CN105701226A - Multimedia resource assessment method and device - Google Patents
Multimedia resource assessment method and device Download PDFInfo
- Publication number
- CN105701226A CN105701226A CN201610029193.2A CN201610029193A CN105701226A CN 105701226 A CN105701226 A CN 105701226A CN 201610029193 A CN201610029193 A CN 201610029193A CN 105701226 A CN105701226 A CN 105701226A
- Authority
- CN
- China
- Prior art keywords
- multimedia resource
- described multimedia
- resource
- video
- content recommendation
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention relates to a multimedia resource assessment method and device, ands aims to assess multimedia resources in recommended contents; the multimedia resource assessment method comprises the following steps: obtaining behavior data of a plurality of users corresponding to the multimedia resources in a preset time period; filtering the behavior data of the plurality of users; accessing the quality of the multimedia resources according to the filtered user behavior data; accessing the heat level of the multimedia resources according to the quality assess result of the multimedia resources and the recommended contents. The multimedia resource assessment method and device can properly consider content self of the commended multimedia resources, thus reducing influences on user experiences by hot spot multimedia resources or headline and screenshot multimedia resources, and improving user experiences.
Description
Technical field
The present invention relates to multimedia resource process field, particularly relate to a kind of multimedia resource appraisal procedure and device。
Background technology
Current commending system, the such as multimedia resource commending system CF (CollaborativeFiltering by such as main flow, collaborative filtering) algorithm, logistic regression algorithm scheduling algorithm, mainly utilize user behavior data to recommend the multimedia resources such as such as video to user。At present, what recommend to user is all the multimedia resources liked of other users, or recommends, according to the historical behavior (or attribute information) of individual subscriber, the multimedia resource that its people may like。
But, the content of this recommended technology multimedia resource to recommending itself considers less, consequently, it is possible to cause some social hotspots multimedia resources or rely on title, the multimedia resource of sectional drawing and attractive eyeball frequently appears in content recommendation, causes that Consumer's Experience is poor。
Summary of the invention
Technical problem
In view of this, the technical problem to be solved in the present invention is, how the contents such as the multimedia resource recommended to user by conventional recommendation technology to be estimated, to improve Consumer's Experience。
Solution
In order to solve above-mentioned technical problem, according to one embodiment of the invention, provide a kind of multimedia resource appraisal procedure, for the multimedia resource in content recommendation is estimated, described multimedia resource appraisal procedure includes: obtain the multiple user behavior datas corresponding with described multimedia resource in predetermined amount of time；Multiple described user behavior datas are filtered；According to the user behavior data after filtering, described multimedia resource is carried out quality evaluation；And described multimedia resource is carried out temperature assessment by the quality assessment result and described content recommendation according to described multimedia resource。
For above-mentioned multimedia resource appraisal procedure, in a kind of possible implementation, described user behavior data includes the broadcasting situation of user cookie, ID, the user processing mode to multimedia resource and handled multimedia resource, wherein, described processing mode includes playing, collect, comment on, push up and stepping on；Described broadcasting situation includes resource duration, playing duration, statistics time started and statistics end time。
For above-mentioned multimedia resource appraisal procedure, in a kind of possible implementation, described multimedia resource is carried out temperature assessment particularly as follows: quality assessment result and described content recommendation according to described multimedia resource calculate temperature assessment point according to the quality assessment result of described multimedia resource and described content recommendation。
For above-mentioned multimedia resource appraisal procedure, in a kind of possible implementation, equation 1 below is adopted to perform, according to the user behavior data after filtering, described multimedia resource is carried out quality evaluation,
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of described multimedia resource, V represents the broadcasting number of described multimedia resource, C represents the number of reviews of described multimedia resource, D represents the useful order of described multimedia resource, what B represented described multimedia resource steps on number, F represents the collection number of described multimedia resource, T ' represents the difference between the statistics end time of described multimedia resource and statistics time started, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
For above-mentioned multimedia resource appraisal procedure, in a kind of possible implementation, adopt equation 2 below to perform the quality assessment result according to described multimedia resource and described content recommendation calculate temperature assessment point,
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of described multimedia resource, Rec represents that described multimedia resource occurs in the ratio in described content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
In order to solve above-mentioned technical problem, according to another embodiment of the present invention, provide a kind of multimedia resource apparatus for evaluating, for the multimedia resource in content recommendation is estimated, described multimedia resource apparatus for evaluating includes: acquiring unit, for obtaining the multiple user behavior datas corresponding with described multimedia resource in predetermined amount of time；Filter element, is connected with described acquiring unit, for multiple described user behavior datas are filtered；Quality estimation unit, is connected with described filter element, for described multimedia resource being carried out quality evaluation according to the user behavior data after filtering；And temperature assessment unit, it is connected with described filter element and described quality estimation unit, for quality assessment result and the described content recommendation according to described multimedia resource, described multimedia resource is carried out temperature assessment。
For above-mentioned multimedia resource apparatus for evaluating, in a kind of possible implementation, described user behavior data includes the broadcasting situation of user cookie, ID, the user processing mode to multimedia resource and handled multimedia resource, wherein, described processing mode includes playing, collect, comment on, push up and stepping on；Described broadcasting situation includes resource duration, playing duration, statistics time started and statistics end time。
For above-mentioned multimedia resource apparatus for evaluating, in a kind of possible implementation, described temperature assessment unit specifically for: according to the quality assessment result of described multimedia resource and described content recommendation calculate temperature assessment point。
For above-mentioned multimedia resource apparatus for evaluating, in a kind of possible implementation, described quality estimation unit adopts equation 1 below that described multimedia resource is carried out quality evaluation,
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of described multimedia resource, V represents the broadcasting number of described multimedia resource, C represents the number of reviews of described multimedia resource, D represents the useful order of described multimedia resource, what B represented described multimedia resource steps on number, F represents the collection number of described multimedia resource, T ' represents the difference between the statistics end time of described multimedia resource and statistics time started, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
For above-mentioned multimedia resource apparatus for evaluating, in a kind of possible implementation, described temperature assessment unit adopts equation 2 below to calculate the assessment point of described temperature,
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of described multimedia resource, Rec represents that described multimedia resource occurs in the ratio in described content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
Beneficial effect
By the multimedia resource appraisal procedure of the embodiment of the present invention and device, based on the user behavior data corresponding with the multimedia resource in content recommendation this multimedia resource can be carried out quality evaluation and temperature assessment, thus processing being resequenced to the content that user recommends by conventional recommendation technology or carrying out being not desired to user the content directly rejecting etc. of viewing, then result is recommended again user。So, the content itself of the multimedia resource by with due regard to recommending, it is possible to reduce focus multimedia resource or title party, the impact on Consumer's Experience of the sectional drawing party multimedia resource, thus promoting Consumer's Experience。
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, further feature and the aspect of the present invention will be clear from。
Accompanying drawing explanation
The accompanying drawing of the part comprising in the description and constituting description together illustrates the exemplary embodiment of the present invention, feature and aspect with description, and is used for explaining principles of the invention。
Fig. 1 illustrates the flow chart of multimedia resource appraisal procedure according to an embodiment of the invention；
Fig. 2 illustrates the flow chart of multimedia resource appraisal procedure according to another embodiment of the present invention；
Fig. 3 illustrates the structured flowchart of multimedia resource apparatus for evaluating according to an embodiment of the invention。
Detailed description of the invention
The various exemplary embodiments of the present invention, feature and aspect is described in detail below with reference to accompanying drawing。Accompanying drawing labelling identical in accompanying drawing represents the same or analogous element of function。Although the various aspects of embodiment shown in the drawings, but unless otherwise indicated, it is not necessary to accompanying drawing drawn to scale。
Word " exemplary " special here means " as example, embodiment or illustrative "。Here should not necessarily be construed as preferred or advantageous over other embodiments as any embodiment illustrated by " exemplary "。
It addition, in order to better illustrate the present invention, detailed description of the invention below gives numerous details。It will be appreciated by those skilled in the art that there is no some detail, the equally possible enforcement of the present invention。In some instances, method, means, element and the circuit known for those skilled in the art are not described in detail, in order to highlight the purport of the present invention。
Current commending system recommends multimedia resource mainly through CF algorithm, logistic regression algorithm scheduling algorithm to user。Such as multimedia resource is video, then the results for video recommended to user according to sequencing by above-mentioned algorithm is as follows: video 1, video 2 ..., video 9, video 10 etc.。So, user is it can be seen that above-mentioned content recommendation, and can watch after the corresponding video in clicking above-mentioned content recommendation。
But, in above content recommendation, owing to the content of multimedia resource, such as video itself is considered less, consequently, it is possible to cause some social hotspots videos or rely on title, the video of sectional drawing and attractive eyeball frequently appears in content recommendation。But, the video in these content recommendations be likely to be not user want viewing content, so cause that Consumer's Experience is poor。
In order to solve the problems referred to above, the present invention proposes a kind of multimedia resource appraisal procedure and device。By the multimedia resource appraisal procedure of the present invention and device, based on the user behavior data corresponding with the multimedia resource in content recommendation this multimedia resource can be carried out quality evaluation and temperature assessment, thus processing being resequenced to the content that user recommends by conventional recommendation technology or carrying out being not desired to user the content directly rejecting etc. of viewing, then result is recommended again user。So, the content itself of the multimedia resource by with due regard to recommending, it is possible to reduce focus multimedia resource or title party, the impact on Consumer's Experience of the sectional drawing party multimedia resource, thus promoting Consumer's Experience。
The particular content of multimedia resource appraisal procedure provided by the invention and device will be set forth in the examples below。Wherein, in the examples below, mainly illustrate using video as the example of multimedia resource。But, those skilled in the art understand that, multimedia resource is possible not only to as video, it is also possible to for picture, electronic document or music etc.。Therefore, utilize multimedia resource appraisal procedure provided by the invention and device, be possible not only to video is estimated, it is also possible to various types of multimedia resources such as picture, electronic document or music are estimated。
Embodiment 1
Fig. 1 illustrates the flow chart of multimedia resource appraisal procedure according to an embodiment of the invention。Wherein, this multimedia resource appraisal procedure is mainly used in commending system is estimated to each multimedia resource in the content recommendation of user。As it is shown in figure 1, this multimedia resource appraisal procedure mainly may comprise steps of S100, step S110, step S120 and step S130。
Step S100, the multiple user behavior datas corresponding with multimedia resource obtained in predetermined amount of time。
Such as, this multimedia resource is such as video。When utilizing the terminal units such as mobile phone, desktop computer, notebook computer, intelligent television, Set Top Box that a certain video is processed user, the user behavior data corresponding with this video can be produced。In a kind of possible implementation, user behavior data mainly can include the broadcasting situation of user cookie, ID (namely, ID), the user processing mode to video and handled video。Wherein, described processing mode mainly can include playing, collect, comment on, push up and stepping on；Described broadcasting situation mainly can include video duration, playing duration, statistics time started and statistics end time。In a kind of possible implementation, above-mentioned user behavior data can be stored in such as user journal。In the different time, user is used video by terminal unit, namely video is correspondingly processed, and all can produce corresponding user behavior data。Therefore, a video can corresponding multiple user behavior datas。
So, after commending system utilizes conventional recommendation technology to recommend the multimedia resources such as such as video to user, the multimedia resource apparatus for evaluating of the present invention can obtain the user behavior data corresponding with each video in above-mentioned content recommendation in predetermined amount of time from such as user journal。
Such as, it is recommended that system is video 1, video 2 ..., video 9, video 10 to the content that user recommends, then multimedia resource apparatus for evaluating can obtain user behavior data corresponding with this 10 videos above in predetermined amount of time respectively from user journal。In a kind of possible implementation, this predetermined amount of time can be 12 hours, 24 hours, 1 day, 2 days etc., and the present invention is not limiting as the concrete numerical value of predetermined amount of time。Those skilled in the art understand that, it is more long that predetermined amount of time is arranged, and user behavior data is more many, and the data in multimedia resource list also can be more many。This accuracy that multimedia resource is estimated by raising, but, also can increase the computation complexity of multimedia resource appraisal procedure accordingly。
Step S110, multiple user behavior datas are filtered。
Specifically, after step S100 obtains multiple above-mentioned user behavior datas, according to predetermined rule, accessed user behavior data can be carried out suitable filtration, have adverse effect or the assessment result of the present invention is affected less user behavior data rejecting assessment result unwanted, on the present invention。As such, it is possible to make the result that the quality evaluation carried out afterwards and temperature are assessed more objective and accurate。
Such as, the user processing wherein a certain video has processed multitude of video in above-mentioned predetermined amount of time, and it processes quantity and has exceeded the threshold value pre-set, then it is assumed that this user belongs to abnormal user。Owing to assessment result can be had adverse effect by the user behavior data of this abnormal user, therefore, it can to filter out with this user-dependent user behavior data。And for example, the hour of log-on processing the wherein user of a certain video is shorter, such as hour of log-on was less than one day, then it is believed that the impact of assessment result is less with this user-dependent user behavior data, therefore the user-dependent user behavior data short with this user, i.e. hour of log-on can be filtered out。And for example, a certain user seldom watches video, namely this user to process the frequency of video low and lower than the dependent thresholds pre-set, then it is believed that also that the impact of assessment result is less with this user-dependent user behavior data。Therefore, it can filter out the user-dependent user behavior data low with the frequency of this process video。
Above rule is only example, the invention is not restricted to this, it is possible to according to actual needs, filtering rule is suitably changed。
Step S120, according to filter after user behavior data described multimedia resource is carried out quality evaluation。
After the step S110 user behavior data to getting carries out suitably filtration, it is possible to according to the user behavior data corresponding with each multimedia resource in content recommendation after filtering, each multimedia resource is carried out quality evaluation respectively。
Such as, according to the user behavior data corresponding with video in content recommendation 1 after filtering, video 1 can be carried out quality evaluation, according to the user behavior data corresponding with video in content recommendation 2 after filtering, video 2 can be carried out quality evaluation, ..., it is possible to according to the user behavior data corresponding with video in content recommendation 10 after filtering, video 10 is carried out quality evaluation。
As such, it is possible to complete the quality evaluation of all multimedia resources in content recommendation according to the user behavior data after filtering。
In a kind of possible implementation, it is possible to calculate quality evaluation according to user behavior data and divide, multimedia resource is carried out quality evaluation。In a kind of possible implementation, when user behavior data include playing, collect, comment on, push up, step on, video duration, playing duration, statistics time started and during the statistics end time, it is possible to using playing number, collection number, comment number, serve as a fill-in, step on number, video duration, playing duration, statistics time started and add up these data item of end time and divide as the coefficient carrying out quality evaluation calculating to calculate quality evaluation。
Multimedia resource is carried out temperature assessment by step S130, quality assessment result and content recommendation according to multimedia resource。
After above-mentioned steps S120, it is possible to according to the attribute difference opposite sex of each multimedia resource in the quality assessment result of each multimedia resource in content recommendation and content recommendation, each multimedia resource is carried out temperature assessment respectively。
Such as, temperature assessment can be carried out to carrying out video 1 according to the attribute difference opposite sex between other video in the quality assessment result of the video 1 in content recommendation and this video 1 and content recommendation, temperature assessment can be carried out to carrying out video 2 according to the attribute difference opposite sex between other video in the quality assessment result of the video 2 in content recommendation and this video 2 and content recommendation, ..., temperature assessment can be carried out to carrying out video 10 according to the attribute difference opposite sex between other video in the quality assessment result of the video 10 in content recommendation and this video 10 and content recommendation。Wherein, the attribute difference opposite sex represents the difference of type between multimedia resource。Such as, if two videos belong to video of making laughs together, then the attribute difference opposite sex between them can be expressed as 0；If one is video of making laughs, another is sports video, then the attribute difference opposite sex between them can be expressed as 1。In other words, it is possible to specify as follows: the attribute difference opposite sex between similar video is 0, the attribute difference opposite sex between inhomogeneity video is 1。
It should be noted that, it it is more than attribute difference opposite sex one prescribed manner, the invention is not restricted to this, finer division can be carried out according to the size of diversity between multimedia resource, such as, being 0 by the attribute difference opposite sex between similar video, the attribute difference opposite sex between the video that video type difference is bigger is 1, and the attribute difference opposite sex that video type differs between less video is the value between 0～1。
So, according to the quality assessment result in step S120 and difference between each multimedia resource in content recommendation, it is possible to all multimedia resources in content recommendation are carried out temperature assessment。
After the temperature assessment result of all multimedia resources in obtaining content recommendation, it is possible to according to above-mentioned temperature assessment result, above-mentioned content recommendation is suitably processed, then result is recommended user。Such as, carry out by content recommendation multimedia resource resequence process or carry out the process deleted by some multimedia resource from content recommendation。
Such as, by conventional recommendation technology, it is recommended that system recommendation arranges as follows to the content recommendation of user sequentially: video 1, video 2 ..., video 9, video 10。Above-mentioned video is carried out after temperature assessment by the said method according to the present invention, commending system is recommended the content recommendation of user and is arranged possible as follows sequentially: video 9, video 2, video 1 ..., video 5, video 6, the sequence video 5,6 such as relying on title, sectional drawing etc. rearward can also be deleted, then again remaining video be recommended user。
Multimedia resource appraisal procedure according to embodiments of the present invention, based on the user behavior data corresponding with the multimedia resource in content recommendation this multimedia resource can be carried out quality evaluation and temperature assessment, thus processing being resequenced to the content that user recommends by conventional recommendation technology or carrying out being not desired to user the content directly rejecting etc. of viewing, then result is recommended again user。So, the content itself of the multimedia resource by with due regard to recommending, it is possible to reduce focus multimedia resource or title party, the impact on Consumer's Experience of the sectional drawing party multimedia resource, thus promoting Consumer's Experience。
Embodiment 2
Fig. 2 illustrates the flow chart of multimedia resource appraisal procedure according to another embodiment of the present invention。The step that in Fig. 2, label is identical with Fig. 1 has identical function, for simplicity's sake, omits the detailed description to these steps。
As in figure 2 it is shown, the differring primarily in that of multimedia resource appraisal procedure shown in the multimedia resource appraisal procedure shown in Fig. 2 and Fig. 1, the step S130 in Fig. 1 specifically can realize by performing step S140。
Step S140, calculate temperature assessment point according to the quality assessment result of multimedia resource and content recommendation。
In other words, it is possible to the form of the temperature assessment point by calculating in the present embodiment, the result carrying out temperature assessment in above-described embodiment is represented。
Such as, the video 1 of content recommendation that calculates according to the quality assessment result of multimedia resource and content recommendation, video 2 ..., video 9, the temperature assessment point respectively 9 points of video 10,2 points ..., 7 points, 5 points。
According to the assessment point of above-mentioned temperature, it is possible to above-mentioned video is re-started sequence according to the height of temperature assessment point, then recommends user。According to the threshold value pre-set, such as 5 point, the videos of less than 5 points can also be deleted from above-mentioned content recommendation, then recommend user again。
It should be noted that the present invention adopts the form example as temperature assessment result of temperature assessment point, but the invention is not restricted to this, those skilled in the art understand that, it is possible to adopts other rational form according to actual application scenarios。
In a kind of possible implementation, it is possible to concrete employing equation 1 below performs above-mentioned steps S120。
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of multimedia resource, V represents the broadcasting number of multimedia resource, C represents the number of reviews of multimedia resource, D represents the useful order of multimedia resource, what B represented multimedia resource steps on number, F represents the collection number of multimedia resource, T ' represents the issue duration of multimedia resource, this issue duration represents the difference between statistics end time and statistics time started, P represents the rate that finishes playing of multimedia resource, wherein, the rate that finishes playing of multimedia resource represents that the playing duration of this multimedia resource is worth divided by resource duration。Such as, using video as multimedia resource, video playback complete time, i.e. video duration are 2 hours, and now this video has only been play 1 hour, then the rate that finishes playing of multimedia resource is 0.5。
In a kind of possible implementation, the quality assessment result of multimedia resource can be showed by the form that quality evaluation divides, it is also possible to is showed by other form according to actual application scenarios。
In a kind of possible implementation, it is possible to adopt equation 2 below to perform above-mentioned steps S140。
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of multimedia resource, Rec represents that described multimedia resource occurs in the ratio of content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, and P represents the rate that finishes playing of described multimedia resource。
Occur in the ratio of content recommendation about multimedia resource, for instance, it is recommended that in content, one has 15 videos, namely video 1, video 2, video 3 ..., video 13, video 14, video 15。In a kind of possible implementation, above-mentioned content recommendation only shows first three video, namely video 1, video 2, video 3, and other video hide, at this moment represent these three video all occur in that once respectively。When such as pressing a certain button, three videos can be shown again, namely now be shown that video 1, video 2, video 3, video 4, video 5, video 6。At this moment represent that video 1, video 2, video 3 all occur in that twice, and video 4, video 5, video 6 all just occur once。The rest may be inferred, and during display all videos, video 1, video 2, video 3 all occur in that 5 times, then the Rec value of these three video is 100%；Video 4, video 5, video 6 all occur in that 4 times, then the Rec value of these three video is 80%；Video 7, video 8, video 9 all occur in that 3 times, then the Rec value of these three video is 60%；Video 10, video 11, video 12 all occur in that 2 times, then the Rec value of these three video is 40%；Video 13, video 14, video 15 all occur in that 2 times, then the Rec value of these three video is 20%。
Below it is only a kind of mode calculating Rec value, as long as the multimedia resource that can embody in content recommendation is in the calculation of the component shared by content recommendation。
By above-mentioned formula 2, user behavior data based on accessed a certain multimedia resource, after knowing that this multimedia resource occurs in the attribute difference opposite sex G of other multimedia resources in the ratio Rec of content recommendation, the quality assessment result Score of this multimedia resource, this multimedia resource and content recommendation and the rate P that finishes playing of multimedia resource, it becomes possible to calculate a temperature assessment point hotScore for multimedia resource。Then, come again to user's content recommendation according to calculated temperature assessment point。
So, by the multimedia resource appraisal procedure of the embodiment of the present invention, quality evaluation can be calculated with specific reference to above-mentioned formula 1 divide and calculate temperature assessment point according to above-mentioned formula 2, it is thus possible to based on the user behavior data corresponding with the multimedia resource in content recommendation this multimedia resource to be carried out quality evaluation and temperature assessment, thus processing being resequenced to the content that user recommends by conventional recommendation technology or carrying out being not desired to user the content directly rejecting etc. of viewing, then result is recommended again user。So, the content itself of the multimedia resource by with due regard to recommending, it is possible to reduce focus multimedia resource or title party, the impact on Consumer's Experience of the sectional drawing party multimedia resource, thus promoting Consumer's Experience。
Embodiment 3
Fig. 3 illustrates the structured flowchart of multimedia resource apparatus for evaluating according to an embodiment of the invention。This multimedia resource apparatus for evaluating 10 is mainly used in the multimedia resource in content recommendation is estimated。As it is shown on figure 3, multimedia resource apparatus for evaluating 10 mainly may include that acquiring unit 11, for obtaining the multiple user behavior datas corresponding with described multimedia resource in predetermined amount of time；Filter element 12, is connected with described acquiring unit 11, for multiple described user behavior datas are filtered；Quality estimation unit 13, is connected with described filter element 12, for described multimedia resource being carried out quality evaluation according to the user behavior data after filtering；And temperature assessment unit 14, it is connected with described filter element 12 and described quality estimation unit 13, for quality assessment result and the described content recommendation according to described multimedia resource, described multimedia resource is carried out temperature assessment。
In a kind of possible implementation, described user behavior data includes the broadcasting situation of user cookie, ID, the user processing mode to multimedia resource and handled multimedia resource, wherein, described processing mode includes playing, collect, comment on, push up and stepping on；Described broadcasting situation includes resource duration, playing duration, statistics time started and statistics end time。
In a kind of possible implementation, described temperature assessment unit 14 specifically for: according to the quality assessment result of described multimedia resource and described content recommendation calculate temperature assessment point。
In a kind of possible implementation, described quality estimation unit 13 adopts equation 1 below that described multimedia resource is carried out quality evaluation,
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of described multimedia resource, V represents the broadcasting number of described multimedia resource, C represents the number of reviews of described multimedia resource, D represents the useful order of described multimedia resource, what B represented described multimedia resource steps on number, F represents the collection number of described multimedia resource, T ' represents the difference between the statistics end time of described multimedia resource and statistics time started, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
In a kind of possible implementation, described temperature assessment unit 14 adopts equation 2 below to calculate the assessment point of described temperature,
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of described multimedia resource, Rec represents that described multimedia resource occurs in the ratio in described content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
The above-mentioned multimedia resource apparatus for evaluating 10 of the embodiment of the present invention can be used in performing the multimedia resource appraisal procedure described in above-described embodiment 1 or 2, and the idiographic flow of above-mentioned multimedia resource appraisal procedure refers to the relevant elaboration in above-described embodiment 1 or 2 to multimedia resource appraisal procedure。
By the multimedia resource apparatus for evaluating of the embodiment of the present invention, based on the user behavior data corresponding with the multimedia resource in content recommendation this multimedia resource can be carried out quality evaluation and temperature assessment, thus processing being resequenced to the content that user recommends by conventional recommendation technology or carrying out being not desired to user the content directly rejecting etc. of viewing, then result is recommended again user。So, the content itself of the multimedia resource by with due regard to recommending, it is possible to reduce focus multimedia resource or title party, the impact on Consumer's Experience of the sectional drawing party multimedia resource, thus promoting Consumer's Experience。
The above; being only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; change can be readily occurred in 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 described scope of the claims。
Claims (10)
1. a multimedia resource appraisal procedure, it is characterised in that for the multimedia resource in content recommendation is estimated, described multimedia resource appraisal procedure includes:
Obtain the multiple user behavior datas corresponding with described multimedia resource in predetermined amount of time；
Multiple described user behavior datas are filtered；
According to the user behavior data after filtering, described multimedia resource is carried out quality evaluation；And
Described multimedia resource is carried out temperature assessment by quality assessment result and described content recommendation according to described multimedia resource。
2. multimedia resource appraisal procedure according to claim 1, it is characterized in that, described user behavior data includes the broadcasting situation of user cookie, ID, the user processing mode to multimedia resource and handled multimedia resource, wherein, described processing mode includes playing, collect, comment on, push up and stepping on；Described broadcasting situation includes resource duration, playing duration, statistics time started and statistics end time。
3. multimedia resource appraisal procedure according to claim 2, it is characterised in that according to the quality assessment result of described multimedia resource and described content recommendation, described multimedia resource is carried out temperature assessment particularly as follows:
Quality assessment result and described content recommendation according to described multimedia resource calculate temperature assessment point。
4. multimedia resource appraisal procedure according to claim 3, it is characterised in that adopt equation 1 below to perform, according to the user behavior data after filtering, described multimedia resource is carried out quality evaluation,
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of described multimedia resource, V represents the broadcasting number of described multimedia resource, C represents the number of reviews of described multimedia resource, D represents the useful order of described multimedia resource, what B represented described multimedia resource steps on number, F represents the collection number of described multimedia resource, T ' represents the difference between the statistics end time of described multimedia resource and statistics time started, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
5. the multimedia resource appraisal procedure according to claim 3 or 4, it is characterised in that adopt equation 2 below to perform the quality assessment result according to described multimedia resource and described content recommendation calculates temperature assessment point,
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of described multimedia resource, Rec represents that described multimedia resource occurs in the ratio in described content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
6. a multimedia resource apparatus for evaluating, it is characterised in that for the multimedia resource in content recommendation is estimated, described multimedia resource apparatus for evaluating includes:
Acquiring unit, for obtaining the multiple user behavior datas corresponding with described multimedia resource in predetermined amount of time；
Filter element, is connected with described acquiring unit, for multiple described user behavior datas are filtered；
Quality estimation unit, is connected with described filter element, for described multimedia resource being carried out quality evaluation according to the user behavior data after filtering；And
Temperature assessment unit, is connected with described filter element and described quality estimation unit, for quality assessment result and the described content recommendation according to described multimedia resource, described multimedia resource is carried out temperature assessment。
7. multimedia resource apparatus for evaluating according to claim 6, it is characterized in that, described user behavior data includes the broadcasting situation of user cookie, ID, the user processing mode to multimedia resource and handled multimedia resource, wherein, described processing mode includes playing, collect, comment on, push up and stepping on；Described broadcasting situation includes resource duration, playing duration, statistics time started and statistics end time。
8. multimedia resource apparatus for evaluating according to claim 7, it is characterised in that described temperature assessment unit specifically for:
Quality assessment result and described content recommendation according to described multimedia resource calculate temperature assessment point。
9. multimedia resource apparatus for evaluating according to claim 8, it is characterised in that described quality estimation unit adopts equation 1 below that described multimedia resource is carried out quality evaluation,
Score=((V+C+D-B+F)/T ') * P formula 1
Wherein, Score represents the quality assessment result of described multimedia resource, V represents the broadcasting number of described multimedia resource, C represents the number of reviews of described multimedia resource, D represents the useful order of described multimedia resource, what B represented described multimedia resource steps on number, F represents the collection number of described multimedia resource, T ' represents the difference between the statistics end time of described multimedia resource and statistics time started, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
10. multimedia resource apparatus for evaluating according to claim 8 or claim 9, it is characterised in that described temperature assessment unit adopts equation 2 below to calculate the assessment point of described temperature,
HotScore=Rec*Scroe*G/P formula 2
Wherein, hotScore represents the temperature assessment point of described multimedia resource, Rec represents that described multimedia resource occurs in the ratio in described content recommendation, Score represents the quality assessment result of described multimedia resource, G represents the attribute difference opposite sex of described multimedia resource and other multimedia resources in described content recommendation, P represents the rate that finishes playing of described multimedia resource, described in finish playing playing duration that rate is described multimedia resource divided by resource duration。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610029193.2A CN105701226A (en) | 2016-01-18 | 2016-01-18 | Multimedia resource assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610029193.2A CN105701226A (en) | 2016-01-18 | 2016-01-18 | Multimedia resource assessment method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105701226A true CN105701226A (en) | 2016-06-22 |
Family
ID=56227463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610029193.2A Pending CN105701226A (en) | 2016-01-18 | 2016-01-18 | Multimedia resource assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701226A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604137A (en) * | 2016-12-29 | 2017-04-26 | Tcl集团股份有限公司 | Method and apparatus for predicting video viewing time length |
| CN106656768A (en) * | 2017-02-09 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Resource recommendation method and apparatus |
| CN107493467A (en) * | 2017-07-06 | 2017-12-19 | 北京奇艺世纪科技有限公司 | A kind of video quality evaluation method and device |
| CN108595492A (en) * | 2018-03-15 | 2018-09-28 | 腾讯科技（深圳）有限公司 | Method for pushing and device, storage medium, the electronic device of content |
| CN109068158A (en) * | 2018-09-18 | 2018-12-21 | 苏州商信宝信息科技有限公司 | A kind of short-sighted frequency value estimate recommender system based on the network platform |
| CN109168044A (en) * | 2018-10-11 | 2019-01-08 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of video features |
| CN109547856A (en) * | 2018-12-18 | 2019-03-29 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN110598046A (en) * | 2019-09-17 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Artificial intelligence-based identification method and related device for title party |
| CN111147886A (en) * | 2020-01-06 | 2020-05-12 | 郑红 | Multimedia file playing processing method and device |
| CN111708944A (en) * | 2020-06-17 | 2020-09-25 | 北京达佳互联信息技术有限公司 | Multimedia resource identification method, device, equipment and storage medium |
| CN107423262B (en) * | 2017-08-10 | 2020-10-09 | 四川长虹电器股份有限公司 | Method for evaluating output result of autonomous recommendation algorithm based on third-party data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130339434A1 (en) * | 2012-06-19 | 2013-12-19 | Microsoft Corporation | Automatically Generating Music Marketplace Editorial Content |
| CN104506894A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for evaluating multi-media resources |
| CN104504059A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Multimedia resource recommending method |
| CN104933129A (en) * | 2015-06-12 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Event context acquisition method and system based on micro-blogs |
-
2016
- 2016-01-18 CN CN201610029193.2A patent/CN105701226A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130339434A1 (en) * | 2012-06-19 | 2013-12-19 | Microsoft Corporation | Automatically Generating Music Marketplace Editorial Content |
| CN104506894A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for evaluating multi-media resources |
| CN104504059A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Multimedia resource recommending method |
| CN104933129A (en) * | 2015-06-12 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Event context acquisition method and system based on micro-blogs |
Non-Patent Citations (2)
| Title |
|---|
| 中国电影家协会中国文联电影艺术中心: "《中国电影产业研究报告》", 31 July 2014, 中国电影出版社 * |
| 向志强: "《2012年中国传媒产品质量评估报告》", 31 December 2014, 新华出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604137A (en) * | 2016-12-29 | 2017-04-26 | Tcl集团股份有限公司 | Method and apparatus for predicting video viewing time length |
| CN106656768A (en) * | 2017-02-09 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Resource recommendation method and apparatus |
| CN106656768B (en) * | 2017-02-09 | 2020-06-23 | 腾讯科技（深圳）有限公司 | Resource recommendation method and device |
| CN107493467A (en) * | 2017-07-06 | 2017-12-19 | 北京奇艺世纪科技有限公司 | A kind of video quality evaluation method and device |
| CN107423262B (en) * | 2017-08-10 | 2020-10-09 | 四川长虹电器股份有限公司 | Method for evaluating output result of autonomous recommendation algorithm based on third-party data |
| CN108595492A (en) * | 2018-03-15 | 2018-09-28 | 腾讯科技（深圳）有限公司 | Method for pushing and device, storage medium, the electronic device of content |
| CN109068158A (en) * | 2018-09-18 | 2018-12-21 | 苏州商信宝信息科技有限公司 | A kind of short-sighted frequency value estimate recommender system based on the network platform |
| CN109068158B (en) * | 2018-09-18 | 2021-06-22 | 上海众引文化传播股份有限公司 | Short video value estimation recommendation system based on network platform |
| CN109168044A (en) * | 2018-10-11 | 2019-01-08 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of video features |
| CN109168044B (en) * | 2018-10-11 | 2021-07-23 | 北京奇艺世纪科技有限公司 | Method and device for determining video characteristics |
| CN109547856B (en) * | 2018-12-18 | 2020-11-20 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN109547856A (en) * | 2018-12-18 | 2019-03-29 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
| CN110598046A (en) * | 2019-09-17 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Artificial intelligence-based identification method and related device for title party |
| CN111147886A (en) * | 2020-01-06 | 2020-05-12 | 郑红 | Multimedia file playing processing method and device |
| CN111147886B (en) * | 2020-01-06 | 2021-12-03 | 深圳市超维互动科技有限公司 | Multimedia file playing processing method and device |
| CN111708944A (en) * | 2020-06-17 | 2020-09-25 | 北京达佳互联信息技术有限公司 | Multimedia resource identification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701226A (en) | Multimedia resource assessment method and device | |
| CN107038213B (en) | Video recommendation method and device | |
| US9967628B2 (en) | Rating videos based on parental feedback | |
| US9015109B2 (en) | Systems, methods, and computer readable media for maintaining recommendations in a media recommendation system | |
| KR101832996B1 (en) | Enhanced program guide | |
| CN104053023B (en) | A kind of method and device of determining video similarity | |
| JP5285196B1 (en) | Recommended content providing apparatus, recommended content providing program, and recommended content providing method | |
| US20140122590A1 (en) | Systems, methods, and computer readable media for selecting a playhead in social media playback | |
| CN103686237A (en) | Method and system for recommending video resource | |
| CN107454442B (en) | Method and device for recommending video | |
| CN104216883A (en) | Video recommendation reason generating system and method | |
| US9659256B2 (en) | Network service recommendation method and apparatus | |
| JP2008547108A5 (en) | ||
| CN109684507A (en) | Video recommendation method, video recommendations device and computer readable storage medium | |
| KR20130090344A (en) | Apparatus, system, method and computer readable recording media storing the program for related recommendation of tv program contents and web contents | |
| CN107562848B (en) | Video recommendation method and device | |
| CN105163183B (en) | A kind of screening technique and device of video pictures | |
| CN111523050B (en) | Content recommendation method, server and storage medium | |
| CN106980666B (en) | Method and device for recommending video | |
| CN106534984B (en) | Television program pushing method and device | |
| CN105208409B (en) | A kind of information recommendation method and device | |
| CN109688217B (en) | Message pushing method and device and electronic equipment | |
| CN103942247A (en) | Information providing method and device of multimedia resources | |
| JP2012222569A (en) | Broadcast-program recommending device, method and program | |
| CN110381339B (en) | Picture transmission 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 | ||
| CB02 | Change of applicant information |
Address after: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant after: Youku network technology (Beijing) Co.,Ltd. Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant before: 1VERGE INTERNET TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200617 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant before: Youku network technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160622 |
|
| RJ01 | Rejection of invention patent application after publication |