and other access users according to the history interaction record of the access user, acquiring course scoring matrices of other access users, performing matrix fusion on the demand coefficient matrix and the course scoring matrix to acquire a demand coefficient course scoring matrix of the access user, and compensating missing data of the access user in a user feature recommendation mechanism and a course feature recommendation mechanism through the demand coefficient course scoring matrix, thereby improving the quality of personalized course resource recommendation.
Drawings
Fig. 1 is a schematic diagram of an online course data cloud management system based on the internet according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application, taken in conjunction with the accompanying drawings, clearly and completely describes the technical solutions of the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
As shown in fig. 1, an internet-based online course data cloud management system comprises an online course platform, wherein the online course platform is in communication connection with a data analysis module and a mechanism matching module;
the data analysis module acquires the user characteristic integrity and the course characteristic integrity of the access user according to the access user fixed attribute and the historical access record;
the mechanism matching module starts different feature recommendation mechanisms according to the user feature integrity of the user feature matrix and the course feature integrity of the course feature matrix of the access user at the current moment to generate a learning resource recommendation list of the access user, wherein the feature recommendation mechanisms comprise a course feature recommendation mechanism, a user feature recommendation mechanism and a comprehensive feature recommendation mechanism, and when the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix do not meet the standard, the history interaction record of the access user is obtained according to the access ID of the access user, and the relation feature recommendation mechanism is started according to the history interaction record of the access user.
It should be further noted that, in the implementation process, the process of the data analysis module obtaining the user feature integrity and the course feature integrity of the access user according to the fixed attribute and the history access record of the access user includes:
presetting a user characteristic index of a user characteristic matrix of an access user and a course characteristic index of a course characteristic matrix;
when an access user logs in an online course platform through an access ID and a password, acquiring fixed attributes and historical access records of the access user according to the access ID, acquiring a user feature set and a course feature set of the access user according to the fixed attributes and the historical access records of the access user, and constructing a user feature matrix and a course feature matrix of the access user at the current moment according to user features in the user feature set and course features in the course feature set;
the user fixed attribute comprises but is not limited to accessing registration information selected and filled by a user when the user registers on the platform, wherein the registration information comprises age, academy, favorite course category, occupation information, occupation target and the like, and the user characteristic index of the user characteristic matrix comprises but is not limited to age, academy, favorite course category, occupation information, occupation target and the like;
the history access records comprise, but are not limited to, scoring, browsing history, learning duration, praise times, forwarding times and the like of the access user on different course IDs, and course characteristic indexes of the course characteristic matrix comprise, but are not limited to, scoring, course category, browsing history, learning duration, praise times, forwarding times and the like corresponding to the different course IDs;
and acquiring the user feature integrity of the user feature matrix of the current access user and the course feature integrity of the course feature matrix according to the user feature matrix, the user feature index, the course feature matrix and the course feature index.
It should be further noted that, in the implementation process, the process of obtaining the user feature integrity of the user feature matrix of the current access user and the course feature integrity of the course feature matrix includes:
presetting weight factors of various types of user features in user feature indexes and weight factors of various types of course features in course feature indexes, performing type matching on various types of user features in the user feature indexes and various types of user features in a user feature matrix to obtain a matching result, adding scalar tags for various types of user features in the user feature indexes according to the matching result, and obtaining the user feature integrity of the user feature matrix according to the scalar tags and the weight factors of various types of user features in the user feature indexes;
and in the same way, performing type matching on the various types of course characteristics in the course characteristic indexes and the various types of course characteristics in the course characteristic matrix to obtain a matching result, adding scalar labels for the various types of course characteristics in the course characteristic indexes according to the matching result, and obtaining the course characteristic integrity of the course characteristic matrix according to the scalar labels and the weight factors of the various types of course characteristics in the course characteristic indexes.
It should be further noted that, in the implementation process, when the user feature type in the user feature matrix has a corresponding user feature type in the user feature index, that is, the type of user feature in the user feature index is successfully matched with the type of user feature in the user feature matrix, the scalar label of the type of user feature in the user feature index is set to 1, otherwise, the scalar label is set to 0, for example, the user feature of the user feature index includes age, academy, favorite course category, professional information and professional target, and the user feature of the user feature matrix includes only age, academy and professional information, the scalar label of the age, academy and professional information of the user feature index is set to 1, the scalar label of the favorite course category and professional target is set to 0, then the scalar label and the weight factor of the user feature index are weighted and averaged to obtain the user feature integrity of the user feature matrix, and the course feature integrity of the course feature matrix is obtained according to the above process.
It should be further noted that, in the implementation process, the mechanism matching module starts different feature recommendation mechanisms according to the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix at the current moment, and the process of producing the learning resource recommendation list of the access user includes:
presetting a user feature integrity threshold and a course feature integrity threshold, and comparing the user feature integrity of a user feature matrix accessed by a user at the current moment and the course feature integrity of a course feature matrix with the user feature integrity threshold and the course feature integrity threshold respectively;
if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a course feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is less than or equal to the course feature integrity threshold, starting a user feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a comprehensive feature recommendation mechanism;
and if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is smaller than the course feature integrity threshold, starting a relation feature recommendation mechanism.
It should be further noted that, in the implementation process, the process of the mechanism matching module starting the course feature recommending mechanism includes:
acquiring a course feature matrix of an access user at the current moment, then acquiring historical course feature matrices of other access users in a data storage module, presetting a course feature similarity threshold and a course feature similarity base threshold, comparing the course feature matrix with a plurality of historical course feature matrices in course feature similarity, acquiring course feature similarity of the course feature matrix and each historical course feature matrix, screening out historical course feature matrices with the course feature similarity greater than or equal to the course feature similarity threshold, counting the total number of the historical course feature matrices, and comparing the total number with the course feature similarity base threshold;
if the total number is greater than or equal to the threshold value of the course feature similarity base, sequentially arranging the history course feature matrixes after finishing screening according to the course feature similarity of the history course feature matrixes, obtaining a history course feature matrix linked list, and constructing a learning resource recommendation list according to the history course feature matrix linked list;
and if the total number is smaller than the threshold of the similarity base of the course features, starting a relation feature recommendation mechanism.
It should be further described that, in the specific implementation process, the process of sequentially arranging the history course feature matrices after completing the screening according to the course feature similarity of the history course feature matrices to obtain the history course feature matrix linked list includes:
constructing a history course feature matrix linked list, acquiring course IDs contained in a history course feature matrix of an access user from a data storage module, acquiring course IDs contained in the history course feature matrix after screening, judging whether the course IDs contained in the history course feature matrix after screening exist in the course IDs with consistent course IDs contained in the history course feature matrix of the access user, if so, eliminating the history course feature matrix to which the course IDs belong, avoiding that a learning resource recommendation list contains a course learned by the access user, then acquiring that the history course feature matrix with highest course feature similarity is positioned at the first position of the history course feature matrix linked list, and sequentially filling the history course feature matrix into the history course feature matrix linked list according to the course feature similarity, and then constructing a history resource recommendation list according to the course IDs contained in the history course feature matrix linked list.
It should be further noted that, in the implementation process, the process of the mechanism matching module starting the user feature recommendation mechanism includes:
acquiring a user feature matrix of an access user at the current moment, then acquiring user feature matrices of other access users in a data storage module, presetting a user feature similarity threshold, comparing the user feature matrix of the access user with the user feature matrices of other access users, and acquiring the user feature similarity of the user feature matrix of the access user and the user feature matrix of other access users;
screening out other access users with user feature similarity greater than or equal to a user feature similarity threshold, acquiring other access users with highest user feature similarity, acquiring a course feature matrix and course feature integrity of the other access users, judging whether the course feature integrity is greater than or equal to a course feature integrity threshold, acquiring course scoring matrixes of the other access users according to the course feature matrix of the other access users if the course feature integrity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes, acquiring the course feature matrix of the other access users with second high user feature similarity if the course scoring matrix is not greater than or equal to the course scoring matrix, acquiring the course feature matrix of the other access users with second high user feature similarity and the course feature integrity of the other access users with second high user feature similarity, judging whether the course feature integrity is greater than or equal to the course feature integrity threshold, if the course feature matrix of the other access users with second high user feature similarity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes of the other access users with second high user feature similarity, and acquiring other recommendation lists of the user feature similarity;
and if the user feature similarity is greater than or equal to the user feature similarity threshold, starting a relationship feature recommendation mechanism if the course feature integrity of other access users is smaller than the course feature integrity threshold.
It should be further noted that, in the implementation process, the course scoring matrix of other access users is obtained according to the course feature matrix of the access user, and the process of obtaining the learning resource recommendation list according to the course scoring matrix is as follows: and obtaining scores of other access users on each course ID according to the course feature matrix of the other access users, generating a course score matrix of the other access users according to the scores of the other access users on each course ID, and obtaining the top n course IDs with the highest scores from the course score matrix to form a learning resource recommendation list.
It should be further noted that, in the implementation process, the process of starting the comprehensive feature recommendation mechanism by the mechanism matching module includes:
respectively acquiring a learning resource recommendation list generated by a course feature recommendation mechanism and a learning resource recommendation list generated by a user feature recommendation mechanism, constructing a comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism into the first position of the comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the secondary position of the comprehensive learning resource recommendation list, pushing the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism and the course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the comprehensive learning resource recommendation list in turn, and filling the course ID in the comprehensive learning resource recommendation list until the completion of filling the course ID in the comprehensive learning resource recommendation list.
It should be further noted that, in the implementation process, the process of the mechanism matching module starting the relationship feature recommendation mechanism includes:
acquiring a history interaction record of an access user according to an access ID of the access user, acquiring a demand coefficient matrix between the access user and other access users according to the history interaction record of the access user, simultaneously acquiring course scoring matrices of other access users, performing matrix fusion on the demand coefficient matrix and the course scoring matrix to acquire a demand coefficient course scoring matrix of the access user, and acquiring a learning resource recommendation list of the access user according to the demand coefficient course scoring matrix.
It should be further noted that, in the implementation process, the online course platform is provided with a help evaluation system, after the visiting user views the published content of other visiting users, the visiting user can be given help scores, and the history interaction records of the visiting users include: the method comprises the steps that the number of praise times, the number of comments, the number of shares, the demand scores of the access users for other users and the average help scores of other access users with interaction records of the access users of other access users are obtained by the access users, the number of praise times, the number of comments, the number of shares, the demand scores of the access users for other users and the average help scores of other access users with interaction records of the access users are weighted average processed, the demand coefficients between the access users and the other access users are obtained, and a demand coefficient matrix is formed;
in the process of carrying out matrix fusion on the demand coefficient matrix and the course scoring matrix to obtain the demand coefficient course scoring matrix of the access user, a matrix fusion formula is as follows:
；
wherein,to access the user's demand coefficient course scoring matrix,to access a matrix of demand coefficients between users and other accessing users,scoring matrices for courses of other visiting users, ""means multiplication of elements at corresponding positions of the demand coefficient matrix and the course scoring matrix;
the scoring information of the access user for each course ID is obtained by means of the demand coefficient between the access user and other access users in the demand coefficient matrix and the scoring information of other access users for each course ID, and the scoring information calculation formula of the access user for each course ID is:
；
wherein,representing the scoring of course IDs by visiting user M;representing the scoring of course IDs by other visiting users K;representing a demand coefficient between the access user M and the other access users K; n represents the total number of other access users K for which access user M has a history of interactions.
Obtaining scoring information of the access user on each course ID according to the demand coefficient course scoring matrixAccording to the scoring informationThe learning resource recommendation list of the access user is built from high to low.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. An online course data cloud management system based on the Internet comprises an online course platform and is characterized in that the online course platform is in communication connection with a data analysis module and a mechanism matching module;
the data analysis module acquires the user characteristic integrity and the course characteristic integrity of the access user according to the access user fixed attribute and the historical access record;
the mechanism matching module starts different feature recommendation mechanisms according to the user feature integrity of the user feature matrix and the course feature integrity of the course feature matrix of the access user at the current moment to generate a learning resource recommendation list of the access user, wherein the feature recommendation mechanisms comprise a course feature recommendation mechanism, a user feature recommendation mechanism and a comprehensive feature recommendation mechanism, and when the user feature integrity of the user feature matrix of the access user and the course feature integrity of the course feature matrix do not meet the standard, the history interaction record of the access user is obtained according to the access ID of the access user, and the relation feature recommendation mechanism is started according to the history interaction record of the access user.
2. The internet-based online curriculum data cloud management system of claim 1, wherein said process of said data analysis module obtaining user feature integrity and curriculum feature integrity of an accessing user based on access user fixed attributes and historical access records comprises:
presetting a user characteristic index of a user characteristic matrix of an access user and a course characteristic index of a course characteristic matrix;
when an access user logs in an online course platform through an access ID and a password, acquiring fixed attributes and historical access records of the access user according to the access ID, acquiring a user feature set and a course feature set of the access user according to the fixed attributes and the historical access records of the access user, and constructing a user feature matrix and a course feature matrix of the access user at the current moment according to user features in the user feature set and course features in the course feature set;
and acquiring the user feature integrity of the user feature matrix of the current access user and the course feature integrity of the course feature matrix according to the user feature matrix, the user feature index, the course feature matrix and the course feature index.
3. The internet-based online lesson data cloud management system of claim 2, wherein the process of obtaining the user characteristic integrity of the user characteristic matrix of the currently accessed user and the lesson characteristic integrity of the lesson characteristic matrix comprises:
presetting weight factors of various types of user features in user feature indexes and weight factors of various types of course features in course feature indexes, performing type matching on various types of user features in the user feature indexes and various types of user features in a user feature matrix to obtain a matching result, adding scalar tags for various types of user features in the user feature indexes according to the matching result, and obtaining the user feature integrity of the user feature matrix according to the scalar tags and the weight factors of various types of user features in the user feature indexes;
and in the same way, performing type matching on the various types of course characteristics in the course characteristic indexes and the various types of course characteristics in the course characteristic matrix to obtain a matching result, adding scalar labels for the various types of course characteristics in the course characteristic indexes according to the matching result, and obtaining the course characteristic integrity of the course characteristic matrix according to the scalar labels and the weight factors of the various types of course characteristics in the course characteristic indexes.
4. The internet-based online course data cloud management system of claim 3, wherein said mechanism matching module initiates different feature recommendation mechanisms according to user feature integrity of a user feature matrix of a visiting user at a current time and course feature integrity of a course feature matrix, and the process of generating a learning resource recommendation list of the visiting user comprises:
presetting a user feature integrity threshold and a course feature integrity threshold, and comparing the user feature integrity of a user feature matrix accessed by a user at the current moment and the course feature integrity of a course feature matrix with the user feature integrity threshold and the course feature integrity threshold respectively;
if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a course feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is less than or equal to the course feature integrity threshold, starting a user feature recommendation mechanism;
if the user feature integrity is greater than or equal to the user feature integrity threshold and the course feature integrity is greater than or equal to the course feature integrity threshold, starting a comprehensive feature recommendation mechanism;
and if the user feature integrity is smaller than the user feature integrity threshold and the course feature integrity is smaller than the course feature integrity threshold, starting a relation feature recommendation mechanism.
5. The internet-based online curriculum data cloud management system of claim 4, wherein said mechanism matching module initiates a curriculum feature recommendation mechanism comprising:
acquiring a course feature matrix of an access user at the current moment, then acquiring historical course feature matrices of other access users in a data storage module, presetting a course feature similarity threshold and a course feature similarity base threshold, comparing the course feature matrix with a plurality of historical course feature matrices in course feature similarity, acquiring course feature similarity of the course feature matrix and each historical course feature matrix, screening out historical course feature matrices with the course feature similarity greater than or equal to the course feature similarity threshold, counting the total number of the historical course feature matrices, and comparing the total number with the course feature similarity base threshold;
if the total number is greater than or equal to the threshold value of the course feature similarity base, sequentially arranging the history course feature matrixes subjected to screening according to the course feature similarity of the history course feature matrixes, obtaining a history course feature matrix linked list, and constructing a learning resource recommendation list according to the history course feature matrix linked list, wherein the learning resource recommendation list is composed of course IDs in the course feature matrixes;
and if the total number is smaller than the threshold of the similarity base of the course features, starting a relation feature recommendation mechanism.
6. The internet-based online curriculum data cloud management system of claim 5, wherein said mechanism matching module initiates a user feature recommendation mechanism comprising:
acquiring a user feature matrix of an access user at the current moment, then acquiring user feature matrices of other access users in a data storage module, presetting a user feature similarity threshold, comparing the user feature matrix of the access user with the user feature matrices of other access users, and acquiring the user feature similarity of the user feature matrix of the access user and the user feature matrix of other access users;
screening out other access users with user feature similarity greater than or equal to a user feature similarity threshold, acquiring other access users with highest user feature similarity, acquiring a course feature matrix and course feature integrity of the other access users, judging whether the course feature integrity is greater than or equal to a course feature integrity threshold, acquiring course scoring matrixes of the other access users according to the course feature matrix of the other access users if the course feature integrity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes, acquiring the course feature matrix of the other access users with second high user feature similarity if the course scoring matrix is not greater than or equal to the course scoring matrix, acquiring the course feature matrix of the other access users with second high user feature similarity and the course feature integrity of the other access users with second high user feature similarity, judging whether the course feature integrity is greater than or equal to the course feature integrity threshold, if the course feature matrix of the other access users with second high user feature similarity is greater than or equal to the course feature integrity threshold, acquiring a learning resource recommendation list according to the course scoring matrixes of the other access users with second high user feature similarity, and acquiring other recommendation lists of the user feature similarity;
and if the user feature similarity is greater than or equal to the user feature similarity threshold, starting a relationship feature recommendation mechanism if the course feature integrity of other access users is smaller than the course feature integrity threshold.
7. The internet-based online curriculum data cloud management system of claim 6, wherein said mechanism matching module initiates a comprehensive feature recommendation mechanism comprising:
respectively acquiring a learning resource recommendation list generated by a course feature recommendation mechanism and a learning resource recommendation list generated by a user feature recommendation mechanism, constructing a comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism into the first position of the comprehensive learning resource recommendation list, filling the first course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the secondary position of the comprehensive learning resource recommendation list, pushing the first course ID in the learning resource recommendation list generated by the course feature recommendation mechanism and the course ID in the learning resource recommendation list generated by the user feature recommendation mechanism into the comprehensive learning resource recommendation list in turn, and filling the course ID in the comprehensive learning resource recommendation list until the completion of filling the course ID in the comprehensive learning resource recommendation list.
8. The internet-based online curriculum data cloud management system of claim 7, wherein said mechanism matching module initiates a process of relational feature recommendation mechanism comprising:
acquiring a history interaction record of an access user according to an access ID of the access user, acquiring a demand coefficient matrix between the access user and other access users according to the history interaction record of the access user, simultaneously acquiring course scoring matrices of other access users, performing matrix fusion on the demand coefficient matrix and the course scoring matrix to acquire a demand coefficient course scoring matrix of the access user, and acquiring a learning resource recommendation list of the access user according to the demand coefficient course scoring matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251535.XA CN117830046B (en) | 2024-03-06 | 2024-03-06 | Online course data cloud management system based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251535.XA CN117830046B (en) | 2024-03-06 | 2024-03-06 | Online course data cloud management system based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117830046A true CN117830046A (en) | 2024-04-05 |
| CN117830046B CN117830046B (en) | 2024-05-07 |
Family
ID=90524283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410251535.XA Active CN117830046B (en) | 2024-03-06 | 2024-03-06 | Online course data cloud management system based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117830046B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391687A (en) * | 2017-07-24 | 2017-11-24 | 华中师范大学 | A kind of mixing commending system towards local chronicle website |
| CN110990691A (en) * | 2019-11-14 | 2020-04-10 | 泰康保险集团股份有限公司 | Online course recommendation method and device and computer storage medium |
| CN112214670A (en) * | 2020-10-09 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Online course recommendation method and device, electronic equipment and storage medium |
| CN112948710A (en) * | 2021-03-22 | 2021-06-11 | 华南师范大学 | Graph neural network-based punishment education recommendation method, system and storage medium |
| US20210390394A1 (en) * | 2020-06-11 | 2021-12-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating recommendation model, content recommendation method and apparatus, device and medium |
| CN116521936A (en) * | 2023-06-30 | 2023-08-01 | 云南师范大学 | Course recommendation method and device based on user behavior analysis and storage medium |
| CN116628339A (en) * | 2023-06-09 | 2023-08-22 | 国信蓝桥教育科技股份有限公司 | Educational resource recommendation method and system based on artificial intelligence |
| KR20240011370A (en) * | 2022-07-19 | 2024-01-26 | 주식회사 유리프트 | Non face-to-face learning curriculum creation and recommendation system based on coding learning data |
| CN117593089A (en) * | 2023-12-04 | 2024-02-23 | 中国农业银行股份有限公司 | Credit card recommendation method, apparatus, device, storage medium and program product |
-
2024
- 2024-03-06 CN CN202410251535.XA patent/CN117830046B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391687A (en) * | 2017-07-24 | 2017-11-24 | 华中师范大学 | A kind of mixing commending system towards local chronicle website |
| CN110990691A (en) * | 2019-11-14 | 2020-04-10 | 泰康保险集团股份有限公司 | Online course recommendation method and device and computer storage medium |
| US20210390394A1 (en) * | 2020-06-11 | 2021-12-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating recommendation model, content recommendation method and apparatus, device and medium |
| CN112214670A (en) * | 2020-10-09 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Online course recommendation method and device, electronic equipment and storage medium |
| CN112948710A (en) * | 2021-03-22 | 2021-06-11 | 华南师范大学 | Graph neural network-based punishment education recommendation method, system and storage medium |
| KR20240011370A (en) * | 2022-07-19 | 2024-01-26 | 주식회사 유리프트 | Non face-to-face learning curriculum creation and recommendation system based on coding learning data |
| CN116628339A (en) * | 2023-06-09 | 2023-08-22 | 国信蓝桥教育科技股份有限公司 | Educational resource recommendation method and system based on artificial intelligence |
| CN116521936A (en) * | 2023-06-30 | 2023-08-01 | 云南师范大学 | Course recommendation method and device based on user behavior analysis and storage medium |
| CN117593089A (en) * | 2023-12-04 | 2024-02-23 | 中国农业银行股份有限公司 | Credit card recommendation method, apparatus, device, storage medium and program product |
Non-Patent Citations (1)
| Title |
|---|
| 周希禹: "自适应学习***中推荐方法的研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 16 December 2023 (2023-12-16) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117830046B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852347B (en) | Fire detection method using improved YOLO v3 | |
| CN109598995B (en) | Intelligent teaching system based on Bayesian knowledge tracking model | |
| CN106126524B (en) | Information pushing method and device | |
| CN111741330A (en) | Video content evaluation method and device, storage medium and computer equipment | |
| CN108322317A (en) | A kind of account identification correlating method and server | |
| CN112910961B (en) | Method and system for automatically evaluating video quality of network course | |
| CN112380429A (en) | Exercise recommendation method and device | |
| CN116958320A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN115563259A (en) | Multi-mode question and answer data acquisition method and device | |
| CN114492803A (en) | Knowledge graph-based question and answer generation method and device and automatic examination question generation system | |
| CN117830046B (en) | Online course data cloud management system based on Internet | |
| CN110996128B (en) | Online teaching video push management system | |
| CN115438152B (en) | Simple answer scoring method and system based on multi-neural network and knowledge graph | |
| CN116340625A (en) | Course recommendation method and device combining learning state fitness and course collocation degree | |
| CN111179666B (en) | Self-adaptive education system based on artificial intelligence | |
| CN115131180A (en) | Teaching application system based on artificial intelligence | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| CN112598553A (en) | Service system based on online learning and intelligent evaluation | |
| CN113869569A (en) | Learning score prediction and personalized intervention method based on decision tree | |
| CN116226678B (en) | Model processing method, device, equipment and storage medium | |
| CN112991077B (en) | Financial risk control system and method | |
| CN117218396B (en) | Automatic visual sample data labeling method and system based on large model | |
| CN113066327B (en) | Online intelligent education method for college students | |
| Li et al. | Design of Intelligent Push System for Teaching Resources Based on User Profile | |
| CN116303559B (en) | Method, system and storage medium for controlling form question and answer |
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 |