CN105824946A - Method and system for multimedia recommendation on basis of data grading - Google Patents
Method and system for multimedia recommendation on basis of data grading Download PDFInfo
- Publication number
- CN105824946A CN105824946A CN201610162406.9A CN201610162406A CN105824946A CN 105824946 A CN105824946 A CN 105824946A CN 201610162406 A CN201610162406 A CN 201610162406A CN 105824946 A CN105824946 A CN 105824946A
- Authority
- CN
- China
- Prior art keywords
- multimedia
- scoring
- website
- achievement data
- data
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- 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
- G06F16/954—Navigation, e.g. using categorised browsing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for multimedia recommendation on the basis of data grading. The method comprises the following steps of receiving a selection instruction of a user on the category, and obtaining index data of multimedia in the selected category; classifying the index data of the multimedia according to sites, and performing statistics to obtain the index data of the multimedia of each site; obtaining the grading of the multimedia in each site through calculation according to the index data of the multimedia of each site; performing unified sequencing on the multimedia of different sites according to the grading result in accordance with the grading values, and recommending the multimedia to the user according to the sequencing. The invention also discloses a system for multimedia recommendation on the basis of data grading. The method and the system for multimedia recommendation on the basis of data grading have the advantages that the grading of the multimedia is obtained through calculation through the index data of the multimedia in one site, so that the multimedia of different sites can be sequenced according to the grading; the precise recommendation of the multimedia is finally realized; further, the experience degree of the user is improved.
Description
Technical field
The present invention relates to multimedia technology field, particularly relate to a kind of method and system carrying out Multimedia Recommendation based on data scoring.
Background technology
In intelligent television system, video website or intelligent terminal software, in order to meet the different demands of different hobby user, usually can prepare the video resource of magnanimity for user.Such as: intelligent television can provide the user such as the carousel channels such as all-in one desk, film platform, TV play platform, animation platform, sports station, documentary film platform, Music Radio, it is provided with different programs in each channel and selects viewing for user.In same channel, background work personnel can select thermal center mesh from massive video storehouse, and broadcasts sequentially in time.
In video recommendations technology, obtaining the video recommendations result relevant to user preferences is not the most a difficult problem, but before Multimedia Recommendation result is showed user, how to be ranked up the multi-medium data got, or a difficult problem the most unsolved.Because for separate sources or the video of website, there is a lot of difference in the verity of same data target, reliability.Most of the time, the similar index of separate sources does not have comparability, if by its equivalent processes, then the accuracy of recommended engine marking will exist bigger problem.Concrete manifestation phenomenon out is exactly:
(1) in recommendation list, the data in same website or source flock together appearance, and multiformity is poor.
(2) data in certain site or source are overall higher or on the low side, cause overall sequence poor, arise that the data arrangement substantially ranked behind has arrived the problem before the forward data of ranking.
Summary of the invention
In view of this, it is an object of the invention to propose a kind of method and system carrying out Multimedia Recommendation based on data scoring, it is possible to the multimedia for different websites sorts accurately and recommends.
A kind of method carrying out Multimedia Recommendation based on data scoring provided based on the above-mentioned purpose present invention, including:
Receive user and classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now；
Being classified according to website by the described multimedia achievement data obtained, statistics obtains the multimedia achievement data of each website；
According to the multimedia achievement data of described each website, it is calculated multimedia scoring in each website；
According to described multimedia appraisal result, the multimedia of different websites is carried out unifying sequence according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
Preferably, being calculated the computing formula of multimedia scoring in each website described in is:
Z=(X-mean (X))/stdev (X),
Wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, and stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；
S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)),
Wherein, the scoring vector that during S is a described website, multimedia is corresponding.
Preferably, the step of the described class of described acquisition multimedia achievement data now includes:
In selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；
Obtain the achievement data that the multimedia of the predetermined number chosen is corresponding.
Further, described according to multimedia appraisal result, before the multimedia of different websites is carried out, according to the size of scoring score value, the step unifying to sort, also include:
For each multimedia, it is judged that whether described multimedia exists more than one scoring；
If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.
Further, described multimedia achievement data includes: multimedia broadcasting number, comment number, hits or download number.
Present invention also offers a kind of system carrying out Multimedia Recommendation based on data scoring, including:
Choose module, for receiving user, classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now, multimedia achievement data is sent to statistical module；
Statistical module, for being classified according to website by the described described multimedia achievement data choosing module transmission, statistics obtains the multimedia achievement data of each website, and this achievement data is sent to grading module；
Grading module, for accepting the achievement data that described statistical module sends, according to the multimedia achievement data of described each website, is calculated multimedia scoring in each website；Appraisal result is sent to recommending module；
Recommending module, is used for receiving the multimedia appraisal result that institute's scoring module sends, and carries out unifying sequence by the multimedia of different websites according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
Preferably, the calculation of falling into a trap of institute's scoring module obtains the computing formula of multimedia scoring in each website and is:
Z=(X-mean (X))/stdev (X),
Wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, and stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；
S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)),
Wherein, the scoring vector that during S is a described website, multimedia is corresponding.
Further, described in choose module and be additionally operable to,
In selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；
Obtain the achievement data that the multimedia of the predetermined number chosen is corresponding.
Further, institute's scoring module is additionally operable to, for each multimedia, it is judged that whether described multimedia exists more than one scoring；
If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.
Further, described multimedia achievement data includes: multimedia broadcasting number, comment number, hits or download number.
As can be seen from above, the method and system carrying out Multimedia Recommendation based on data scoring that the present invention provides, by in a website, according to multimedia achievement data, it is calculated multimedia scoring, the multimedia making different website can be ranked up according to described scoring, finally achieves multimedia accurate recommendation, and then improves the Experience Degree of user.
Accompanying drawing explanation
The flow chart of one embodiment of the method carrying out Multimedia Recommendation based on data scoring that Fig. 1 provides for the present invention；
The flow chart of another embodiment of the method carrying out Multimedia Recommendation based on data scoring that Fig. 2 provides for the present invention；
The structural representation of one embodiment of the system carrying out Multimedia Recommendation based on data scoring that Fig. 3 provides for the present invention.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and referring to the drawings, the present invention is described in more detail.
It should be noted that, in the embodiment of the present invention, the statement of all uses " first " and " second " is for the parameter of entity or the non-equal distinguishing two same names non-equal, visible " first " " second " is only for the convenience of statement, should not be construed as the restriction to the embodiment of the present invention, this is illustrated by subsequent embodiment the most one by one.
With reference to shown in Fig. 1, the flow chart of an embodiment of the method carrying out Multimedia Recommendation based on data scoring provided for the present invention.Described carry out the method for Multimedia Recommendation based on data scoring and be applied to all kinds of carry out in the website of Multimedia Recommendation, application software or other system, described carry out the method for Multimedia Recommendation based on data scoring and include:
Step 101, receives user and classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now.
Wherein, shown classification refers to system or the server combination carrying out classifying set in advance for different multimedia, and user only need to click on the word corresponding to corresponding classification just can select this classification.Server both can be set as receiving user and classification chosen instruction, it is also possible to being set to, time initial, Server Default selectes some classification.Or, classification can also be divided into multiple different level by server according to the actual needs, and user can be according to the needs of oneself, the classification required for selection accordingly.Such as: multimedia is first divided into TV play, film, variety, animation etc. type by server, is then dividing different kinds in the type that these are different, such as: in film, is being again split into action, science fiction, comedy, war etc. type.So, user can select the most accurate multimedia type.Described achievement data is used for evaluating the degree that multimedia is concerned, including: multimedia broadcasting number, comment number, hits or download number etc..
Step 102, classifies the described multimedia achievement data obtained according to website, and statistics obtains the multimedia achievement data of each website.
Wherein, described different websites are multimedia different source, such as: different websites are divided into network, this locality；Or, different websites divide the video website that Baidu, Sina, Sohu etc. are different.Multimedia achievement datas based on different websites are not have comparability, therefore, it is necessary first to classify multimedia achievement data according to website, then add up multimedia achievement data in each website.
Step 103, according to the multimedia achievement data of described each website, is calculated multimedia scoring in each website.
Equally, owing to the multimedia achievement data of different websites does not have comparability, therefore when multimedia carrying out scoring and processing, need in units of website, carry out scoring process respectively, i.e. the multimedia in same website is carried out respectively scoring process, obtains the scoring of this website inner multimedia.Although and this scoring multimedia is that index based on same website inner multimedia is calculated, but its scoring score value has comparability, therefore between different websites so that the multimedia of different websites can be ranked up based on same standards of grading.
Step 104, according to described multimedia appraisal result, carries out unifying sequence by the multimedia of different websites according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
Owing to multimedia scoring has comparability between different websites, therefore, scoring based on different multimedia, the different multimedia of all websites can be obtained a unified sequence according to the size of scoring score value, and this sequence is very reliable, finally according to the order of sequence, the multimedia after sequence is recommended user.
From above-described embodiment, the method carrying out Multimedia Recommendation of marking based on data of the present invention is by selected class now, for the multimedia in a website, according to described multimedia achievement data, it is calculated multimedia scoring in each website, and described scoring score value makes the different multimedia between different website can be ranked up based on same standards of grading so that for different websites multimedia sequence more accurately and reliable.Finally, improve the accuracy of the described method carrying out Multimedia Recommendation based on data scoring, and then make user have the preferably multimedia experience of viewing.
As further embodiment of the present invention, described in be calculated the computing formula of the scoring of different multimedia in each website and be:
Z=(X-mean (X))/stdev (X),
Wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, and stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；
S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)),
Wherein, the scoring vector that during S is a described website, multimedia is corresponding.
Here, data vector representated by X refers to a series of multimedia achievement data, such as: in same website, has 5 different multimedias A, B, C, D, E, its achievement data is respectively 4,5,6,7,8, so can obtain X=(4,5,6,7,8), meansigma methods mean (X)=(4+5+6+7+8)/5=6, standard deviation stdev (X)=sqrt (((4-6)2+(5-6)2+(6-6)2+(7-6)2+(8-6)2)/5)=sqrt (2).Further, it is possible to be calculated the standard scores numerical value that different multimedia is corresponding, these standard scores numerical value composition standard score vector Z.By calculated scoring vector S so that the multimedia scoring at different websites obtains based on same calculating standard, namely make the different multimedia of different website can carry out unified sequence.
The computing formula of described multimedia scoring makes multimedia scoring in a website more accurate, and the method makes the multimedia of different website obtain having the scoring score value of comparability based on identical algorithm, finally improve the accuracy being ranked up for different website multimedias and recommending so that sort and the result recommended is relatively reliable.
In some preferred embodiments of the present invention, the step 101 of the described class of described acquisition multimedia achievement data now also includes:
In selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；
Obtain the achievement data that the multimedia of the predetermined number chosen is corresponding.
When carrying out multimedia recommendation due to different websites or system, often simply recommend the multimedia of limited quantity, and user has only to recommend multimedia the most forward in sequence the most mostly, therefore, it is required for obtaining multimedia quantity to be defined, that is, preset the multimedia quantity needing to obtain in each website.But this acquisition is not random acquisition, but choose according to the ranking results of multimedia achievement data in different websites.So, not only fast selecting has obtained the multimedia file needed, and owing to only have chosen the multimedia file of relative order limited quantity formerly, improve and carry out the acquisition of multimedia file, the speed marked and sort and recommend and efficiency so that described carry out the method for Multimedia Recommendation based on data scoring and can carry out multimedia sequence and recommendation more rapid and exactly.
Preferably, described according to multimedia appraisal result, the step 104 that the multimedia of each website carries out unifying sequence according to the size of scoring score value is farther included before: for each multimedia, it is judged that whether described multimedia exists more than one scoring；If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.Based in different websites; usually there will be identical multimedia; so when being calculated multimedia scoring score value; some multimedia has different scoring score values in different websites; now, the maximum in this multimedia all scorings score value is filtered out as this multimedia final scoring.In so avoiding the problem that same multimedia repeats in same sequence, and analysis and the process when carrying out Multimedia Recommendation to different websites of the feature of different website, beneficially server can be obtained according to the scoring in different websites of the same multimedia.Further ensure and described carry out the method for Multimedia Recommendation based on data scoring and carry out stability and the reliability of Multimedia Recommendation.
As further embodiment of the present invention, described classification is multimedia kind, or comprises the compound type of multimedia kind, and described type includes: source, kind, area and language.Described source refers to obtain multimedia source, such as: Sina, Baidu and excellent extremely etc..Described kind refers to the differentiation of multimedia character, such as: film, TV play, animation.And different types of multimedia is not have comparability, generally, user the most only can choose for the multimedia of a kind.Described area refer to multimedia from country type, such as: the division that Hong Kong and Taiwan, continent, America and Europe, Japan and Korea S etc. are different.Described language refers to the language form used in multimedia, such as: Chinese, Japanese, English, German etc..All of multimedia disposably can be divided into different compound types by the system or the website that carry out Multimedia Recommendation, it is also possible to multimedia is divided into many levels so that multimedia classification is the most accurate.Preferably, described classification must comprise multimedia kind.
As further embodiment of the invention, described multimedia index includes: multimedia broadcasting number, comment number, hits or download number.Described multimedia index is for evaluating multimedia most basic data, and the follow-up result calculating scoring or sequence is required to according to this multimedia achievement data.And for same multimedia, usually there is different pointer types, user can select the pointer type needing sequence, or gives tacit consent to the index foundation as sequence of a certain class in website or system.Certainly, the present embodiment simply lists several frequently seen pointer type, it is also possible to according to the feature of different multimedia, selects corresponding multimedia index.Such as: for the sales volume in shop, favorable comment quantity etc. in shopping website.
With reference to shown in Fig. 2, the flow chart of another embodiment of the method carrying out Multimedia Recommendation based on data scoring provided for the present invention.Described carry out the method for Multimedia Recommendation based on data scoring and include:
Step 201, receives user and classification is chosen instruction, determine the classification selected by user.
Step 202, in selected classification, according to the ranking results of achievement data multimedia in each website, chooses sequence multimedia formerly according to predetermined number.
Step 203, obtains the achievement data that the multimedia of the predetermined number chosen is corresponding.
Step 204, adds up according to different websites respectively by the described multimedia achievement data obtained, and obtains the different multimedia achievement data of website.
Step 205, according to the multimedia achievement data of described each website, is calculated multimedia scoring in each website.
Step 206, for each multimedia, it is judged that whether described multimedia exists more than one scoring, if there is more than one scoring, then performs step 207, otherwise performs step 208.
Step 207, chooses the maximum of scoring score value as this multimedia scoring.
Step 208, according to described multimedia appraisal result, carries out unifying sequence by the multimedia of different websites according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
With reference to shown in Fig. 3, the structural representation of an embodiment of the system carrying out Multimedia Recommendation based on data scoring provided for the present invention.Described carry out the system of Multimedia Recommendation based on data scoring and include:
Choose module 301, for receiving user, classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now, multimedia achievement data is sent to statistical module 302；
Statistical module 302, for choosing the described multimedia achievement data that module 301 sends classify described respectively according to website, statistics obtains the multimedia achievement data of each website, and this achievement data is sent to grading module 303；
Grading module 303, for accepting the achievement data that described statistical module 302 sends, according to the multimedia achievement data of described each website, is calculated multimedia scoring in each website；Appraisal result is sent to recommending module 304；
Recommending module 304, is used for receiving the multimedia appraisal result that institute's scoring module 303 sends, and carries out unifying sequence by the multimedia of different websites according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
From above-described embodiment, described based on data scoring carry out the system of Multimedia Recommendation pass through described in choose module 301 and obtain the multimedia achievement data in selected classification, then by described statistical module 302, the multimedia achievement data obtained is carried out classified statistic respectively according to different websites, by institute's scoring module 303 for the multimedia achievement data in same website, it is calculated multimedia scoring, finally the multimedia of the different websites obtained is ranked up by recommending module 304, and according to this ranking results by the Multimedia Recommendation of different websites to user.The described system carrying out Multimedia Recommendation of marking based on data, by the achievement data in same website, obtains the scoring at different websites with comparability so that the multimedia of different websites is all capable of unified sequence.So, drastically increase and described carry out the system of Multimedia Recommendation based on data scoring and carry out the accuracy of Multimedia Recommendation.
In some preferred embodiments, being calculated the computing formula of multimedia scoring in each website in institute's scoring module 303 is: Z=(X-mean (X))/stdev (X), wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)), wherein, the scoring vector that during S is a described website, multimedia is corresponding.In such manner, it is possible to obtain appraisal result more accurately.
In other preferred embodiments of the present invention, described in choose module 301 and be additionally operable to, in selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；And obtain the achievement data that the multimedia of predetermined number chosen is corresponding.So, described carry out the system of Multimedia Recommendation based on data scoring and can not only obtain the efficient multimedia achievement data of predetermined number, and the system that can further speed up carries out speed and the efficiency marking and sort.
In further embodiment of the present invention, institute's scoring module 303 is additionally operable to, for each multimedia, it is judged that whether described multimedia exists more than one scoring；If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.So, described scoring based on data carries out the system of Multimedia Recommendation it can be avoided that same multimedia repetition is sorted and recommend so that the result of system is more accurate.
In some preferred embodiments of the present invention, described classification is multimedia kind, or comprises the compound type of multimedia kind, and described type includes: source, kind, area and language.
In other preferred embodiments of the present invention, described multimedia achievement data includes: multimedia broadcasting number, comment number, hits or download number.
Those of ordinary skill in the field are it is understood that the discussion of any of the above embodiment is exemplary only, it is not intended that hint the scope of the present disclosure (including claim) is limited to these examples；Under the thinking of the present invention, can also be combined between technical characteristic in above example or different embodiment, step can realize with random order, and there is other change of many of the different aspect of the present invention as above, for they not offers in details simple and clear.
It addition, for simplifying explanation and discussing, and in order to obscure the invention, can illustrate in the accompanying drawing provided or can not illustrate and integrated circuit (IC) chip and the known power supply/grounding connection of other parts.In addition, device can be shown in block diagram form, to avoid obscuring the invention, and this have also contemplated that following facts, the i.e. details about the embodiment of these block diagram arrangements is (that is, in the range of these details should be completely in the understanding of those skilled in the art) of the platform depending highly on and will implementing the present invention.Elaborating that detail is (such as, circuit) to describe the exemplary embodiment of the present invention in the case of, it will be apparent to those skilled in the art that can in the case of there is no these details or these details change in the case of implement the present invention.Therefore, these descriptions are considered as illustrative and not restrictive.
Although invention has been described to have been incorporated with the specific embodiment of the present invention, but according to description above, these embodiments a lot of replace, amendment and modification will be apparent from for those of ordinary skills.Such as, other memory architecture (such as, dynamic ram (DRAM)) can use discussed embodiment.
Embodiments of the invention are intended to all such replacement, amendment and the modification fallen within the broad range of claims.Therefore, all within the spirit and principles in the present invention, any omission of being made, amendment, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (10)
1. the method carrying out Multimedia Recommendation based on data scoring, it is characterised in that including:
Receive user and classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now；
Being classified according to website by the described multimedia achievement data obtained, statistics obtains the multimedia achievement data of each website；
According to the multimedia achievement data of described each website, it is calculated multimedia scoring in each website；
According to described multimedia appraisal result, the multimedia of different websites is carried out unifying sequence according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
Method the most according to claim 1, it is characterised in that described in be calculated the computing formula of multimedia scoring in each website and be:
Z=(X-mean (X))/stdev (X),
Wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, and stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；
S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)),
Wherein, the scoring vector that during S is a described website, multimedia is corresponding.
Method the most according to claim 1, it is characterised in that the step of the described class of described acquisition multimedia achievement data now includes:
In selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；
Obtain the achievement data that the multimedia of the predetermined number chosen is corresponding.
4., according to the method described in claim 1-3 any one, it is characterised in that described according to multimedia appraisal result, before the multimedia of different websites is carried out, according to the size of scoring score value, the step unifying to sort, also include:
For each multimedia, it is judged that whether described multimedia exists more than one scoring；
If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.
5. according to the method described in claim 1-3 any one, it is characterised in that described multimedia achievement data includes: multimedia broadcasting number, comment number, hits or download number.
6. the system carrying out Multimedia Recommendation based on data scoring, it is characterised in that including:
Choose module, for receiving user, classification is chosen instruction, determine the classification selected by user and obtain described class multimedia achievement data now, multimedia achievement data is sent to statistical module；
Statistical module, for being classified according to website by the described described multimedia achievement data choosing module transmission, statistics obtains the multimedia achievement data of each website, and this achievement data is sent to grading module；
Grading module, for accepting the achievement data that described statistical module sends, according to the multimedia achievement data of described each website, is calculated multimedia scoring in each website；Appraisal result is sent to recommending module；
Recommending module, is used for receiving the multimedia appraisal result that institute's scoring module sends, and carries out unifying sequence by the multimedia of different websites according to the size of scoring score value, and presses described sequence by Multimedia Recommendation to user.
System the most according to claim 6, it is characterised in that the calculation of falling into a trap of institute's scoring module obtains the computing formula of multimedia scoring in each website and is:
Z=(X-mean (X))/stdev (X),
Wherein, X is the data vector of multimedia achievement data composition in a described website, mean (X) is the meansigma methods of X, and stdev (X) is the standard deviation of X, and Z is the standard score vector that in a described website, multimedia achievement data is corresponding；
S=(-min (Z)+(Log (X)-mean (X))/stdev (X)) * 100/ (max (Z)-min (Z)),
Wherein, the scoring vector that during S is a described website, multimedia is corresponding.
System the most according to claim 6, it is characterised in that described in choose module and be additionally operable to,
In selected classification, according to the ranking results of achievement data multimedia in each website, choose sequence multimedia formerly according to predetermined number；
Obtain the achievement data that the multimedia of the predetermined number chosen is corresponding.
9. according to the system described in claim 6-8 any one, it is characterised in that institute's scoring module is additionally operable to, for each multimedia, it is judged that whether described multimedia exists more than one scoring；
If there is more than one scoring, then choose the maximum of scoring score value as this multimedia scoring.
10. according to the system described in claim 6-8 any one, it is characterised in that described multimedia achievement data includes: multimedia broadcasting number, comment number, hits or download number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610162406.9A CN105824946A (en) | 2016-03-21 | 2016-03-21 | Method and system for multimedia recommendation on basis of data grading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610162406.9A CN105824946A (en) | 2016-03-21 | 2016-03-21 | Method and system for multimedia recommendation on basis of data grading |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105824946A true CN105824946A (en) | 2016-08-03 |
Family
ID=56524189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610162406.9A Pending CN105824946A (en) | 2016-03-21 | 2016-03-21 | Method and system for multimedia recommendation on basis of data grading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105824946A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485554A (en) * | 2016-10-18 | 2017-03-08 | 希音（深圳）投资有限公司 | A kind of musical instruments chooses system |
| CN107241621A (en) * | 2017-05-26 | 2017-10-10 | 北京小米移动软件有限公司 | Main broadcaster's methods of marking and device |
| CN110633376A (en) * | 2019-08-22 | 2019-12-31 | 北京奇艺世纪科技有限公司 | Media object sorting method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101320375A (en) * | 2008-07-04 | 2008-12-10 | 浙江大学 | Digital book search method based on user click action |
| JP2009033366A (en) * | 2007-07-25 | 2009-02-12 | Advanced Telecommunication Research Institute International | Optical marker system |
| CN103167330A (en) * | 2011-12-15 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Method and system for audio/video recommendation |
| CN103646053A (en) * | 2013-11-29 | 2014-03-19 | 北京奇虎科技有限公司 | Website providing object recommendation method and device |
| CN104133823A (en) * | 2013-07-19 | 2014-11-05 | 腾讯科技（深圳）有限公司 | Method and device for recommending multimedia information |
-
2016
- 2016-03-21 CN CN201610162406.9A patent/CN105824946A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009033366A (en) * | 2007-07-25 | 2009-02-12 | Advanced Telecommunication Research Institute International | Optical marker system |
| CN101320375A (en) * | 2008-07-04 | 2008-12-10 | 浙江大学 | Digital book search method based on user click action |
| CN103167330A (en) * | 2011-12-15 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Method and system for audio/video recommendation |
| CN104133823A (en) * | 2013-07-19 | 2014-11-05 | 腾讯科技（深圳）有限公司 | Method and device for recommending multimedia information |
| CN103646053A (en) * | 2013-11-29 | 2014-03-19 | 北京奇虎科技有限公司 | Website providing object recommendation method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485554A (en) * | 2016-10-18 | 2017-03-08 | 希音（深圳）投资有限公司 | A kind of musical instruments chooses system |
| CN107241621A (en) * | 2017-05-26 | 2017-10-10 | 北京小米移动软件有限公司 | Main broadcaster's methods of marking and device |
| CN110633376A (en) * | 2019-08-22 | 2019-12-31 | 北京奇艺世纪科技有限公司 | Media object sorting method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108920497B (en) | Man-machine interaction method and device | |
| CN105095431A (en) | Method and device for pushing videos based on behavior information of user | |
| EP3324312A1 (en) | Content recommendation system with weighted metadata annotations | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| US8620849B2 (en) | Systems and methods for facilitating open source intelligence gathering | |
| US20170188102A1 (en) | Method and electronic device for video content recommendation | |
| CN108090208A (en) | Fused data processing method and processing device | |
| US20150278359A1 (en) | Method and apparatus for generating a recommendation page | |
| EP2560111A2 (en) | Systems and methods for facilitating the gathering of open source intelligence | |
| Pyo et al. | LDA-based unified topic modeling for similar TV user grouping and TV program recommendation | |
| CN105956148A (en) | Resource information recommendation method and apparatus | |
| CN103984740B (en) | Based on the method and system that the retrieved page of combination tag shows | |
| CN105893443A (en) | Video recommendation method and apparatus, and server | |
| CN104504149A (en) | Application recommendation method and device | |
| CN105281925B (en) | The method and apparatus that network service groups of users divides | |
| CN107729578B (en) | Music recommendation method and device | |
| CN104182392B (en) | The method and apparatus of service recommendation processing | |
| CN112328906A (en) | Content item recommendation method, device, equipment and storage medium | |
| CN106294794A (en) | A kind of content recommendation method and device | |
| CN108228657B (en) | Method and device for realizing keyword retrieval | |
| CN106326297B (en) | Application program recommendation method and device | |
| CN103729362A (en) | Method and device for determining navigation content | |
| CN105824946A (en) | Method and system for multimedia recommendation on basis of data grading | |
| CN104933135A (en) | Method and device for clustering multimedia data | |
| CN105373600A (en) | Method and device for sorting video playlists |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160803 |