CN103886054A - Personalization recommendation system and method of network teaching resources - Google Patents
Personalization recommendation system and method of network teaching resources Download PDFInfo
- Publication number
- CN103886054A CN103886054A CN201410093793.6A CN201410093793A CN103886054A CN 103886054 A CN103886054 A CN 103886054A CN 201410093793 A CN201410093793 A CN 201410093793A CN 103886054 A CN103886054 A CN 103886054A
- Authority
- CN
- China
- Prior art keywords
- resource
- teacher
- course
- data
- label
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims description 33
- 230000003542 behavioural effect Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 21
- 230000009471 action Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 68
- 238000010586 diagram Methods 0.000 description 19
- 101100194363 Schizosaccharomyces pombe (strain 972 / ATCC 24843) res2 gene Proteins 0.000 description 10
- 230000000875 corresponding effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000002452 interceptive effect Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 101100194362 Schizosaccharomyces pombe (strain 972 / ATCC 24843) res1 gene Proteins 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Images
Classifications
-
- 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
Abstract
The invention discloses a recommendation system and method of network teaching resources. The system comprises a data establishing module, an off-line data processing module and an on-line recommendation module. The data establishing module establishes teacher behavior data, teacher model data, a course model data and resource model data. The off-line data processing module is used for initializing and adjusting course model data and resource model data, teacher behavior data are used for deducing teacher identities, the degree of association between the resources is computed according to the teacher behavior data, the similarity between the resources is computed according to the resource model data, and the degree of association between the resources and courses is computed according to the resource model data and the course model data. The on-line recommendation module describes on-line recommendation resources through the association degree between the resources, the similarity between the resources, the association degree between the courses and the resources and the dynamic states of teachers, and the on-line recommendation module transmits teacher behavior data to the teacher behavior data of the data establishing module according to the feedback recommendation resource labels of the teachers on the recommendation resources through UI interaction.
Description
Technical field
The present invention relates to computer internet technical field, relate in particular to a kind of personalized recommendation system and its implementation aspect networked teaching resource.
Background technology
Along with the emergence of E-Learning, network teaching resource is also increasing in swift and violent mode, the overload of information has brought many challenges to the person of teaching organization and learner, they have to spend a large amount of time and efforts, just can filter out the teaching resource that meets own demand, therefore, the commending system yielding unusually brilliant results at commercial field, also start to be applied to gradually education sector, it utilizes user's historical behavior data, carrying out personalization calculates, find user interest point, guiding user finds demand information or resource gradually, this to a great extent, improve user's working and learning efficiency.
Current popular proposed algorithm has collaborative filtering recommending (Collaborative filtering, be called for short CF), content-based recommendation (Content-based recommendation is called for short CB), recommendation (Knowledge-based recommendation) based on knowledge and mix recommendation (Hybrid recommendation) algorithm.Collaborative filtering is to recommend article according to the hobby before user and the close user's of other interest selection to user; Content-based recommendation, is mainly derived from information retrieval field, and its principle is to select in the past the content of article by analysis user, extracts text feature, in unselected article, according to text feature, calculates article similarity, realizes and recommending; Recommendation based on knowledge by and user between mutual, as limited the conditions such as purchasing price interval, brand, function, constantly approach user's psychology expection; Mixing proposed algorithm is by different modes, above three kinds of methods to be merged, and has complementary advantages, and realizes and recommending.
In conjunction with the recommend method of commercial field, researchist has proposed multiple commending system in E-Learning, is included in and in commending system, incorporates body construction, CB, CF and data mining mixed method etc.In formal middle and primary schools' teaching process, teacher need to prepare a large amount of teaching materials and data, prepares, and at home in middle and primary schools teaching for giving lessons, and exists the problems such as student's use book geographic difference, the horizontal level of teacher be uneven.At present a lot of commending systems recommend precision on the low side, directly use collaborative filtering method, lack the understanding understanding to course content, cause and recommend the out-of-date of resource, the degree of association problem on the low side of recommendation results and the task of course of preparing, and system is in the time of initial launch, adding of new user or new resources, lack historical behavior record, therefore easily cause user's historical behavior Sparse, and the problem such as cold start-up; Body is by the basic terms of specific area vocabulary and relation thereof, and define vocabulary off-balancesheet in conjunction with these terms and relation and prolong regular formalization and express, conventionally expert that need to this field builds and safeguards, in commending system, adopt body construction, need very large manpower and materials to drop into, therefore, need the one can be based on course content, can save labour turnover, recommend the personalized recommendation system of relevant teaching resource.
Summary of the invention
(1) technical matters that will solve
The technical matters that wish of the present invention solves is in formal teaching, how fully to excavate course content, incidence relation between analytic instruction resource content and resource, and how course, teaching resource and teacher's behavior are combined, the network teaching resource realizing based on tally set and teacher's behavior is recommended.
(2) technical scheme
The invention provides a sharp network teaching resource commending system, it is characterized in that, comprising:
Data construct module, it builds teacher's behavioral data, tutor model data, course prototype data, resource model data;
Off-line data processing module, it is for initialization and adjust course prototype data and resource model data, and utilize teacher's behavioral data to infer teacher's identity, according to the degree of association between teacher's behavioral data computational resource, according to the similarity between resource model data computational resource, calculate the degree of association between course and resource according to resource model data and course prototype data;
Online recommending module, it utilizes the degree of association of similarity, course and resource between the degree of association, the resource between resource, teacher's dynamic description to recommend online resource, also according to teacher, the feedback of recommending resource is recommended to resource tag, and the behavioral data that teacher is produced sends to data construct module, with beginning teacher's behavioral data more.
The present invention also provides a kind of network teaching resource recommend method, it is characterized in that, comprising:
Data construct step, it builds teacher's behavioral data, tutor model data, course prototype data, resource model data;
Off-line data treatment step, it is for initialization and adjust course prototype data and resource model data, and utilize teacher's behavioral data to infer teacher's identity, according to the degree of association between teacher's behavioral data computational resource, according to the similarity between resource model data computational resource, calculate the degree of association between course and resource according to resource model data and course prototype data;
Online recommendation step, it utilizes the degree of association of similarity, course and resource between the degree of association, the resource between resource, teacher's dynamic description to recommend online resource, also according to teacher, the feedback of recommending resource is recommended to resource tag, and the more beginning teacher's behavioral data of behavioral data producing according to teacher.
(3) beneficial effect
Can find out from technique scheme, the present invention has following beneficial effect:
For teacher user's characteristic and demand, from magnanimity resources bank, screening is suitable for teacher's teaching resource, overcomes the problem of Internet resources library information overload.
1, the present invention adopts Knowledge Decision-making tree construction, is the layout structure that uses books according to teaching, designs, meanwhile, use the paths in decision tree, represent the dynamic description of tutor model, under this tree structure, screen network of relation resource, can improve precision and the quality of recommendation.
2, the present invention adopts the recommend method of content-based and label, can effectively avoid cold start-up and Sparse Problem, the impact bringing to commending system.
3, the present invention uses association rule mining method, to there is the successional hypothesis of object based on same teacher operation at short notice, be translated into the problem that can use association rule mining method processing, calculate the degree of association between teaching resource, reduce in Sparse situation, use collaborative filtering to find the impact of neighbour's difficulty.
4, the present invention uses the methods such as latent semantic analysis, statistics, cluster, by teacher's behavior record, course label and resource tag are filtered to expansion, along with the increase of behavior record, it is more and more stable and accurate that course label in system and resource tag can become, and effectively reduces content-based recommend method in the inaccuracy of extracting keyword.
Brief description of the drawings
Fig. 1 is the structured flowchart of network teaching resource commending system in the present invention;
Fig. 2 is the data structure schematic diagram of tutor model module in the present invention;
Fig. 3 (a) is the data structure schematic diagram of course prototype module in the present invention;
Fig. 3 (b) is the explanation schematic diagram of Fig. 3 (a) symbol;
Fig. 4 is the data structure schematic diagram of resource model module in the present invention;
Fig. 5 (a) is the workflow schematic diagram of webcrawler module in the present invention;
Fig. 5 (b) is the workflow schematic diagram of Chinese version analysis module of the present invention;
Fig. 6 is the workflow schematic diagram that in the present invention, resource is mixed recommending module;
Fig. 7 is the method flow diagram of processed offline part in the recommend method of network teaching resource in the present invention;
Fig. 8 (a) shows the method flow diagram of online processing section in the recommend method of network teaching resource of the present invention;
Fig. 8 (b) shows in the present invention the detailed process schematic diagram of course selection in online processing section.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in further detail.
As shown in Figure 1, the invention discloses a kind of commending system of network teaching resource, this system is divided into data construct module, off-line data processing module and online recommending module, by teacher's behavior record module 101, tutor model 102, course prototype 103, resource model 104, teachers'action is described reasoning module 105, resource calculation of relationship degree module 110, course label adjusting module 106 and 107, resource tag adjusting module 108 and 109, course resources calculation of relationship degree module 111, resource similarity computing module 112, resource is mixed recommending module 113, label recommending module 114 and UI interactive module 115, totally 15 module compositions.Wherein, teacher's behavior record module 101, tutor model 102, course prototype 103 and resource model 104 composition datas build module, are the data bases of system; Teachers'action is described reasoning module 105, course label adjusting module 106 and 107, resource tag adjusting module 108 and 109, resource calculation of relationship degree module 110, course resources calculation of relationship degree module 111, resource similarity computing module 112 and is formed off-line data processing module, off-line data processing module is obtained corresponding data from data construct module, carries out analytical calculation; Resource is mixed recommending module 113, label recommending module 114 and UI interactive module 115 and is formed online recommending module, on the basis that online recommending module is analyzed at off-line module, different behaviors for teacher in UI interface, searching resource and resource tag, and these behaviors are collected in teacher's behavior record database of data construct module.Respectively these modules are introduced below.
Teacher's behavior record 101, for recording teacher in system platform, the various operations of carrying out, for personalized recommendation provides data basis.According to teacher's different behaviors, teacher's behavior record can be divided into teacher resource behavior record, teachers ' teaching task record and teacher's label behavior record.Teacher resource behavior record is to record teacher in UI interactive module 115, to the operation behavior of resource, comprise download, mark, collect, browse, as shown in table 1, each teacher has a teacher ID, each resource also has resource ID, behavior, teacher ID, resource ID and the running time of association store teacher to resource in teacher resource behavior record; Teachers ' teaching task record refers to that teacher is in UI interactive module 115, and the Instructional Design carrying out and the operation of preparing lessons are as shown in table 2, wherein association store teacher ID, course ID and teaching task content and the running time; Teacher's label behavior record refers in UI interactive module 115, and the operation that teacher carries out the resource tag of recommending comprises selection, amendment, deletes, as shown in table 3, wherein label and running time after association store teacher ID, resource ID, recommendation label, operation.
Table 1 teacher resource behavior record
Table 2 teachers ' teaching task record
Table 3 teacher label behavior record
Fig. 2 shows the data structure schematic diagram of tutor model module 102 in the present invention.As shown in Figure 2, its data structure comprises static description 201 and dynamically describes 202.Static description 201 refers to user's essential information, comprises teacher ID (system assignment), name, sex, address, education degree and Email etc.; Dynamically description 202 refers to the attribute of journey that teacher teaches, demarcate its position in course prototype knowledge tree, attribute comprises grade, subject, version, unit and course, and asking of attribute is set membership, and the knowledge tree of course prototype 103 is elaborated to this.Static description 201 is in the time that teacher registers, the information that need to complete.Dynamically the obtain manner of description 202 comprises two kinds, the one, and teacher logins the demonstration information feedback after platform, carries out online teaching task design, and the teacher of this process need login selects the attribute of course; The 2nd, system, according to teacher resource behavior record, is inferred teacher's dynamic description, and this part is described in reasoning 105 and introduced in detail at teachers'action.
Fig. 3 (a) shows the data structure schematic diagram of course prototype 103 in the present invention; Fig. 3 (b) shows in the present invention the explanation schematic diagram of symbol in course prototype.As shown in Fig. 3 (a) and 3 (b), described course prototype 103 comprises by knowledge tree 301 and course label 302.Knowledge tree is decision tree structure, according to curriculum attribute in teaching books, comprise grade, subject, version, unit and course, domestic primary and secondary teaching material layout is become to tree structure, the 0th layer of corresponding root node, for grade under judgement course, the judgement of subject under the 1st layer of corresponding course, the judgement of version under the 2nd layer of corresponding course, the judgement of unit under the 3rd layer of corresponding course, the judgement of the 4th layer of corresponding place course, the 5th layer is leaf node, for the concrete title of each course of teaching books, the word between each layer of line, is decision condition.Decision tree structure easy to understand and realization can be made feasible and respond well result to large data source within the relatively short time, utilize hierarchical structure can locate the dynamic description of tutor model, and make recommendation more accurate.Course label, for representing the content characteristic of course, its data structure is word dynamic set, as seven grades people teach edition course label of geographical " the first segment earth and terrestrial globe ": { latitude, warp, graticules, longitude, Beijing, map, distance, terrestrial globe, the earth, divides, geography, parallel }, initialization completes by course label adjusting module 106,107, afterwards, system off-line is processed teacher's teaching task content, constantly adjusts and optimizes course label.Knowledge tree 301 is based on the constructed decision tree of middle and primary schools' teaching books, and root node is that grade is judged; Grade is from first grade of primary school to Senior Three, and totally ten two grades classify; Subject comprises Chinese language, mathematics, English, politics, biology, history etc., and the foundation of subject decision condition is that the subject of offering according to grade is set; Version comprises the teaching material version that domestic education of middle and primary schools is used, and by above these nodes, can decision-making go out the books that teacher uses, as three grades Chinese language people teach version; Unit condition is the division of carrying out according to the catalogue of books, as first volume first module, volume two Unit the 3rd; After course node is judged, can obtain a certain concrete course.Certainly, knowledge tree is also not limited to middle and primary schools' teaching books, and it can be also the decision tree that other teaching datas build.The explanation of symbol in 303,304,305,306 and 307 corresponding diagram 3 (a) decision trees in Fig. 3 (b).According to this decision tree structure tissue teaching books, as three grades Chinese language people teach an edition first volume second unit " bullfinch ", can be presented in knowledge tree.Course label 302, represent the core content of course, its initialization, is completed by the web crawlers 106 in course label adjusting module in Fig. 1 and text analyzing 107, but because text analyzing is to obtain course label by computerized algorithm analysis, lack the semantic understanding for content of text, in the course label extracting, have the label lower with its degree of association, i.e. course label noise, needs constantly by teachers ' teaching task definition is analyzed, filtered noise is expanded course label simultaneously.
Fig. 4 shows the data structure schematic diagram of resource model 104 in the present invention.As shown in Figure 4, comprise resource ID 401, title 402, keyword 403, description 404 and resource tag 405.Resource ID 401 is default, and title 402, keyword 403 and description 404 are resource owner associated description to resource; Resource tag 405 represents the content characteristic of resource, its data structure is word dynamic set, as the resource tag of resource " earth movements " is: { turn in vain, the earth, revolution, motion }, its initialization, is completed by the resource content analysis 108 in resource tag adjusting module in Fig. 1 and resource tag analysis 109.Identical with course prototype, in resource tag, also there is noise, in resource tag, there is the label lower with the resource degree of association, by teacher's label behavior record is carried out to Algorithm Analysis, filtered noise, extended resources label.
Teachers'action is described reasoning module 105, it uses two kinds of method reasoning teachers' dynamic description, described two kinds of methods comprise: the one, and the resource content inference method based on knowledge tree: by calculating the degree of association between the course label that the resource tag that relates in teacher resource behavior record and knowledge tree leaf node are corresponding, carry out reasoning teacher's dynamic description.As: teacher 1801 registered address is Baoding, Hebei province, down loading network resource behavior within a period of time is as shown in table 1, the degree of association between the corresponding course label of the resource tag of computational resource 1,2,3 and knowledge tree leaf node, deducibility teacher 1801 journey of teaching is high school physics " Newton second law ", according to teacher 1801 registered address information, the version of deducibility teacher 1801 journey of teaching is behaved and is taught version, finally can in knowledge tree, orient the current information of giving lessons of teacher 1801 and be: high school physics people teaches an edition chapter 4 " 3 Newton second law ".The 2nd, Cooperative Reasoning method: the neighbour who finds any active ues, in k neighbour teacher, if certain teacher has clear and definite dynamically description, infer that any active ues has identical dynamic description, as: teacher 1802 has clear and definite dynamic description, and there is common behavior record to relate to resource with teacher 1801, therefore, can reasoning teacher 1 801 identical with dynamic description of the teacher 1 802.By the reasoning of dynamic description, can recommend the related resource of this joint or next joint, avoid the related resource of course before recommending, thereby make to recommend more accurate.
Course label adjusting module, input course prototype and teachers ' teaching task record, by web crawlers and text analyzing, course label corresponding to leaf node in output knowledge tree.Course label adjusting module, comprise webcrawler module 106 and text analysis model 107, described webcrawler module 106 is during for the initialization of course label, crawl the web page contents of course correlation connection, described text analysis model 107 is for extracting the content characteristic of input text, and described input text comprises the teachers ' teaching task record in web page contents and teacher's behavior record module 101 of the course correlation connection that webcrawler module 106 crawls.Particularly, described text analysis model 107 is according to processing procedure, dynamically adjust course label, if initialization procedure, extracts web page contents feature, merge Web Page Key Words by course, as course label, if makeover process, extracts teachers ' teaching task definition feature, use clustering method, the label liveness method of falling row and latent semantic analysis that course label is filtered and expanded.There is the quantity of the course of certain label in described clustering method analysis, the label that occurrence number is greater than to certain threshold value is deleted from course label, this is because the many labels of occurrence number, do not there is good separating capacity, as there is " teaching " in the course label of a lot of courses, this word can not be used for distinguishing these courses so, therefore needs to delete.The label of the label liveness extraction of falling discharge method teachers ' teaching task definition, and add up the frequency that each label occurs, as label liveness, by label low liveness, from course label, delete.Latent semantic analysis, for Give lecture-label matrix, uses matrix disassembling method, and the proper vector of solution matrix, utilizes distance metric methods analyst proper vector, solves the neighbour of label, expands course tag set.
Fig. 5 (a) and Fig. 5 (b) show respectively the workflow schematic diagram of described webcrawler module 106 and text analysis model 107.As shown in Fig. 5 (a), shown in the workflow of webcrawler module is specific as follows:
Step 501: select teaching books, as a Chinese language people teaches version;
Step 502: the title of extracting each course in teaching books;
Step 503: based on search engine technique, using course name as keyword, the related web page of search course;
Step 504: obtain web page listings and chained address;
Step 505: crawl the web page contents in list link;
Step 506: judge whether all teaching books finish, and if so, enter next stage, otherwise, jump to step 501, select next teaching books.
As shown in Fig. 5 (b), shown in the workflow of text analysis model is specific as follows:
Step 507: use TF-IDF algorithm to extract keyword from the web page contents of course correlation and teachers ' teaching task record, if the frequency TF that certain word or phrase occur in one section of article is high, and the reverse frequency IDF occurring in other articles is low, think that this word or phrase have good class discrimination ability, therefore extract it for keyword;
Step 508: press course and merge keyword, a set merged in the keyword that is about to the same course that extracts from different web pages and/or teachers ' teaching task record, as obtained the keyword of two webpages of course 1 by step 1, (course 1, webpage 1): { earth, revolution, turn in vain the sun, five bands, round the clock }, (course 1, webpage 2): { revolution, the sun, terrestrial globe, the earth, geography, five bands, round the clock }, merge into the course 1:{ earth, revolution, the sun, turn in vain terrestrial globe, geography, five bands, round the clock };
Step 509: according to input text content sources, adjust course label, if the web page contents that web crawlers crawls directly outputs to course label model 103 using keyword as course label; If the keyword set that teachers ' teaching task obtains, filters and expands the course label of course prototype.The method of filtering and expand has label liveness to fall to arrange, latent semantic analysis, clustering method etc.Label liveness falls row, refers to the keyword set obtaining according to teachers ' teaching task, and the statistics number of times that wherein each keyword occurs, filters the label that does not occur or often do not occur in course label; Latent semantic analysis, utilizes the method for svd to decompose course-label matrix, the neighbour of calculated characteristics vector, find the similarity between label, by and not word in course label high with course label similarity, join in course label, realize expanded function; Clustering method, is statistics everyday words, for example, in multiple course tag sets, all has " teaching ", and it can not represent the content characteristic of course, therefore filtered out.
Resource tag adjusting module, teacher's label behavior record and resource model, as input, use clustering method, the label liveness method of falling row and potential semantic approach, and resource tag is filtered and expanded.Resource tag adjusting module comprises resource content analysis module 108 and resource tag analysis module 109.Resource content analysis module 108 is by DF Algorithm Analysis resource title, keyword, description, and therefrom filter out resource tag, particularly, document frequency DF if there is certain word is high, this word does not have good separating capacity, removed, using all the other words as resource tag; Resource tag analysis module 109 is optimized after adjustment for resource tag that resource content analysis module 108 is filtered out and the resource tag of teacher's label behavior record, is exported to resource model.If at resource tag initialization procedure, it is directly outputed in resource model, table 4 is the resource model after resource tag initialization; If calculate teacher label behavior record gained, utilize label liveness to fall row, latent semantic analysis and clustering method statistics, filter and extended resources label.Label liveness falls row, and the number of times that in statistics resource tag, each keyword occurs, filters the label that does not occur or often do not occur in resource tag; Latent semantic analysis, utilize the method resource-label matrix of svd to decompose, the neighbour of calculated characteristics vector, finds the similarity between resource tag, and by and not word in resource tag high with resource tag similarity, join in resource tag; Clustering method is statistics everyday words, if it can not represent the content characteristic of resource, by its deletion.
The resource tag of table 4 resource model and extraction
The number of times occurring when Num (res1 ∩ res2) represents resl and res2 department;
Num (resl ∪ res2) represents the total degree that resl or res2 occur.
Suppose that the teacher resource behavior record that teacher 1801 and teacher 1802 carry out resource 1,2,3 is as shown in table 1.Teacher 1801 at short notice, has download behavior to resource 1,2,3, is converted into transaction record and is: the Resources list { 1,2,3} that transaction number is 1; Teacher 1802 at short notice, has download behavior to resource 2,3, but is the operation at second day to the behavior of resource 1, is converted into transaction record and is: the Resources list { 2,3}, the Resources list { 1} that transaction number is 3 that transaction number is 2.If it is 20 that multiple users have such behavior record number to resource 2,3 at short notice, i.e. Num (res2 ∩ res3)=20, and occur that the behavior record number of resource 2 is 25, the behavior record number that occurs resource 3 is 30,
Num (res2 ∪ res3)=Num (res2)+Num (res3)-Num (res2 ∩ res3)=25+30-20=35, the degree of association of resource 2,3 is relevance=20/35=0.571, if setting degree of association threshold value is 0.5≤relevance≤1, think and be associated resource the 2, the 3rd, the degree of association is 0.571.
Course resources label calculation of relationship degree module 111, course label and resource tag are as input, service range measure calculates the degree of association of course label and resource tag, use k near neighbor method or the lower resource of the setpoint distance threshold filtering degree of association, finally export the degree of association between course and resource.Distance metric method is selected formula 2, calculates the degree of association between course and resource, is not less than certain threshold value, thinks associated.
IntS (crs, res) represent set { tag|tag ∈ course label crs, and the element number of tag ∈ resource tag res}, SupS (crs, res) represent set { tag|tag ∈ course label crs, or the element number of tag ∈ resource tag res}.
Resource similarity computing module 112, input resource tag, the distance between service range measure computational resource, is used k near neighbor method or the lower resource of setpoint distance threshold filtering similarity, finally exports the similarity between resource and resource.Distance metric method is selected formula 3, and the similarity of computational resource 1 and resource 2, is not less than certain threshold value, thinks similar.If the tally set of resource 1 is { latitude, China, multimedia teaching, longitude, map, warp, graticules, parallel }, the tally set of resource 2 is { latitude, the world, multimedia teaching, longitude, map, warp, graticules, parallels }, sim=7/9=0778.
IntS (crs, res) represent set { tag|tag ∈ resource tag resl, and the element number of tag ∈ resource tag res2}, SupS (crs, res) represent set { tag|tag ∈ resource tag resl, or the element number of tag ∈ resource tag res2}.
Fig. 6 shows resource in the present invention and mixes the workflow schematic diagram of recommending module 113.As shown in Figure 6, carry out teaching resource recommendation alignment user, the data of utilizing processed offline to obtain, and according to the degree of association of the dynamic description of tutor model and course resources, calculate in conjunction with resource calculation of relationship degree and resource similarity, mix and recommend resource.
Step 601: judge that whether teacher's behavior is searching resource, if so, jumps to step 602, otherwise jumps to step 603;
Step 602: according to the query word of teacher's input, carrying out keyword with the resource tag in resource model mates, obtain the Resources list high with keyword matching degree, while serving as a teacher certain resource entering in the Resources list, as teacher's searched key word " li po ", system is in all resource models, carry out keyword coupling, obtain the Resources list: resource 1-li po .jpg, resource 2-li po .doc, resource 3-will enter wine .doc etc., serve as a teacher and click certain resource, as resource 3-will enter wine .doc, while entering into the detailed description interface of this resource, jump to step 604,
Step 603: process the result obtaining from course resources calculation of relationship degree module 111, filter out with tutor model and dynamically describe (grade, subject, version, unit, course) resource that the degree of association is higher, obtain the Resources list;
Step 604: in conjunction with resource calculation of relationship degree module 110 and resource similarity computing module 112, resource in searching and resource or the Resources list, the resource that the degree of association and similarity are higher, according to default weights, the degree of association and similarity to these resources are weighted, obtain related resource list, and the weight of each resource, as with resource 1 degree of association and the higher resource 2 of similarity, its degree of association is 0.8, similarity is 0.5, and default weights are respectively 0.6,0.4, and the weight of resource 2 is 0.8
*0.6+0.5
*0.4=0.68:
Step 605: fall to arrange according to weight height, recommend teaching resource.
Label recommending module 114, to use after resource teacher, recommend the respective labels of this resource to it, obtain teacher's feedback information, as teacher has downloaded " world map .jpg ", recommend " world ", " map ", " longitude ", " latitude ", " warp ", " parallel " etc. to it, teacher can modify to the label of recommending, selection, deletion action.
UI interactive module 115 is responsible for mutual between teacher, according to teacher's different behaviors, realizes personalized recommendation, meanwhile, collects the various operation behaviors of teacher in system, by these behavior records output, is kept in teacher's behavior record of data Layer.
The invention allows for a kind of recommend method of network teaching resource.The method comprises processed offline and online two parts flow process of processing.
Processed offline is by data and the model of off-line analysis data construct module, for online recommendation provides intermediate data, and analyzes teacher's behavioral data that data construct module is collected, and continues to optimize each model of data construct module.
Fig. 7 shows the method step process flow diagram of processed offline part in the recommend method of network teaching resource in the present invention.As shown in Figure 7, in described commending system, modules process can separately be moved, and is applicable to distributed parallel and calculates, and can, for the treatment of large data, be conducive to system extension.The step of processed offline part is as follows, and as can be seen from Figure 7, each step is asked independence and out-of-order relation mutually:
Step 701: obtain teacher resource behavior record from teacher's behavior record module 101, use teachers'action to describe reasoning module 105 teachers'action is described and carried out reasoning, obtain teacher's dynamic description; Use the resource degree of association in resource calculation of relationship degree module 110 computational resource models simultaneously;
Step 702: obtain course name from course prototype 103, by web crawlers 106 and the text analyzing 107 of course label adjusting module, the course label of described course is carried out to initialization; Obtain teachers ' teaching task record from teacher's behavior record module 101, by text analysis model 107, course label is filtered and expanded;
Step 703: Gains resources content from resource model 104, comprise resource title, keyword and description, analyze 109 by resource content analysis 108 and the resource tag of resource tag adjusting module, resource tag is carried out to initialization; Obtain teacher's label behavior record from teacher's behavior record module 101, by resource tag analysis module 109, resource tag is filtered and expanded;
Step 704: obtain respectively course prototype data and resource model data from course prototype 103 and resource model 104, both combinations, by course resources calculation of relationship degree module 111, calculate the course resources degree of association;
Step 705: from resource model 104, Gains resources model data, by resource similarity computing module 112, the similarity of asking of computational resource.
Fig. 8 (a) shows the method flow diagram of online processing section in the present invention.Online processing section ShiUI circle and, by with teacher ask mutual, realize resource recommendation and label to recommend, as shown in Figure 8, step is as follows:
Step 801: judge whether user registers: if so, log on as teacher; Otherwise, registered user, the new user's of system registry tutor model, registers new user's essential information, comprises teacher ID (system assignment), name, sex, address, education degree and Email etc.;
Step 802: judge teacher's behavior: serve as a teacher after logging in network platform, if preparation teaching task, as Online instructional design, prepare lessons etc. online, platform carries out step 803 course selection, if searching resource jumps to step 804, if carry out other behaviors, as manage individual resource, amendment information etc., jump to step 806;
Step 803: select course correlation attribute, and the dynamic description of explicitly obtaining teacher according to the selected course of teacher, comprising grade, subject, version, unit and course, amendment tutor model 102, jumps to step 807;
Step 804: teacher is inputted search word initiatively, searching resource, system is according to input keyword, carrying out keyword with the resource tag in resource model mates, obtain the Resources list high with keyword matching degree, as teacher's searched key word " li po ", system is in all resource models, carry out keyword coupling, obtain the Resources list: resource 1-li po .jpg, resource 2-li po .doc, resource 3-will enter wine .doc etc.;
Step 805: teacher is to certain resource operation in the Resources list, the resource similarity that the resource dependency degree that system obtains in conjunction with resource calculation of relationship degree module 110 and resource similarity computing module 112 obtain, use and mix recommending module 113, resource in searching and resource or the Resources list, the resource that the degree of association and similarity are higher, according to default weights, the degree of association and similarity to these resources are weighted, obtain related resource list, and the weight of each resource, as with resource 1 degree of association and the higher resource 2 of similarity, its degree of association is 0.8, similarity is 0.5, default weights are respectively 0.6, 0.4,
The weight of resource 2 is 0.8*0.6+0.5*0.4=0.68; Recommend teaching resource according to weight height, jump to step 808;
Step 806: system is extracted the dynamic description of tutor model 102;
Step 807: recommend teaching resource by resource recommendation module: resource recommendation module is according to the dynamic description of tutor model 102, in conjunction with resource calculation of relationship degree module 110, course resources calculation of relationship degree module 111 and resource similarity computing module 112, use mixing recommending module 113 to process the result obtaining from course resources calculation of relationship degree module 111, filter out with tutor model and dynamically describe (grade, subject, version, unit, course) resource that the degree of association is higher, obtain the Resources list; In conjunction with resource calculation of relationship degree module 110 and resource similarity computing module 112, resource in searching and resource or the Resources list, the resource that the degree of association and similarity are higher, according to default weights, the degree of association and similarity to these resources are weighted, obtain related resource list, and the weight of each resource; Recommend teaching resource according to weight height, jump to step 808;
Step 808: system acquisition teacher resource behavior feedback information, as downloaded, browse, scoring etc., and is saved in teacher's resource behavior record and teaching task record in teacher's behavior record module 101;
Step 809: according to teacher resource behavior feedback, resource tag recommending module is recommended relevant resource tag, as teacher has downloaded resource " heliocentric theory .jpg ", by the resource tag { meaning of this resource, Copernius, theory, core content, heliocentric theory, open, increase the visual field } recommend teacher;
Step 810: collect the feedback of teacher to label, comprise the behaviors such as selection, deletion, amendment, and teacher's label behavior record is saved in to teacher's behavior record module 101, as the resource tag of teacher to the resource " heliocentric theory .jpg " of recommending, select " heliocentric theory " and " Copernius ", delete " meaning ", " theory ", " open ", " increase ", " visual field ";
Step 811: judge that whether teacher exits, and if so, exits; Otherwise, jump procedure 802.
The operation behavior that teacher carries out in UI module, all will output in teacher's behavior record of data construct module, for processed offline.
Fig. 8 (b) shows the course selection detailed process of step 803 in the present invention.As shown in Fig. 8 (b), this step comprises:
Step 812: select grade;
Step 813: select subject;
Step 814: select version;
Step 815: selected cell;
Step 816: select specific course.
System and method disclosed by the invention can be recommended as required teacher user by resources of interest fast and accurately in magnanimity teaching resource, effectively overcome Internet resources library information overload problem, reduce teacher's workload, in order to complete Instructional Design, prepare lessons etc., teaching task facilitates.Meanwhile, the present invention can effectively reduce the impact that cold start-up and Sparse Problem bring, and has improved the interactivity that system and teacher ask, for the personalized recommendation of network teaching resource provides a kind of pervasive method.
Above-described specific embodiment; object of the present invention, technical scheme and beneficial effect are further described; be understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment of making, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. a network teaching resource commending system, is characterized in that, comprising:
Data construct module, it builds teacher's behavioral data, tutor model data, course prototype data, resource model data;
Off-line data processing module, it is for initialization and adjust course prototype data and resource model data, and utilize teacher's behavioral data to infer teacher's identity, according to the degree of association between teacher's behavioral data computational resource, according to the similarity between resource model data computational resource, calculate the degree of association between course and resource according to resource model data and course prototype data;
Online recommending module, it utilizes the degree of association of similarity, course and resource between the degree of association, the resource between resource, teacher's dynamic description to recommend online resource, also according to teacher, the feedback of recommending resource is recommended to resource tag, and the behavioral data that teacher is produced sends to data construct module, with beginning teacher's behavioral data more.
2. the system as claimed in claim 1, is characterized in that,
Described teacher's behavioral data comprises: teacher resource behavior record, teachers ' teaching task record and teacher's label behavior record, wherein teacher resource behavior record comprises the behavior of teacher to resource, teachers ' teaching task record comprises the Instructional Design that teacher carries out and the operation of preparing lessons, and teacher's label behavior record comprises the operation of teacher to resource tag;
Described tutor model data comprise that teacher's static state is described and dynamically description, and the static essential information of describing teacher of the giving advice, dynamically describes the attribute that comprises journey that teacher teaches;
Described course prototype data comprise knowledge tree and course label; Described knowledge tree adopts decision tree structure, is the tree structure according to curriculum attribute is lined up in teaching books.
Described resource model comprises Resource Properties and resource tag.
3. the system as claimed in claim 1, is characterized in that, described off-line data processing module comprises:
Teachers'action is described reasoning module, use Cooperative Reasoning method and the resource content inference method based on knowledge tree, according to k neighbour teacher's dynamic description, teacher to the degree of association between the resource tag and the course label that relate in the operation behavior record data of resource, reasoning teacher's dynamic description;
Resource calculation of relationship degree module, according to same teacher in the given time to the degree of association between the operation behavior computational resource of resource;
Course label adjusting module, crawls course correlation webpage according to course name in course prototype data from webpage, and therefrom extracts course keyword as course prototype data described in the initialization of course label; According to teachers ' teaching task definition feature in teachers ' teaching task record, use clustering method, the label liveness method of falling row and latent semantic analysis that course label is filtered and expanded;
Resource tag adjusting module, extracts resource tag according to resource content in resource model data, with resource model data described in initialization; Utilize label liveness to fall row, latent semantic analysis and clustering method statistics to the resource tag obtaining from teacher's label behavior record, filter and extended resources label;
Course resources calculation of relationship degree module, service range measure calculates the degree of association of course label and resource tag, and uses k near neighbor method or the lower resource of the setpoint distance threshold filtering degree of association, finally exports the degree of association between resource and course;
Resource similarity computing module, the distance between service range measure computational resource label, is used k near neighbor method or the lower resource of setpoint distance threshold filtering similarity, finally exports the similarity between resource and resource.
4. the method for claim 1, wherein online recommending module comprises:
Resource is mixed recommending module, according to the query word of teacher's input, obtain the Resources list by coupling resource tag, or describe according to the teachers'action in tutor model data, obtain describing with this teachers'action the resource that the degree of association is higher and obtain the Resources list, then according to the Resource Calculation in the Resources list and its degree of association and the associated and similar resource of similarity higher than predetermined association degree value and similarity value, according to default weights, obtained associated and similar resource is computed weighted, obtain related resource list, by weighted value in related resource list higher than the resource recommendation of predefined weight value to teacher,
Label recommending module is its resource tag that feeds back this recommendation resource according to teacher to the operation behavior of recommended resource;
Teacher's behavior record module, sends to data construct module for the behavioral data that teacher is produced, with beginning teacher's behavioral data more.
5. a network teaching resource recommend method, is characterized in that, comprising:
Data construct step, it builds teacher's behavioral data, tutor model data, course prototype data, resource model data;
Off-line data treatment step, it is for initialization and adjust course prototype data and resource model data, and utilize teacher's behavioral data to infer teacher's identity, according to the degree of association between teacher's behavioral data computational resource, according to the similarity between resource model data computational resource, calculate the degree of association between course and resource according to resource model data and course prototype data;
Online recommendation step, it utilizes the degree of association of similarity, course and resource between the degree of association, the resource between resource, teacher's dynamic description to recommend online resource, also according to teacher, the feedback of recommending resource is recommended to resource tag, and the more beginning teacher's behavioral data of behavioral data producing according to teacher.
6. method as claimed in claim 5, is characterized in that,
Described teacher's behavioral data comprises: teacher resource behavior record, teachers ' teaching task record and teacher's label behavior record, wherein teacher resource behavior record comprises the behavior of teacher to resource, teachers ' teaching task record comprises the Instructional Design that teacher carries out and the operation of preparing lessons, and teacher's label behavior record comprises the operation of teacher to resource tag;
Described tutor model data comprise that teacher's static state is described and dynamically description, and the static essential information of describing teacher of the giving advice, dynamically describes the attribute that comprises journey that teacher teaches;
Described course prototype data comprise knowledge tree and course label; Described knowledge tree adopts decision tree structure, is the tree structure according to curriculum attribute is lined up in teaching books.
Described resource model comprises Resource Properties and resource tag.
7. method as claimed in claim 5, wherein, off-line data treatment step comprises:
Use Cooperative Reasoning method and the resource content inference method based on knowledge tree, according to the degree of association between the resource tag and the course label that relate in k neighbour teacher's dynamic description, teacher resource behavior record, reasoning teacher's dynamic description; And according to the same teacher degree of association of asking of the operation behavior computational resource to resource in the given time;
Crawl course correlation webpage according to course name in course prototype data from webpage, and therefrom extract course keyword as course prototype data described in the initialization of course label; According to teachers ' teaching task definition feature in teachers ' teaching task record, use clustering method, the label liveness method of falling row and latent semantic analysis that course label is filtered and expanded;
Extract resource tag according to resource content in resource model data, with resource model data described in initialization; Utilize label liveness to fall row, latent semantic analysis and clustering method statistics to the resource tag obtaining from teacher's label behavior record, filter and extended resources label;
Service range measure calculates the degree of association of course label and resource tag, and uses k near neighbor method or the lower resource of the setpoint distance threshold filtering degree of association, finally exports the degree of association between resource and course:
Distance between service range measure computational resource label, is used k near neighbor method or the lower resource of setpoint distance threshold filtering similarity, finally exports the similarity between resource and resource.
8. method as claimed in claim 5, wherein, online recommendation step comprises:
According to the query word of teacher's input, obtain the Resources list by coupling resource tag, or describe according to the teachers'action in tutor model data, obtain describing with this teachers'action the resource that the degree of association is higher and obtain the Resources list, then according to the Resource Calculation in the Resources list and its degree of association and the associated and similar resource of similarity higher than predetermined association degree value and similarity value, according to default weights, obtained associated and similar resource is computed weighted, obtain related resource list, by weighted value in related resource list higher than the resource recommendation of predefined weight value to teacher,
According to teacher, the operation behavior of recommended resource is fed back the resource tag of this recommendation resource.
The more beginning teacher's behavioral data of behavioral data producing according to teacher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093793.6A CN103886054B (en) | 2014-03-13 | 2014-03-13 | Personalization recommendation system and method of network teaching resources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093793.6A CN103886054B (en) | 2014-03-13 | 2014-03-13 | Personalization recommendation system and method of network teaching resources |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103886054A true CN103886054A (en) | 2014-06-25 |
| CN103886054B CN103886054B (en) | 2017-02-15 |
Family
ID=50954946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410093793.6A Expired - Fee Related CN103886054B (en) | 2014-03-13 | 2014-03-13 | Personalization recommendation system and method of network teaching resources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103886054B (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504517A (en) * | 2014-12-17 | 2015-04-08 | 天脉聚源（北京）教育科技有限公司 | Teaching data management device for intelligent teaching system and management method thereof |
| CN104504948A (en) * | 2014-12-17 | 2015-04-08 | 天脉聚源（北京）教育科技有限公司 | Method and device for displaying pushed course for intelligent teaching system |
| CN104680453A (en) * | 2015-02-28 | 2015-06-03 | 北京大学 | Course recommendation method and system based on students' attributes |
| CN104952009A (en) * | 2015-04-23 | 2015-09-30 | 阔地教育科技有限公司 | Resource management method, system and server and interactive teaching terminal |
| CN105117460A (en) * | 2015-08-21 | 2015-12-02 | 湖南亿谷科技发展股份有限公司 | Learning resource recommendation method and system |
| CN105183782A (en) * | 2015-08-14 | 2015-12-23 | 广东能龙教育股份有限公司 | Analysis recommendation method based on APP platform and data mining |
| CN105512256A (en) * | 2015-12-01 | 2016-04-20 | 深圳拼课邦科技有限公司 | Method and device for pushing lecturer information |
| CN105719206A (en) * | 2016-01-01 | 2016-06-29 | 河南牧业经济学院 | Higher-education teaching resource configuration and analysis system |
| CN105894091A (en) * | 2016-03-31 | 2016-08-24 | 湘潭大学 | Test question difficulty factor knowledge discovery method based on collaborative decision-making mechanism |
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN107122399A (en) * | 2017-03-16 | 2017-09-01 | 中国科学院自动化研究所 | Combined recommendation system based on Public Culture knowledge mapping platform |
| CN107133307A (en) * | 2017-04-28 | 2017-09-05 | 太仓诚泽网络科技有限公司 | A kind of multimedia teaching video playback interface supplying system |
| CN107395725A (en) * | 2017-07-26 | 2017-11-24 | 广东小天才科技有限公司 | A kind of application program recommends method, application program recommendation apparatus and electronic equipment |
| CN107731034A (en) * | 2017-11-09 | 2018-02-23 | 北京市农林科学院 | A kind of remote education terminal, service end and Distance Education Resources recommend method |
| CN107908650A (en) * | 2017-10-12 | 2018-04-13 | 浙江大学 | Knowledge train of thought method for auto constructing based on mass digital books |
| CN108121785A (en) * | 2017-12-15 | 2018-06-05 | 华中师范大学 | A kind of analysis method based on education big data |
| CN108596804A (en) * | 2018-04-28 | 2018-09-28 | 重庆玮宜电子科技有限公司 | Multithreading online education evaluation method |
| CN108763342A (en) * | 2018-05-14 | 2018-11-06 | 北京比特智学科技有限公司 | Education resource distribution method and device |
| CN109299368A (en) * | 2018-09-29 | 2019-02-01 | 北京思路创新科技有限公司 | A kind of method and system for the intelligent personalized recommendation of environmental information resource AI |
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| CN109508429A (en) * | 2019-01-30 | 2019-03-22 | 四川省电子信息产业技术研究院有限公司 | Personalized adaptive learning recommended method based on teaching platform big data analysis |
| WO2019095450A1 (en) * | 2017-11-17 | 2019-05-23 | 深圳市鹰硕技术有限公司 | Teacher-student multi-dimensional matching method and system for use in online teaching |
| CN110060538A (en) * | 2019-04-08 | 2019-07-26 | 上海云之驾科技股份有限公司 | Personalized artificial based on historical data modeling intelligently drives training and practices system and method |
| CN110457493A (en) * | 2019-07-24 | 2019-11-15 | 安徽新知数媒信息科技有限公司 | A kind of interactive Rich Media's intelligent recommendation and the method locally called |
| CN110457283A (en) * | 2019-05-24 | 2019-11-15 | 四川信息职业技术学院(广元无线电技工学校) | A kind of teaching comment based on data mining and recommender system and its method |
| CN111292212A (en) * | 2020-03-04 | 2020-06-16 | 湖北文理学院 | Personalized thinking political affairs education system |
| CN112069423A (en) * | 2020-08-14 | 2020-12-11 | 京华信息科技股份有限公司 | Information recommendation method and device, storage medium and computer equipment |
| CN112148964A (en) * | 2019-06-29 | 2020-12-29 | 阿里巴巴集团控股有限公司 | Information processing and recommending method, system and equipment |
| CN112182413A (en) * | 2020-12-01 | 2021-01-05 | 三盟科技股份有限公司 | Intelligent recommendation method and server based on big teaching data |
| CN112287239A (en) * | 2020-12-30 | 2021-01-29 | 平安科技（深圳）有限公司 | Course recommendation method and device, electronic equipment and storage medium |
| CN112765374A (en) * | 2020-07-27 | 2021-05-07 | 上海斐杰教育科技有限公司 | Education resource screening system and method for information push |
| CN113222357A (en) * | 2021-04-22 | 2021-08-06 | 朱洪东 | Big data resource allocation method and readable storage medium for online education |
| CN116431895A (en) * | 2023-02-15 | 2023-07-14 | 武汉博晟安全技术股份有限公司 | Personalized recommendation method and system for safety production knowledge |
| CN117009829A (en) * | 2023-10-07 | 2023-11-07 | 成都华栖云科技有限公司 | Similarity recognition method and device for recorded and broadcast courses |
| CN117407594A (en) * | 2023-12-12 | 2024-01-16 | 山东大学 | Book information recommendation system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024033951A1 (en) * | 2022-08-11 | 2024-02-15 | Social Things S.R.L. | Computer- implemented method for providing a recommendation to a teacher user for creating a personalized teaching course |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169906A (en) * | 2006-10-24 | 2008-04-30 | 天象网络技术（上海）有限公司 | Integrated teaching procedure |
| US20090049077A1 (en) * | 2007-08-15 | 2009-02-19 | Martin Edward Lawlor | System And Method For The Creation And Access Of Dynamic Course Content |
| US20110010210A1 (en) * | 2009-07-10 | 2011-01-13 | Alcorn Robert L | Educational asset distribution system and method |
| CN102063459A (en) * | 2010-10-20 | 2011-05-18 | 袁昱明 | Distance educational system supported by digital resource management and integration technology |
| US20110125757A1 (en) * | 2007-03-28 | 2011-05-26 | Yahoo! Inc. | Distributed collaborative knowledge generation system |
| CN103116657A (en) * | 2013-03-11 | 2013-05-22 | 中国科学院自动化研究所 | Individual searching method of network teaching resource |
| CN103455576A (en) * | 2013-08-22 | 2013-12-18 | 西安交通大学 | Thinking-map-based e-learning resource recommendation method |
| 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 |
-
2014
- 2014-03-13 CN CN201410093793.6A patent/CN103886054B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101169906A (en) * | 2006-10-24 | 2008-04-30 | 天象网络技术（上海）有限公司 | Integrated teaching procedure |
| US20110125757A1 (en) * | 2007-03-28 | 2011-05-26 | Yahoo! Inc. | Distributed collaborative knowledge generation system |
| US20090049077A1 (en) * | 2007-08-15 | 2009-02-19 | Martin Edward Lawlor | System And Method For The Creation And Access Of Dynamic Course Content |
| US20110010210A1 (en) * | 2009-07-10 | 2011-01-13 | Alcorn Robert L | Educational asset distribution system and method |
| CN102063459A (en) * | 2010-10-20 | 2011-05-18 | 袁昱明 | Distance educational system supported by digital resource management and integration technology |
| CN103116657A (en) * | 2013-03-11 | 2013-05-22 | 中国科学院自动化研究所 | Individual searching method of network teaching resource |
| 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 |
| CN103455576A (en) * | 2013-08-22 | 2013-12-18 | 西安交通大学 | Thinking-map-based e-learning resource recommendation method |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504948A (en) * | 2014-12-17 | 2015-04-08 | 天脉聚源（北京）教育科技有限公司 | Method and device for displaying pushed course for intelligent teaching system |
| CN104504517A (en) * | 2014-12-17 | 2015-04-08 | 天脉聚源（北京）教育科技有限公司 | Teaching data management device for intelligent teaching system and management method thereof |
| CN104680453B (en) * | 2015-02-28 | 2017-10-03 | 北京大学 | Course based on student's attribute recommends method and system |
| CN104680453A (en) * | 2015-02-28 | 2015-06-03 | 北京大学 | Course recommendation method and system based on students' attributes |
| CN104952009A (en) * | 2015-04-23 | 2015-09-30 | 阔地教育科技有限公司 | Resource management method, system and server and interactive teaching terminal |
| CN105183782A (en) * | 2015-08-14 | 2015-12-23 | 广东能龙教育股份有限公司 | Analysis recommendation method based on APP platform and data mining |
| CN105117460A (en) * | 2015-08-21 | 2015-12-02 | 湖南亿谷科技发展股份有限公司 | Learning resource recommendation method and system |
| CN105512256A (en) * | 2015-12-01 | 2016-04-20 | 深圳拼课邦科技有限公司 | Method and device for pushing lecturer information |
| CN105719206A (en) * | 2016-01-01 | 2016-06-29 | 河南牧业经济学院 | Higher-education teaching resource configuration and analysis system |
| CN105894091A (en) * | 2016-03-31 | 2016-08-24 | 湘潭大学 | Test question difficulty factor knowledge discovery method based on collaborative decision-making mechanism |
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN106528656B (en) * | 2016-10-20 | 2019-08-20 | 杭州新百锐基业科技股份有限公司 | A kind of method and system for realizing that course is recommended based on student's history and real-time learning state parameter |
| CN107122399A (en) * | 2017-03-16 | 2017-09-01 | 中国科学院自动化研究所 | Combined recommendation system based on Public Culture knowledge mapping platform |
| CN107133307A (en) * | 2017-04-28 | 2017-09-05 | 太仓诚泽网络科技有限公司 | A kind of multimedia teaching video playback interface supplying system |
| CN107395725A (en) * | 2017-07-26 | 2017-11-24 | 广东小天才科技有限公司 | A kind of application program recommends method, application program recommendation apparatus and electronic equipment |
| CN107395725B (en) * | 2017-07-26 | 2020-08-04 | 广东小天才科技有限公司 | Application program recommendation method, application program recommendation device and electronic equipment |
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| CN107908650A (en) * | 2017-10-12 | 2018-04-13 | 浙江大学 | Knowledge train of thought method for auto constructing based on mass digital books |
| CN107908650B (en) * | 2017-10-12 | 2019-11-05 | 浙江大学 | Knowledge train of thought method for auto constructing based on mass digital books |
| CN107731034A (en) * | 2017-11-09 | 2018-02-23 | 北京市农林科学院 | A kind of remote education terminal, service end and Distance Education Resources recommend method |
| WO2019095450A1 (en) * | 2017-11-17 | 2019-05-23 | 深圳市鹰硕技术有限公司 | Teacher-student multi-dimensional matching method and system for use in online teaching |
| CN108121785A (en) * | 2017-12-15 | 2018-06-05 | 华中师范大学 | A kind of analysis method based on education big data |
| CN108596804A (en) * | 2018-04-28 | 2018-09-28 | 重庆玮宜电子科技有限公司 | Multithreading online education evaluation method |
| CN108763342A (en) * | 2018-05-14 | 2018-11-06 | 北京比特智学科技有限公司 | Education resource distribution method and device |
| CN109299368A (en) * | 2018-09-29 | 2019-02-01 | 北京思路创新科技有限公司 | A kind of method and system for the intelligent personalized recommendation of environmental information resource AI |
| CN109299368B (en) * | 2018-09-29 | 2020-11-24 | 北京思路创新科技有限公司 | Method and system for intelligent and personalized recommendation of environmental information resources AI |
| CN109508429A (en) * | 2019-01-30 | 2019-03-22 | 四川省电子信息产业技术研究院有限公司 | Personalized adaptive learning recommended method based on teaching platform big data analysis |
| CN110060538A (en) * | 2019-04-08 | 2019-07-26 | 上海云之驾科技股份有限公司 | Personalized artificial based on historical data modeling intelligently drives training and practices system and method |
| CN110457283A (en) * | 2019-05-24 | 2019-11-15 | 四川信息职业技术学院(广元无线电技工学校) | A kind of teaching comment based on data mining and recommender system and its method |
| CN112148964A (en) * | 2019-06-29 | 2020-12-29 | 阿里巴巴集团控股有限公司 | Information processing and recommending method, system and equipment |
| CN110457493A (en) * | 2019-07-24 | 2019-11-15 | 安徽新知数媒信息科技有限公司 | A kind of interactive Rich Media's intelligent recommendation and the method locally called |
| CN111292212A (en) * | 2020-03-04 | 2020-06-16 | 湖北文理学院 | Personalized thinking political affairs education system |
| CN112765374A (en) * | 2020-07-27 | 2021-05-07 | 上海斐杰教育科技有限公司 | Education resource screening system and method for information push |
| CN112069423A (en) * | 2020-08-14 | 2020-12-11 | 京华信息科技股份有限公司 | Information recommendation method and device, storage medium and computer equipment |
| CN112182413B (en) * | 2020-12-01 | 2021-02-19 | 三盟科技股份有限公司 | Intelligent recommendation method and server based on big teaching data |
| CN112182413A (en) * | 2020-12-01 | 2021-01-05 | 三盟科技股份有限公司 | Intelligent recommendation method and server based on big teaching data |
| CN112287239A (en) * | 2020-12-30 | 2021-01-29 | 平安科技（深圳）有限公司 | Course recommendation method and device, electronic equipment and storage medium |
| CN112287239B (en) * | 2020-12-30 | 2021-03-19 | 平安科技（深圳）有限公司 | Course recommendation method and device, electronic equipment and storage medium |
| CN113222357A (en) * | 2021-04-22 | 2021-08-06 | 朱洪东 | Big data resource allocation method and readable storage medium for online education |
| CN113222357B (en) * | 2021-04-22 | 2022-03-01 | 广州千课教育科技有限公司 | Big data resource allocation method and readable storage medium for online education |
| CN116431895A (en) * | 2023-02-15 | 2023-07-14 | 武汉博晟安全技术股份有限公司 | Personalized recommendation method and system for safety production knowledge |
| CN117009829A (en) * | 2023-10-07 | 2023-11-07 | 成都华栖云科技有限公司 | Similarity recognition method and device for recorded and broadcast courses |
| CN117407594A (en) * | 2023-12-12 | 2024-01-16 | 山东大学 | Book information recommendation system |
| CN117407594B (en) * | 2023-12-12 | 2024-03-12 | 山东大学 | Book information recommendation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103886054B (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103886054A (en) | Personalization recommendation system and method of network teaching resources | |
| US11715385B2 (en) | Systems and methods for autonomous creation of personalized job or career training curricula | |
| Bauman et al. | Recommending remedial learning materials to students by filling their knowledge gaps | |
| CN106156354A (en) | A kind of education resource commending system | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN111259240A (en) | Test question recommendation method and device | |
| Yin et al. | Detecting latent topics and trends in blended learning using LDA topic modeling | |
| Zhong et al. | Design of a personalized recommendation system for learning resources based on collaborative filtering | |
| Krikun | Applying learning analytics methods to enhance learning quality and effectiveness in virtual learning environments | |
| Cui | Application of deep learning and target visual detection in english vocabulary online teaching | |
| José-García et al. | C3-IoC: A career guidance system for assessing student skills using machine learning and network visualisation | |
| Su et al. | Research on the improvement effect of machine learning and neural network algorithms on the prediction of learning achievement | |
| Huang et al. | A blog article recommendation generating mechanism using an SBACPSO algorithm | |
| Zhang | Construction of personalized learning platform based on collaborative filtering algorithm | |
| CN116860978B (en) | Primary school Chinese personalized learning system based on knowledge graph and large model | |
| Li | A recommendation model for college English digital teaching resources using collaborative filtering and few-shot learning technology | |
| Liu et al. | Design of artificial intelligence-based English network teaching (AI-ENT) system | |
| Yu et al. | The personalized recommendation algorithms in educational application | |
| CN116595188A (en) | Educational knowledge graph system based on artificial intelligence and big data | |
| Poitras et al. | Mining the edublogosphere to enhance teacher professional development | |
| Han | Research on personalized recommendation method of educational resources based on learner behavior analysis | |
| Wan et al. | Personalized professional recommendation system based on undergraduate questionnaires | |
| Liu et al. | Design of adaptive learning system based on big data | |
| Zhang et al. | Teaching video recommendation based on student evaluation | |
| De Medio et al. | Modeling teachers and learning materials: a comparison among similarity metrics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170215 |