CN105404698A - Education video recommendation method and device - Google Patents
Education video recommendation method and device Download PDFInfo
- Publication number
- CN105404698A CN105404698A CN201511013969.3A CN201511013969A CN105404698A CN 105404698 A CN105404698 A CN 105404698A CN 201511013969 A CN201511013969 A CN 201511013969A CN 105404698 A CN105404698 A CN 105404698A
- Authority
- CN
- China
- Prior art keywords
- video
- tab
- similarity
- weight
- target
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiments of the invention provide an education video recommendation method and device, which aims to solve the problem in the prior art that due to the fact that video tags are mixed, disorderly and equally treated, the recommendation accuracy of education videos to users is not high. The method comprises the steps of according to the video attribute information, obtaining a related video set of a target video, wherein the video attribute information comprises a video tag viewing time, a video tag and a video tag category; according to the video tag viewing time, generating a video tag weight, and calculating the similarity between the target video and other targets in the related video set; generating a recommendation list for recommendation according to the similarity between the target video and other targets in the related video set.
Description
Technical field
The present invention relates to recommended technology field, particularly relate to a kind of education video recommend method and device.
Background technology
Along with the development of infotech and internet, people have entered into the epoch of information overload from the epoch of absence of information gradually, and commending system arises at the historic moment.Commending system is the interested video that user finds outside its known range, expands its viewing and experiences.
Wherein, education video is because of the division of its meticulous specific crowd, and the requirement for commending system is harsher.In existing video recommendation system, a kind of is the similarity coming between computing education video based on the video tab of education video, namely whether mating to come the similarity between computing education video according to the intrinsic label of some, is the education video that user recommends not watch according to the similarity generating recommendations list between education video.But thisly in prior art calculate the method for similarity between video based on video tab and there is two problems: one is, there is the problems such as quantity of information overload, unordered, rubbish label in label, this can affect accuracy and the personalization level of commending system; Two are, recommend for education video, each intrinsic label is differentiated for the significance level of user, if put on an equal footing without exception, can cause recommending accuracy not high, affect Consumer's Experience.
Summary of the invention
Embodiments of the invention provide a kind of education video recommend method and device, for solving because video tab is unordered in a jumble in prior art, and are treated equally the problem of recommending education video accuracy not high to user caused.
For achieving the above object, embodiments of the invention adopt following technical scheme:
The embodiment of the present invention provides a kind of education video recommend method, comprises the following steps:
According to Video attribute information, obtain the associated video collection of target video, described Video attribute information comprises video tab viewing time, video tab, video tab generic;
According to the video tab weight generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos;
Concentrate the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.
The embodiment of the present invention additionally provides a kind of education video recommendation apparatus, comprising:
Acquisition module, for according to Video attribute information, obtain the associated video collection of target video, described Video attribute information comprises video tab viewing time, video tab;
Similarity calculation module, for the video tab weight that basis is generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos;
Recommending module, for concentrating the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.
The education video recommend method that the embodiment of the present invention provides and device, according to Video attribute information, obtain the associated video collection of target video, according to the video tab weight generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos, concentrate the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.Because the present invention classifies to video tab, be provided with video tab generic, so the situation that video tab is unordered in a jumble can not be there is again.And generate video tab weight by video tab viewing time, video tab viewing time shows user's demand to certain video within the time period to a certain extent, according to video tab viewing time generating video label weight, video tab weight also reflects user to the demand of video and hobby, user is also reflects to the demand of video and hobby according to the similarity between the video tab weight calculation target video generated and other videos, the video so just can user liked according to similarity and need is picked out, similarity is calculated compared to putting on an equal footing video tab, significantly improve the accuracy of video recommendations, Consumer's Experience is better.Simultaneously, due to according to Video attribute information, determine the associated video collection of target video, first pre-service has been carried out to videos all in database, form associated video collection, reduce video range of choice, calculating target video and associated video concentrate the similarity between other videos just to greatly reduce calculated amount like this, improve recommendation efficiency.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The method flow diagram of a kind of education video recommend method that Fig. 1 provides for the embodiment of the present invention;
The structural representation of a kind of education video recommendation apparatus that Fig. 2 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The embodiment of the present invention provides a kind of education video recommend method, and as shown in Figure 1, the method comprises:
101, video recommendations device is according to Video attribute information, obtains the associated video collection of target video.
Video recommendations device in the embodiment of the present invention can have the server of terminal device for administrative institute, also can be a certain terminal device, this terminal device can be the electronic equipment of intelligent television or portable, pocket or hand-held, such as, smart mobile phone, panel computer and personal digital assistant etc.
Video attribute information in the embodiment of the present invention comprises video tab viewing time, video labeling, video tab and video tab generic.Wherein, above-mentioned video labeling can for the title of video or other uniquely can represent the mark of this video, adopt in the present embodiment v1, v2, v3 ..., vm represents the mark of different video.
First all educational resources are stored in education video collection A.
Each education video comprises following attribute information: video ID, area, grade, subject, teacher, course content description etc.Text word segmentation processing is carried out to Video attribute information, and carries out duplicate removal process, obtain the video tab of education video, be stored in education video collection B.
In addition, the type informations such as store video title, version, subject, grade are gone back in education video collection B.
Exemplary, the data layout of education video B is:
" grade ": " one grade ": [" 3380 " ..., " 5417 "] ..., " high three ": [" 3462 ", ..., " 4172 "] }, " subject ": " mathematics ": [" 3380 " ..., " 5335 "], ..., " history ": [" 3652 " ..., " 4572 "] }, " version ": { " people teaches version ": [" 3360 ", ..., " 5467 "] ..., " Shandong religion version ": [" 3462 ", ..., " 4563 "] ..., " Soviet Union's religion version ": [" 3032 ", ..., " 1579 "] }, " being suitable for crowd ": { ... } }
Wherein, " grade ", " subject ", " version ", " being suitable for crowd " are the video tab generic of education video, " one grade ", " mathematics ", " people teaches version " etc. are the video tabs under the video tab generic of education video, and what " 3380 ", " 5417 " etc. represented is video labeling under corresponding video tab.
According to the video tab of video, video tab generic is set, video tab is classified.
Particularly, video tab generic is: grade, subject, version, applicable crowd.
Exemplary, classified according to video tab generic by the video tab in education video collection B, sorted data are stored in feature extraction result set C.
Wherein, the data layout of feature extraction result set C is:
Video labeling: " XXX ", video tab: " XX " ..., " XX " }.
Preferably, according to Video attribute information, the associated video collection obtaining target video is specially: mated with the video tab generic of other videos by target video, is incorporated to associated video collection with video tab generic other videos that the match is successful of target video.
Exemplary, video tab generic is grade, subject, version, applicable crowd, video tab generic as target video is one grade, mathematics, people teach version, primary school, from all videos, then pick out that video tab generic is also one grade, video that mathematics, people teach version, primary school, these videos are incorporated to the associated video collection of target video collection.
In this way, first carried out filtration treatment to videos all in database, by range shorter in the video set all mated with the video tab generic of target video, like this, computation amount when subsequent calculations, also improves recommendation efficiency.
In addition, education video recommendation apparatus, according to the video-see time in Video attribute information, determines each video tab viewing time.
Preferably, in a step 101, a update cycle can be set, the length of update cycle can set according to the database update situation of video data, such as, can one month be set to, one week or one day, the present invention does not limit this, obtains the attribute information of the video data in described each update cycle and upgrade within each update cycle.The following each step of the present embodiment is all described for current period.
102, education video recommendation apparatus is according to the video tab weight generated by described video tab viewing time, and calculating target video and associated video concentrate the similarity between other videos.
Preferably, the video tab weight generated by described video tab viewing time is specially: generate formula generating video label weight by weight, weight generates formula and is:
,
represent the weight of a kth video tab of video i,
represent the number of days of the time interval current time of a kth video tab in viewing video i,
for the weight factor of a default kth video tab, i, k are natural number.
Wherein,
also hierarchical is arranged, according to the difference of video tab, different weight factors is set, the weight factor that the weight factor of subject emphasis descriptor compares general description information is high, credit is geometry, calculating, application in full, English is divided into grammer, vocabulary, spoken language, Chinese language is divided into the writing in classical Chinese, writing, novel, and the weight factor of these video tabs is high compared to the weight factor of general description information.
Video tab weight is determined by watching video time, and viewing video tab time nearest video tab weight is larger, and it is less to watch video tab time video tab weight more of a specified duration.
Preferably, according to the video tab weight generated by video tab viewing time, calculating target video and associated video concentrates the similarity between other videos to be specially: calculate target video and associated video according to calculating formula of similarity and concentrate similarity between other videos, calculating formula of similarity is:
, wherein, m is the video tab number of target video i, and l is that target video i and other videos j have video tab number,
for the kth video tab weight that target video i and other videos j is total, j, l are natural number.
Be described with instantiation below.
If there are three education video, target video is v1, and associated video concentrates other two videos to be v2, v3.
The video tab generic Dou Shi primary school of these three videos, second grade, English, people teach version.
The video tab of target video v1 has: vocabulary, grammer, spoken language, teacher Li, lecture, examination question collection, explanation.
The video tab of video v2 has: spoken language, teacher Li, personally instruct, course.
The video tab of video v3 has: vocabulary, teacher Zhu, course, spurt, elite.
English is divided into the course content such as grammer, vocabulary, spoken language, reading, belongs to course emphasis and describes, so these video tabs
just be set to 10, and compare the former about master's video tab weight factor that teacher Li, teacher Zhu are such can be lower,
just be set to 5, as other video tab as elite, course, explanation, weight factor arranges lower again,
be set to 3.
In addition, for the video tab in target video v1 and other videos v2, v3, the time occurred recently is respectively: vocabulary is yesterday, and spoken language is that before 7 days, namely student saw the course about vocabulary yesterday, sees the course about spoken language before seven days.
Generate formula according to video tab weight, then the weight of the video tab vocabulary of target video v1 and video v3 is 10 divided by the first power of e, and the weight of the video tab spoken language of video v2 is exactly 10 divided by seven powers of e.
Time parameter is with one month for basic point, if namely some video tab did not all occur within one month, 30 powers so just pressing e calculated.
Present hypothesis only has vocabulary and spoken two video tabs to occur within one month, all the other video tabs did not all occur in one month, so other video tabs are 5 divided by 30 powers of e as the weight of teacher Li, teacher Zhu etc., personally instruct, make a spurt, the weight of the video tab such as elite is 3 divided by 30 powers of e.
After obtaining each video tab weight, the similarity of target video v1 and video v2, video v3 can be obtained according to calculating formula of similarity.
Molecular moiety: the video tab that target video v1 and video v2 has is spoken and teacher Li, and so molecule is 10/ (seven powers of e)+5/ (30 powers of e)
Denominator part: all video tab weight sums being exactly target video v1 is 10/ (first power of e)+10/ (30 powers of e)+10/ (seven powers of e)+5/ (30 powers of e)+3/ (30 powers of e)+3/ (30 powers of e)+3/ (30 powers of e)
Similarity then between target video v1 and video v2 is:
。
In like manner, the similarity between target video v1 and video v3 is calculated.
Molecular moiety: the video tab that target video v1 and video v3 has is vocabulary, so molecule is 10/ (first power of e)
Denominator part: all video tab weight sums being exactly target video v1 is 10/ (first power of e)+10/ (30 powers of e)+10/ (seven powers of e)+5/ (30 powers of e)+3/ (30 powers of e)+3/ (30 powers of e)+3/ (30 powers of e).
Similarity between target video v1 and video v3 is:
。
Preferably, when under grade is, the associated video collection of described target video also comprises the video of the grade that is associated.
Wherein, the grade of the video of the grade that is associated to be grade be high this grade next stage, the video of all the other video tab generic coupling, be namely suitable for crowd, version, subject coupling, and grade is the video of high one grade.
If: target video is that mathematics people teaches version under primary school's Third school grade, then the video that associated video is concentrated does not only include the video that primary school Third school grade mathematics people teaches version, also comprises the video that primary school senior class mathematics people teaches version.
Calculate target video identical with aforesaid way with the similarity be associated between grade video, be not described in detail herein.Suppose that the similarity that this situation calculates is
.
The reason done like this is, considers that the course learning of student may be ahead of the course learning of school, is also taken into account by the video of the grade that is associated, recommend him, improve the diversity of recommendation, also meets the demand of student in view of the situation simultaneously.
Preferably, when grade is high by two or high three, when subject is a kind of in politics, history, geography, associated video collection also comprise of the same grade in the video that is associated with this subject.
If the video be associated with this subject refers to target video subject for politics, then the video be associated is the video of history, geographical aspect.
If target video is that high two political men of senior middle school teach version, then associated video is concentrated and is also comprised the high two history people of senior middle school and teach the video of version and the high two geographical people of senior middle school to teach the video of version, is namely suitable for crowd, grade, version video tab categorical match, the video that subject is associated.
Preferably, when grade is high by two or high three, when subject is a kind of in physics, chemistry, biology, associated video collection also comprise of the same grade in the video that is associated with this subject.
If it is physics that the video be associated with this subject refers to target video subject, then the video be associated is the video of chemistry, biological aspect.
If target video is the high two physical person religion versions of senior middle school, then associated video is concentrated and is also comprised the high two chemical people of senior middle school and teach the video of version and the high two biological people of senior middle school to teach the video of version, is namely suitable for crowd, grade, version video tab categorical match, the video that subject is associated.
The object done like this is, consider that high two laggard style of writing reasons are put into several classes, for student majored in liberal arts, the subject that may belong to student majored in liberal arts all can consider viewing, for student majored in science, the subject that may belong to student majored in science also can consider viewing, therefore by the expanded range of associated video collection, subject being associated also as recommending video to consider list, adding the diversity of recommendation.
Identical with above-mentioned Similarity Measure mode as the Similarity Measure mode between these associated video with target videos, be not described in detail at this.Suppose that the similarity calculated is
.
In addition, the form of the similarity between target video with other videos can be: the similarity of the video that target video all mates with video tab classification and target video and the similarity be associated between grade video and target video are comprehensive with the similarity be associated between subject video.
Similarity between other videos that hypothetical target video and video tab classification are all mated is
, target video with the similarity be associated between grade video is
, target video with the similarity be associated between subject video is
, then the similarity between other videos of concentrating of target video and associated video is:
。
Wherein, variable
,
for regulatory factor, the course learning data analysis according to student regulates regulatory factor, regulatory factor can comprehensive video factor again synthetic user because usually regulating, thus better can realize recommendation results.If student grade is in this grade, variable
value can be 0.If grade is high by two or high three, then
be not 0, can suitably increase
value, to increase the diversity of recommendation.When grade is under this grade, variable can be adjusted
value, make it not be 0.
Adopt in this way, it is thorough just multiple situation can be considered, increases the diversity of recommending, improves Consumer's Experience.
Also can the similarity in the various situations calculated between target video and other videos be carried out integrated ordered in addition, determine recommendation list.Namely the similarity between other videos target video and video tab classification all mated
, target video and the similarity be associated between grade video
, target video and the similarity be associated between subject video
, sort according to similarity size, determine recommendation list.
103, education video recommendation apparatus concentrates similarity between other videos according to described target video and associated video, and generating recommendations list is recommended.
Particularly, education video recommendation apparatus concentrates the similarity between other videos according to target video and associated video, sorts to described similarity, according to predetermined recommendation number determination recommendation list.
In sum, the education video recommend method that the embodiment of the present invention provides, according to Video attribute information, obtain the associated video collection of target video, according to the video tab weight generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos, and concentrate the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.Because the present invention classifies to video tab, be provided with video tab generic, so the situation that video tab is unordered in a jumble can not be there is again.And generate video tab weight by video tab viewing time, video tab viewing time shows user's demand to certain type video within the time period to a certain extent, according to video tab viewing time generating video label weight, video tab weight also reflects user to the demand of video and hobby, user is also reflects to the demand of video and hobby according to the similarity between the video tab weight calculation target video generated and other videos, the video so just can user liked according to similarity and need is picked out, similarity is calculated compared to putting on an equal footing video tab, significantly improve the accuracy of video recommendations, Consumer's Experience is better.Simultaneously, due to according to Video attribute information, determine the associated video collection of target video, first pre-service has been carried out to videos all in database, form associated video collection, reduce video range of choice, calculating target video and associated video concentrate the similarity between other videos just to greatly reduce calculated amount like this, improve recommendation efficiency.
On the other hand, the embodiment of the present invention additionally provides a kind of education video recommendation apparatus, and this device is for realizing above-mentioned education video recommend method, and as shown in Figure 2, this device comprises: acquisition module, similarity calculation module, recommending module, wherein:
Acquisition module, for according to Video attribute information, obtain the associated video collection of target video, described Video attribute information comprises video tab viewing time, video tab, video tab generic;
Similarity calculation module, for the video tab weight that basis is generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos;
Recommending module, for concentrating the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.
Preferably, similarity calculation module is specially: concentrate similarity between other videos according to calculating formula of similarity calculating target video and associated video, calculating formula of similarity is:
, wherein, m is the video tab number of target video i, and l is that target video i and other videos j have video tab number,
for the kth video tab weight that target video i and other videos j is total, j, l are natural number.
Preferably, the video tab weight generated by described video tab viewing time described in similarity calculation module is specially: generate formula generating video label weight by weight, weight generates formula and is:
,
represent the weight of a kth video tab of video i,
represent the number of days of the time interval current time of a kth video tab of viewing video i,
for the weight factor of a default kth video tab, i, k are natural number.
Preferably, according to Video attribute information in acquisition module, the associated video collection obtaining target video is specially: mated with the video tab generic of other videos by target video, is incorporated to associated video collection with video tab generic other videos that the match is successful of target video.
The education video recommendation apparatus that the embodiment of the present invention provides, according to Video attribute information, obtain the associated video collection of target video, according to the video tab weight generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos, concentrate the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.Because the present invention classifies to video tab, be provided with video tab generic, so the situation that video tab is unordered in a jumble can not be there is again.And generate video tab weight by video tab viewing time, video tab viewing time shows user's demand to certain type video within the time period to a certain extent, according to video tab viewing time generating video label weight, video tab weight also reflects user to the demand of video and hobby, user is also reflects to the demand of video and hobby according to the similarity between the video tab weight calculation target video generated and other videos, the video so just can user liked according to similarity and need is picked out, similarity is calculated compared to putting on an equal footing video tab, significantly improve the accuracy of video recommendations, Consumer's Experience is better.Simultaneously, due to according to Video attribute information, determine the associated video collection of target video, first pre-service has been carried out to videos all in database, form associated video collection, reduce video range of choice, calculating target video and associated video concentrate the similarity between other videos just to greatly reduce calculated amount like this, improve recommendation efficiency.
In several embodiments that the application provides, should be understood that disclosed terminal and method can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit comprises, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprises the part steps of some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (Read-OnlyMemory, be called for short ROM), random access memory (RandomAccessMemory, be called for short RAM), magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (10)
1. an education video recommend method, is characterized in that, comprises the following steps:
According to Video attribute information, obtain the associated video collection of target video, described Video attribute information comprises video tab viewing time, video tab and video tab generic;
According to the video tab weight generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos;
Concentrate the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.
2. education video recommend method according to claim 1, it is characterized in that, described according to Video attribute information, the associated video collection obtaining target video is specially: mated with the video tab generic of other videos by target video, is incorporated to associated video collection with video tab generic other videos that the match is successful of target video.
3. education video recommend method according to claim 1, is characterized in that, the described video tab weight generated by described video tab viewing time is specially: generate formula generating video label weight by weight, weight generates formula and is:
,
represent the weight of a kth video tab of video i,
represent the number of days of the time interval current time of a kth video tab in viewing video i,
for the weight factor of a default kth video tab, i, k are natural number.
4. education video recommend method according to claim 3, it is characterized in that, the video tab weight that described basis is generated by video tab viewing time, calculating target video and associated video concentrates the similarity between other videos to be specially: calculate target video and associated video according to calculating formula of similarity and concentrate similarity between other videos, calculating formula of similarity is:
, wherein, m is the video tab number of target video i, and l is that target video i and other videos j have video tab number,
for the kth video tab weight that target video i and other videos j is total, j, l are natural number.
5. education video recommend method according to claim 1, is characterized in that, described video tab generic is: grade, subject, version, applicable crowd.
6. education video recommend method according to claim 5, is characterized in that, when described grade is under this grade, the associated video collection of described target video also comprises the video of the grade that is associated, described in the grade that is associated be high one grade.
7. education video recommend method according to claim 5, it is characterized in that, when described grade is high by two or high three, when described subject is a kind of in physics, chemistry, biology, the associated video collection of described target video also comprises the section's object video that is associated, described in the subject that is associated be in physics, chemistry, biology, to remove in described subject other two kinds; When described grade is high by two or high three, when described subject is a kind of in history, politics, geography, the associated video collection of described target video also comprises the section's object video that is associated, described in the subject that is associated be in history, politics, geography, to remove in described subject other two kinds.
8. an education video recommendation apparatus, is characterized in that, comprising:
Acquisition module, for according to Video attribute information, obtain the associated video collection of target video, described Video attribute information comprises video tab viewing time, video tab, video tab generic;
Similarity calculation module, for the video tab weight that basis is generated by described video tab viewing time, calculating target video and associated video concentrate the similarity between other videos;
Recommending module, for concentrating the similarity between other videos according to described target video and associated video, generating recommendations list is recommended.
9. education video recommendation apparatus according to claim 8, it is characterized in that, the video tab weight generated by described video tab viewing time described in described similarity calculation module is specially: generate formula generating video label weight by weight, weight generates formula and is:
,
represent the weight of a kth video tab of video i,
represent the number of days of the time interval current time of a kth video tab in viewing video i,
for the weight factor of a default kth video tab, i, k are natural number.
10. education video recommendation apparatus according to claim 9, is characterized in that, described similarity calculation module is specially: concentrate similarity between other videos according to calculating formula of similarity calculating target video and associated video, calculating formula of similarity is:
, wherein, m is the video tab number of target video i, and l is that target video i and other videos j have video tab number,
for the kth video tab weight that target video i and other videos j is total, j, l are natural number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511013969.3A CN105404698A (en) | 2015-12-31 | 2015-12-31 | Education video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511013969.3A CN105404698A (en) | 2015-12-31 | 2015-12-31 | Education video recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105404698A true CN105404698A (en) | 2016-03-16 |
Family
ID=55470187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511013969.3A Pending CN105404698A (en) | 2015-12-31 | 2015-12-31 | Education video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105404698A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN106095819A (en) * | 2016-05-31 | 2016-11-09 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN106162351A (en) * | 2016-08-02 | 2016-11-23 | 合网络技术（北京）有限公司 | A kind of video recommendation method and device |
| CN106250557A (en) * | 2016-08-16 | 2016-12-21 | 青岛海信传媒网络技术有限公司 | The recommendation method and device of application |
| CN106407401A (en) * | 2016-09-21 | 2017-02-15 | 乐视控股（北京）有限公司 | A video recommendation method and device |
| CN106599165A (en) * | 2016-12-08 | 2017-04-26 | 腾讯科技（深圳）有限公司 | Playing behavior-based content recommendation method and server |
| CN106777053A (en) * | 2016-12-09 | 2017-05-31 | 国网北京市电力公司 | The sorting technique and device of media content |
| CN106941623A (en) * | 2017-04-27 | 2017-07-11 | 广东小天才科技有限公司 | Method and device for evaluating video course quality based on big data |
| 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 |
| CN107426610A (en) * | 2017-03-29 | 2017-12-01 | 聚好看科技股份有限公司 | Video information synchronous method and device |
| CN108134950A (en) * | 2017-12-07 | 2018-06-08 | 上海斐讯数据通信技术有限公司 | A kind of intelligent video recommends method and system |
| CN108228911A (en) * | 2018-02-11 | 2018-06-29 | 北京搜狐新媒体信息技术有限公司 | The computational methods and device of a kind of similar video |
| CN108334640A (en) * | 2018-03-21 | 2018-07-27 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
| CN108737850A (en) * | 2017-04-21 | 2018-11-02 | 传线网络科技（上海）有限公司 | A kind of video recommendation method, server and client |
| CN109766913A (en) * | 2018-12-11 | 2019-05-17 | 东软集团股份有限公司 | Tenant group method, apparatus, computer readable storage medium and electronic equipment |
| CN110020122A (en) * | 2017-10-16 | 2019-07-16 | Tcl集团股份有限公司 | A kind of video recommendation method, system and computer readable storage medium |
| CN110609955A (en) * | 2019-09-16 | 2019-12-24 | 腾讯科技（深圳）有限公司 | Video recommendation method and related equipment |
| CN110890095A (en) * | 2019-12-26 | 2020-03-17 | 北京大米未来科技有限公司 | Voice detection method, recommendation method, device, storage medium and electronic equipment |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
| CN111182332A (en) * | 2019-12-31 | 2020-05-19 | 广州华多网络科技有限公司 | Video processing method, device, server and storage medium |
| CN112507167A (en) * | 2020-12-10 | 2021-03-16 | 北京达佳互联信息技术有限公司 | Method and device for identifying video collection, electronic equipment and storage medium |
| CN113313065A (en) * | 2021-06-23 | 2021-08-27 | 北京奇艺世纪科技有限公司 | Video processing method and device, electronic equipment and readable storage medium |
| CN113836348A (en) * | 2021-09-26 | 2021-12-24 | 深圳市易平方网络科技有限公司 | Video-based classification label mark processing method, device, terminal and medium |
| CN114064975A (en) * | 2021-11-26 | 2022-02-18 | 四川长虹电器股份有限公司 | Video label generation method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946566A (en) * | 2012-10-24 | 2013-02-27 | 北京奇虎科技有限公司 | Video recommending method and device based on historical information |
| CN102968446A (en) * | 2012-10-24 | 2013-03-13 | 北京奇虎科技有限公司 | Video recommendation method and video recommendation device |
-
2015
- 2015-12-31 CN CN201511013969.3A patent/CN105404698A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102946566A (en) * | 2012-10-24 | 2013-02-27 | 北京奇虎科技有限公司 | Video recommending method and device based on historical information |
| CN102968446A (en) * | 2012-10-24 | 2013-03-13 | 北京奇虎科技有限公司 | Video recommendation method and video recommendation device |
Non-Patent Citations (3)
| Title |
|---|
| 李源鑫: "时间衰减制导的协同过滤相似性计算", 《计算机系统应用》 * |
| 熊海涛: "《面向复杂数据的推荐分析研究》", 31 January 2015 * |
| 蒋翀等: "基于线性衰减的用户兴趣建模", 《计算机系统应用》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN106095819A (en) * | 2016-05-31 | 2016-11-09 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN106162351A (en) * | 2016-08-02 | 2016-11-23 | 合网络技术（北京）有限公司 | A kind of video recommendation method and device |
| CN106250557A (en) * | 2016-08-16 | 2016-12-21 | 青岛海信传媒网络技术有限公司 | The recommendation method and device of application |
| CN106407401A (en) * | 2016-09-21 | 2017-02-15 | 乐视控股（北京）有限公司 | A video recommendation method and device |
| CN106599165A (en) * | 2016-12-08 | 2017-04-26 | 腾讯科技（深圳）有限公司 | Playing behavior-based content recommendation method and server |
| CN106777053A (en) * | 2016-12-09 | 2017-05-31 | 国网北京市电力公司 | The sorting technique and device of media content |
| CN107426610A (en) * | 2017-03-29 | 2017-12-01 | 聚好看科技股份有限公司 | Video information synchronous method and device |
| CN107426610B (en) * | 2017-03-29 | 2020-04-28 | 聚好看科技股份有限公司 | Video information synchronization method and device |
| CN108737850A (en) * | 2017-04-21 | 2018-11-02 | 传线网络科技（上海）有限公司 | A kind of video recommendation method, server and client |
| CN108737850B (en) * | 2017-04-21 | 2020-03-03 | 传线网络科技（上海）有限公司 | Video recommendation method, server and client |
| CN106941623A (en) * | 2017-04-27 | 2017-07-11 | 广东小天才科技有限公司 | Method and device for evaluating video course quality based on big data |
| CN106941623B (en) * | 2017-04-27 | 2019-06-14 | 广东小天才科技有限公司 | Method and device for evaluating video course quality based on big data |
| 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 |
| CN110020122A (en) * | 2017-10-16 | 2019-07-16 | Tcl集团股份有限公司 | A kind of video recommendation method, system and computer readable storage medium |
| CN110020122B (en) * | 2017-10-16 | 2022-06-03 | Tcl科技集团股份有限公司 | Video recommendation method, system and computer readable storage medium |
| CN108134950A (en) * | 2017-12-07 | 2018-06-08 | 上海斐讯数据通信技术有限公司 | A kind of intelligent video recommends method and system |
| CN108228911A (en) * | 2018-02-11 | 2018-06-29 | 北京搜狐新媒体信息技术有限公司 | The computational methods and device of a kind of similar video |
| CN108334640A (en) * | 2018-03-21 | 2018-07-27 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
| CN108681601B (en) * | 2018-05-21 | 2020-12-11 | 北京奇艺世纪科技有限公司 | Video sharing method and device and electronic equipment |
| CN109766913A (en) * | 2018-12-11 | 2019-05-17 | 东软集团股份有限公司 | Tenant group method, apparatus, computer readable storage medium and electronic equipment |
| CN110609955A (en) * | 2019-09-16 | 2019-12-24 | 腾讯科技（深圳）有限公司 | Video recommendation method and related equipment |
| CN110609955B (en) * | 2019-09-16 | 2022-04-05 | 腾讯科技（深圳）有限公司 | Video recommendation method and related equipment |
| CN110941740A (en) * | 2019-11-08 | 2020-03-31 | 腾讯科技（深圳）有限公司 | Video recommendation method and computer-readable storage medium |
| CN110941740B (en) * | 2019-11-08 | 2023-07-14 | 深圳市雅阅科技有限公司 | Video recommendation method and computer-readable storage medium |
| CN110890095A (en) * | 2019-12-26 | 2020-03-17 | 北京大米未来科技有限公司 | Voice detection method, recommendation method, device, storage medium and electronic equipment |
| CN111182332A (en) * | 2019-12-31 | 2020-05-19 | 广州华多网络科技有限公司 | Video processing method, device, server and storage medium |
| CN112507167A (en) * | 2020-12-10 | 2021-03-16 | 北京达佳互联信息技术有限公司 | Method and device for identifying video collection, electronic equipment and storage medium |
| CN113313065A (en) * | 2021-06-23 | 2021-08-27 | 北京奇艺世纪科技有限公司 | Video processing method and device, electronic equipment and readable storage medium |
| CN113836348A (en) * | 2021-09-26 | 2021-12-24 | 深圳市易平方网络科技有限公司 | Video-based classification label mark processing method, device, terminal and medium |
| CN114064975A (en) * | 2021-11-26 | 2022-02-18 | 四川长虹电器股份有限公司 | Video label generation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105404698A (en) | Education video recommendation method and device | |
| CN105512331B (en) | A kind of video recommendation method and device | |
| CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
| CN112711937B (en) | Template recommendation method, device, equipment and storage medium | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN109829810B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN110968684A (en) | Information processing method, device, equipment and storage medium | |
| CN109086420B (en) | Method, device and storage medium for selecting reading material | |
| CN105404680A (en) | Searching recommendation method and apparatus | |
| CN105653547B (en) | Method and device for extracting text keywords | |
| CN113342958B (en) | Question-answer matching method, text matching model training method and related equipment | |
| CN106980667B (en) | A kind of method and apparatus to article mark label | |
| CN109447273A (en) | Model training method, advertisement recommended method, relevant apparatus, equipment and medium | |
| CN113988057A (en) | Title generation method, device, equipment and medium based on concept extraction | |
| CN113127621A (en) | Dialogue module pushing method, device, equipment and storage medium | |
| CN111475731A (en) | Data processing method, device, storage medium and equipment | |
| CN114090880A (en) | Method and device for commodity recommendation, electronic equipment and storage medium | |
| CN116882414B (en) | Automatic comment generation method and related device based on large-scale language model | |
| CN112948526A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN108550019A (en) | A kind of resume selection method and device | |
| CN112541069A (en) | Text matching method, system, terminal and storage medium combined with keywords | |
| CN111062449A (en) | Prediction model training method, interestingness prediction device and storage medium | |
| CN116796730A (en) | Text error correction method, device, equipment and storage medium based on artificial intelligence | |
| CN110750712A (en) | Software security requirement recommendation method based on data driving | |
| CN106021346B (en) | Retrieval processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160316 |
|
| RJ01 | Rejection of invention patent application after publication |