CN113743645B - Online education course recommendation method based on path factor fusion - Google Patents
Online education course recommendation method based on path factor fusion Download PDFInfo
- Publication number
- CN113743645B CN113743645B CN202110810736.5A CN202110810736A CN113743645B CN 113743645 B CN113743645 B CN 113743645B CN 202110810736 A CN202110810736 A CN 202110810736A CN 113743645 B CN113743645 B CN 113743645B
- Authority
- CN
- China
- Prior art keywords
- course
- path
- courses
- weight
- adjacent
- 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 30
- 230000004927 fusion Effects 0.000 title claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000010606 normalization Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 230000008092 positive effect Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 206010049040 Weight fluctuation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an online education course recommendation method based on path factor fusion, which is used for fusing path weight factors of adjacent courses, improving a user similarity calculation value, and simultaneously introducing a self-adaptive weight threshold into the recommendation method, so that the accuracy of online education course recommendation system recommendation is improved, and courses conforming to a professional learning direction are recommended to a user. Finally, a set of recommendation system which takes the user target and the interest as the guide and accords with the learning route is formed, and the method has very positive effect and profound significance on improving the learning efficiency of students.
Description
Technical Field
The invention relates to the field of intelligent recommendation, in particular to a method for recommending online education courses based on path factor fusion.
Background
With the continuous development of information technology, online education uses advanced technical means to move a classroom from offline to online, thereby overcoming the requirements and limitations of time and regions in the traditional education mode and simultaneously realizing the opportunity of more convenient acquisition of educational resources for users. However, with the continuous multiplication of internet teaching resources, users face new problems and confusion in online course selection. Firstly, learning has the characteristic of path, and related courses must be learned according to a knowledge path, otherwise, the learning effect is seriously affected by wrong course sequences; second, fragmented learning can result in a broken curriculum hierarchy that is detrimental to the user in establishing the correct knowledge structure.
Recommendation algorithms in the prior art are well established, but are often applied to application environments of non-path factors, such as commodity recommendation, etc. The advantages of such recommendation algorithms are manifested in: the method can efficiently recommend the content preferred by the user to the user through methods such as interest model matching, content analysis and the like, and saves a great deal of time cost. However, when the conventional recommendation algorithm recommends courses for users, a very accurate effect cannot be produced, because a certain path direction exists in learning among courses, but the conventional recommendation algorithm does not have the characteristic of sensing a learning path, so that the courses which should be subjected to next learning in the current learning state are not valued by a system, and the courses which are related to front and rear learning are difficult to recommend. The method has the advantages that higher requirements are put on course recommendation modes in online education, and recommended courses accord with a certain learning path.
The invention aims to solve the problems that how to combine online education and recommendation technologies, the students learn blindness and face the measure of course resources, and the students learn the course to need path directions, and form a learning mode that a user takes the target as a guide, so that the characteristics of a course recommendation system are exerted.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent course recommendation method based on path factor fusion in an online education application environment. The recommendation method comprises the following steps:
step 1), counting a learned course set I of the user on a trunk learning path;
step 2), obtaining a candidate recommended non-learned course set J which is closest to the learned course;
step 3) calculating the weight Route of the adjacent course paths between all the learned course sets I and the candidate un-learned course set J i,j The method comprises the steps of carrying out a first treatment on the surface of the Path weights of directly adjacent courses i and j are recorded as Route i,j The total number Num of users of the two adjacent courses is learned in sequence i,j Adjacent course path weight Route i,j Namely Num i,j The calculation formula is as follows:
Route i,j ＝Num i,j
step 4) normalizing the weight of each path, and maintaining the value range of the weight between 0 and 1 through normalization, wherein the normalization is carried out
Wherein GetRoute i,j Is the normalized adjacent course path weight, maxRoute, minRoute represents the maximum and minimum values in the adjacent course path respectively;
step 5) calculating the average value of the path weights after normalization processing:
wherein Threshold represents the average value of adjacent course path weights, getRoute i,j And the path weight of the adjacent courses after course normalization is represented, and N represents the total number of courses.
Step 6) counting directed paths from the learned course set I and directly connecting to the candidate recommended non-learned course set J;
step 7) calculating a compensation value M (i, j) of the path weight of the adjacent courses:
when the adjacent course path weight is greater than the threshold, the compensation weight is GetRoute i,j +1, and when it is less than the threshold, the compensation weight isIf the two courses are not directly adjacent, the compensation weight is 1;
step 8) calculating to obtain the similarity between courses, adding the compensation weight obtained by the calculation in the step 7) into calculation of the similarity of the courses to increase influence of the path weight, reducing influence of hot courses on the similarity of the courses, and calculating the similarity between courses by the following formula:
wherein sim (i, j) represents the similarity between course i and course j, and M (i, j) represents the compensation weight;
and 9) counting the sum of the similarity of the un-learned courses j and all the courses in the learned course set I, so as to obtain the preference degree of the user for the recommended un-learned courses j, and recommending the courses to the user according to the similarity ranking.
Further, the backbone learning path is constructed by:
step 1.1) integrating learning full paths of users in a historical data set, constructing a course learning full path of each user according to time sequences of learning courses of all users in the historical user set, and integrating the course learning full paths of all users;
step 1.2), denoising is carried out in the learning full path obtained by integration; in the denoising process, only adjacent course paths with weights greater than or equal to a set threshold value are reserved;
step 1.3) integrating the learning full path subjected to noise elimination processing to obtain a main learning path.
According to the online education course recommendation method provided by the invention, the adjacent course path weight factors are fused, the user similarity calculated value is improved, and the self-adaptive weight threshold is introduced into the recommendation method, so that the accuracy of online education course recommendation system recommendation is improved, and courses conforming to the professional learning direction are recommended to the user. Finally, a set of recommendation system which takes the user target and the interest as the guide and accords with the learning route is formed, and the method has very positive effect and profound significance on improving the learning efficiency of students.
Drawings
Fig. 1: the invention relates to a flow diagram of an online education course recommendation method
The specific embodiment is as follows:
the present invention will be described in further detail with reference to the following specific embodiments. FIG. 1 shows a flow of the online education course recommendation method of the present invention. In the course recommendation method of the present invention, first, a backbone learning path is constructed.
For convenience of description, the related terms in the present invention are described as follows:
adjacent course path: defined as the connection between two successive, adjacent courses during a set time window.
Adjacent course path weights: then it is defined as the number of people on the path of two courses that follow one another and are adjacent to one another in the set time window.
Course learning full path for a user: and obtaining a course learning path of the user according to the time sequence relation among the user behavior data.
Historical user set: all user data sets in the data set learn a specific professional related course.
Backbone learning path: for describing a backbone learning path between the specialty-related courses.
Constructing a backbone learning path includes the steps of:
step 1.1, integrating learning full paths of the historical dataset users. And constructing a course learning total path of each user according to the time sequence of the learning courses of each user in the historical user set, and integrating the course learning total paths of all users.
And 1.2, learning denoising processing in the full path. Because some users have the situation of obviously unreasonable wrong selection courses, paths with path weights which are obviously lower than the normal range exist in the full path learning, such as path weights of 1 or 2. Therefore, in the invention, the course path with lower weight of the adjacent course path is regarded as noise data, and noise reduction processing is needed. In the denoising process, only adjacent course paths with weights greater than or equal to a certain set threshold value are reserved. Therefore, the reliability of recommendation basis based on the historical user learning direction is improved, and the main learning path is further highlighted.
And step 1.3, branch path processing. In the branching path processing, only the weight within a certain proportion range of the maximum adjacent course path weight is reserved, so that the path within the maximum weight fluctuation range can be highlighted.
And obtaining a trunk learning path through the three steps.
Next, the intelligent course recommendation method based on path factor fusion specifically comprises the following steps:
(1) And counting a learned course set I of the user on a main learning path according to the current learning state of the user, wherein a specific learned course is recorded as I.
(2) And obtaining a candidate recommended non-learning course set J which is closest to the learned courses, wherein the specific candidate recommended non-learning course is marked as J. The calculation can be specifically performed according to an algorithm such as a collaborative filtering algorithm based on the item, and the like, and the method is not limited in the invention.
(3) Statistics of adjacent course path weights (weight for short)
Path weights of directly adjacent courses i and j are recorded as Route i,j The total number Num of users of the two adjacent courses is learned in sequence i,j Adjacent course path weight Route i,j Namely Num i,j The calculation formula is as follows:
Route i,j ＝Num i,j (formula-1)
(4) Normalizing adjacent course path weights
Obtaining the Route weight value Route of the adjacent courses i,j And normalizing the path weight of each adjacent course. The value range of the weight is kept to be 0,1 by normalization means]And thereby a normalized formula. Wherein GetRoute i,j Is a normalized adjacent course path weight, maxRoute, minRoute represents the maximum and minimum values in the adjacent course path, respectively.
(5) Adaptive adjacent course path weight threshold
In the existing collaborative filtering algorithm based on items, the influence of paths on course recommendation is not considered in the formula for calculating the similarity, so that most of recommended courses in a recommendation list of a recommendation system are popular courses and courses preferred by users in a concentrated mode. The hotter courses are more easily recommended, which results in a higher similarity between most of the popular courses, but does not truly account for the higher similarity between courses. Therefore, before similarity is calculated, the invention designs the path compensation value according to the path weight threshold value of the adjacent courses, and classifies the courses into two types. When the course path weight is greater than the threshold value, carrying out relevant compensation on the similarity of the course path weight and the threshold value, and improving the contribution of the adjacent course path weight to the similarity; when the adjacent course path weight is smaller than the adjacent course path weight threshold, the compensation for the correlation is further reduced.
Notably, the choice of the adjacent course path weight threshold directly determines Route i,j Contribution of (3). In order to avoid the judgment of threshold human errors, the invention adopts a self-adaptive method to set the threshold. The average value of all the normalized adjacent course path weights is obtained, and is not set by simple people. The threshold calculation formula is shown below.
Wherein Threshold represents the adjacent course path weight Threshold, getRoute i,j And the path weight of the adjacent courses after course normalization is represented, and N represents the total number of courses.
(4) Statistics of directed paths from the learned course set I, direct connection to the candidate recommended non-learned course set J, and setting of compensation values for path weights of adjacent courses
And adding the compensation value into a calculation formula of the similarity due to different path weights among different adjacent courses, and improving the influence component of the path factors. When the adjacent course path weight is greater than the threshold, the compensation weight is GetRoute i,j +1, and when it is less than the threshold, the compensation weight isTwo courses are not immediately adjacent, then their compensation weights are 1. In summary, the larger the weight of the path of the adjacent courses, i.e. the more people learn to select the path of the adjacent courses, the higher the contribution to the calculation of similarity between the two courses, and the greater the likelihood that the subsequent courses will be recommended to the user.
(5) Adding compensation weight to course similarity calculation
The invention adds the compensation weight into the similarity calculation to increase the influence of the path weight, reduce the influence of the hot courses on the course similarity, and the improved similarity calculation formula is shown as follows, wherein sim (i, j) represents the similarity between course i and course j, and M (i, j) represents the compensation weight.
(6) And counting the sum of the similarity of the un-learned courses j and all the courses in the learned course set I, so as to obtain the preference degree of the user for the recommended un-learned courses j, and recommending the courses to the user according to the similarity ranking.
According to the online education course recommendation method provided by the invention, the adjacent course path weight factors are fused, the user similarity calculated value is improved, and the self-adaptive weight threshold is introduced into the recommendation method, so that the accuracy of online education course recommendation system recommendation is improved, and courses conforming to the professional learning direction are recommended to the user. Finally, a set of recommendation system which takes the user target and the interest as the guide and accords with the learning route is formed, and the method has very positive effect and profound significance on improving the learning efficiency of students.
The foregoing is a further detailed description of the invention in connection with specific embodiments, and it is not intended that the invention be limited to such description. It will be apparent to those skilled in the art that several simple deductions or substitutions can be made without departing from the spirit of the invention, and all such modifications are to be considered as falling within the scope of the invention.
Claims (1)
1. An online education course recommendation method based on path factor fusion is characterized by comprising the following steps:
step 1), counting a learned course set I of a user on a trunk learning path;
step 2), obtaining a candidate recommended non-learned course set J which is closest to the learned course;
step 3) calculating the weight Route of the adjacent course paths between all the learned course sets I and the candidate un-learned course set J i,j The method comprises the steps of carrying out a first treatment on the surface of the Handle direct adjacent coursesPath weights for i and course j are noted as Route i,j The total number Num of users of the two adjacent courses is learned in sequence i,j Adjacent course path weight Route i,j Namely Num i,j The calculation formula is as follows:
Route i,j ＝Num i,j
step 4) normalizing the weight of each path, and maintaining the value range of the weight between 0 and 1 through normalization, wherein the normalization is carried out
Wherein GetRoute i,j Is the normalized adjacent course path weight, maxRoute, minRoute represents the maximum and minimum values in the adjacent course path respectively;
step 5) calculating the average value of the path weights after normalization processing:
wherein Threshold represents the average value of adjacent course path weights, getRoute i,j The path weight of adjacent courses after course normalization is represented, and N represents the total number of courses;
step 6) counting directed paths from the learned course set I and directly connecting to the candidate recommended non-learned course set J;
step 7) calculating a compensation value M (i, j) of the path weight of the adjacent courses:
when the adjacent course path weight is greater than the threshold, the compensation weight is GetRoute i,j +1, and when it is less than the threshold, the compensation weight isIf the two courses are not directly adjacent, the compensation weight is 1;
step 8) calculating to obtain the similarity between courses, adding the compensation weight obtained by the calculation in the step 7) into calculation of the similarity of the courses to increase influence of the path weight, reducing influence of hot courses on the similarity of the courses, and calculating the similarity between courses by the following formula:
wherein sim (i, j) represents the similarity between course i and course j, and M (i, j) represents the compensation weight;
step 9) counting the sum of the similarity of the un-learned courses j and all the courses in the learned course set I, so as to obtain the preference degree of the user for the recommended un-learned courses j, and recommending the courses to the user according to the similarity ranking;
the trunk learning path is constructed by the following method:
step 1.1) integrating learning full paths of users in a historical data set, constructing a course learning full path of each user according to time sequences of learning courses of all users in the historical user set, and integrating the course learning full paths of all users;
step 1.2), denoising is carried out in the learning full path obtained by integration; in the denoising process, only adjacent course paths with weights greater than or equal to a set threshold value are reserved;
step 1.3) integrating the learning full path subjected to noise elimination processing to obtain a main learning path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110810736.5A CN113743645B (en) | 2021-07-16 | 2021-07-16 | Online education course recommendation method based on path factor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110810736.5A CN113743645B (en) | 2021-07-16 | 2021-07-16 | Online education course recommendation method based on path factor fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743645A CN113743645A (en) | 2021-12-03 |
| CN113743645B true CN113743645B (en) | 2024-02-02 |
Family
ID=78728739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110810736.5A Active CN113743645B (en) | 2021-07-16 | 2021-07-16 | Online education course recommendation method based on path factor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743645B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN105389622A (en) * | 2015-10-20 | 2016-03-09 | 西安交通大学 | Multi-constraint learning path recommendation method based on knowledge map |
| CN106023015A (en) * | 2016-05-18 | 2016-10-12 | 腾讯科技（深圳）有限公司 | Course learning path recommending method and device |
| CN109447869A (en) * | 2018-12-06 | 2019-03-08 | 安徽教育网络出版有限公司 | The recommended method of course in a kind of online education |
| CN109816494A (en) * | 2019-01-31 | 2019-05-28 | 北京卡路里信息技术有限公司 | A kind of course recommended method, device, equipment and storage medium |
| CN109902128A (en) * | 2019-01-17 | 2019-06-18 | 平安科技（深圳）有限公司 | Learning path planing method, device, equipment and storage medium based on big data |
| KR102030149B1 (en) * | 2018-11-20 | 2019-10-08 | 주식회사 화성 | Method for recommending a customized curriculum and software education system by using the method |
| 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 |
| CN111581529A (en) * | 2020-05-07 | 2020-08-25 | 之江实验室 | Course recommendation method and device combining student fitness and course collocation degree |
| CN112163119A (en) * | 2020-09-29 | 2021-01-01 | 姜锡忠 | Big data online education platform course optimization method and system |
| CN112749805A (en) * | 2021-01-15 | 2021-05-04 | 浙江工业大学 | Online course recommendation method based on multiple entity relationships |
| US11024190B1 (en) * | 2019-06-04 | 2021-06-01 | Freedom Trail Realty School, Inc. | Online classes and learning compliance systems and methods |
| CN113065342A (en) * | 2021-03-22 | 2021-07-02 | 浙江工业大学 | Course recommendation method based on incidence relation analysis |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11908028B2 (en) * | 2014-03-17 | 2024-02-20 | Michael Olenick | Method and system for curriculum management services |
| US20200234606A1 (en) * | 2019-01-22 | 2020-07-23 | International Business Machines Corporation | Personalized educational planning based on user learning profile |
-
2021
- 2021-07-16 CN CN202110810736.5A patent/CN113743645B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN105389622A (en) * | 2015-10-20 | 2016-03-09 | 西安交通大学 | Multi-constraint learning path recommendation method based on knowledge map |
| CN106023015A (en) * | 2016-05-18 | 2016-10-12 | 腾讯科技（深圳）有限公司 | Course learning path recommending method and device |
| KR102030149B1 (en) * | 2018-11-20 | 2019-10-08 | 주식회사 화성 | Method for recommending a customized curriculum and software education system by using the method |
| CN109447869A (en) * | 2018-12-06 | 2019-03-08 | 安徽教育网络出版有限公司 | The recommended method of course in a kind of online education |
| CN109902128A (en) * | 2019-01-17 | 2019-06-18 | 平安科技（深圳）有限公司 | Learning path planing method, device, equipment and storage medium based on big data |
| CN109816494A (en) * | 2019-01-31 | 2019-05-28 | 北京卡路里信息技术有限公司 | A kind of course recommended method, device, equipment and storage medium |
| US11024190B1 (en) * | 2019-06-04 | 2021-06-01 | Freedom Trail Realty School, Inc. | Online classes and learning compliance systems and methods |
| 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 |
| CN111581529A (en) * | 2020-05-07 | 2020-08-25 | 之江实验室 | Course recommendation method and device combining student fitness and course collocation degree |
| CN112163119A (en) * | 2020-09-29 | 2021-01-01 | 姜锡忠 | Big data online education platform course optimization method and system |
| CN112749805A (en) * | 2021-01-15 | 2021-05-04 | 浙江工业大学 | Online course recommendation method based on multiple entity relationships |
| CN113065342A (en) * | 2021-03-22 | 2021-07-02 | 浙江工业大学 | Course recommendation method based on incidence relation analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743645A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213863B (en) | Learning style-based adaptive recommendation method and system | |
| CN108648049B (en) | Sequence recommendation method based on user behavior difference modeling | |
| US11687728B2 (en) | Text sentiment analysis method based on multi-level graph pooling | |
| CN108399428B (en) | Triple loss function design method based on trace ratio criterion | |
| CN111061856B (en) | Knowledge perception-based news recommendation method | |
| CN108804689A (en) | The label recommendation method of the fusion hidden connection relation of user towards answer platform | |
| CN111523029A (en) | Personalized recommendation method based on knowledge graph representation learning | |
| CN109492076B (en) | Community question-answer website answer credible evaluation method based on network | |
| CN111127146A (en) | Information recommendation method and system based on convolutional neural network and noise reduction self-encoder | |
| CN105139211A (en) | Product brief introduction generating method and system | |
| CN110825850B (en) | Natural language theme classification method and device | |
| CN112650886A (en) | Cross-modal video time retrieval method based on cross-modal dynamic convolution network | |
| CN108183956B (en) | Method for extracting key path of propagation network | |
| CN112990464B (en) | Knowledge tracking method and system | |
| CN114037945A (en) | Cross-modal retrieval method based on multi-granularity feature interaction | |
| CN113422761A (en) | Malicious social user detection method based on counterstudy | |
| CN114841164A (en) | Entity linking method, device, equipment and storage medium | |
| US20240168554A1 (en) | Domain adaptation method and system for gesture recognition | |
| CN112883289B (en) | PMF recommendation method based on social trust and tag semantic similarity | |
| CN111125428A (en) | Time-dependent movie recommendation method based on score prediction function fitting structure | |
| CN113743645B (en) | Online education course recommendation method based on path factor fusion | |
| Li et al. | An extended hesitant fuzzy set for modeling multi-source uncertainty and its applications in multiple-attribute decision-making | |
| WO2020135054A1 (en) | Method, device and apparatus for video recommendation and storage medium | |
| CN111339258A (en) | University computer basic exercise recommendation method based on knowledge graph | |
| CN113742586B (en) | Learning resource recommendation method and system based on knowledge graph embedding |
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 |