CN113242459A - New video exposure method, device, medium and computer equipment - Google Patents
New video exposure method, device, medium and computer equipment Download PDFInfo
- Publication number
- CN113242459A CN113242459A CN202110789845.3A CN202110789845A CN113242459A CN 113242459 A CN113242459 A CN 113242459A CN 202110789845 A CN202110789845 A CN 202110789845A CN 113242459 A CN113242459 A CN 113242459A
- Authority
- CN
- China
- Prior art keywords
- new video
- current new
- video
- determining
- user group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26266—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for determining content or additional data repetition rate, e.g. of a file in a DVB carousel according to its importance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a new video exposure method, a device, a medium and computer equipment, wherein the method comprises the following steps: determining the release flow required by the current new video; determining at least one directional user group of the current new video; determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video; determining the distribution probability of at least one directional user group to the current new video; and exposing the current new video in the corresponding directional user group based on the priority and the distribution probability. Therefore, when the video is exposed, the priority is determined by considering the promotion coefficient and the penalty coefficient of the current new video, so that the high-quality video can be fully exposed; and when the current new video is exposed, the current new video can be exposed in the directional user group based on the issuing probability, the click rate of the current new video is ensured, and the waste of flow is avoided.
Description
Technical Field
The invention belongs to the technical field of live broadcast platform video recommendation, and particularly relates to a new video exposure method, a device, a medium and computer equipment.
Background
In video recommendations, new videos are often difficult to expose due to lack of support for historical data. In terms of content ecology, the video is high in timeliness, and new videos need to be recommended in time, so that the new videos are very important. And the up owner (uploader) hopes more people to see after releasing the video, thus arousing the creation enthusiasm of the up owner.
In the related art, it is general to forcibly insert a new video at a specific position. Therefore, although the exposure of new videos can be guaranteed, the exposure amount is very difficult to control, some videos with low quality or narrow target groups cause flow waste, some high-quality videos cannot be fully exposed, and the exposure effect is not ideal.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a new video exposure method, a device, a medium and computer equipment, which are used for solving the technical problem that high-quality videos cannot be fully exposed in time when new video exposure is carried out in the prior art.
The invention provides a new video exposure method, which comprises the following steps:
determining the release flow required by the current new video;
determining at least one directed user group of the current new video;
determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video;
determining a distribution probability of the at least one directed user group to the current new video;
and exposing the current new video in a corresponding directional user group based on the priority and the release probability of the current new video.
Optionally, the determining the distribution flow required by the current new video includes:
acquiring all historical videos issued by the issuer of the current new video within a preset time period;
and acquiring the daily average basic flow of the historical videos, and determining the daily average basic flow as the release flow required by the current new video.
Optionally, before determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video, the method further includes:
based on the formula
Determining a boost factor for the current new video
(ii) a Wherein, theeIs an exponential function ofaTo increase the coefficient-of-influence factor, saidLThe video click conversion rate of the video uploader of the current new video in a preset time period is shown in the specificationbAnd the video click conversion rates of all video uploads of the live platform are 0.5 quantiles in a sequence from small to large.
Optionally, before determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video, the method further includes:
according to the formula
Determining a penalty factor for the current new video
(ii) a Wherein, thesAs a penalty factor, theiIs the sequence number of the penalty factor, the
Is as followsiA statistical number of penalty factors, said
Is a first penalty factor influence factor, said
Is a second penalty factor impact factor.
Optionally, the determining at least one directional user group of the current new video includes:
based on the formula
Determining a target orientation index of the current new video in each user groupT；
If the target orientation index is larger than a preset orientation threshold value, taking a user group corresponding to the target orientation index as an oriented user group of the current new video; wherein, the
Is the first of the user groupmA kind of attribute, saidmIs an attribute of the user group, thejIs a category of the attribute, the
Is as followsmThe second corresponding to the kind attributejGenus of attribute, said
Is as followsmThe second corresponding to the kind attributejThe method comprises the steps that a user group of a kind of attribute type watches the total duration of a target video in a preset time period, wherein the target video is all videos published by a publisher of a current new video in the preset time period; the above-mentioned
Is as followsmThe second corresponding to the kind attributejThe number of users within the user group of the category of the attribute.
Optionally, the determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video includes:
based on the formula
Determining the priority of the current new video; wherein, the
To determine that all the directional user groups satisfying the current new video can be the current new videokSum of the provided flow rates;
for the current new videokRequired publication traffic, saidkIs the identity of the current new video.
Optionally, the determining the distribution probability of the at least one directed user group to the current new video includes:
obtaining the total flow rate that each directed user group can supply aiming at the current new video
And the current remaining traffic of each of the directed user groups
(ii) a The above-mentionedtIs any directional user group;
according to the formula
Determining the distribution probability of each user in the directional user group to the current new video
(ii) a Wherein, thekFor identification of the current new video, the
For the current new videokCorresponding publication traffic.
The present invention also provides a new video exposure apparatus, the apparatus comprising:
the first determining unit is used for determining the release flow required by the current new video;
a second determining unit, configured to determine at least one directional user group of the current new video;
the third determining unit is used for determining the priority of the current new video based on the lifting coefficient of the current new video flow and the penalty coefficient of the current new video flow;
a fourth determining unit, configured to determine a distribution probability of the at least one directed user group to the current new video;
and the distribution unit is used for exposing the current new video in a corresponding directional user group based on the priority and the distribution probability of the current new video.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements the method of any one of the above.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of the above when executing the program.
The invention provides a new video exposure method, a device, a medium and computer equipment, wherein the method comprises the following steps: determining the release flow required by the current new video; determining a directional user group of the current new video; determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video; determining the distribution probability of each user in the directional user group to the current new video; and carrying out flow distribution on the distribution flow in the corresponding user based on the priority and the distribution probability of the current new video, and exposing the current new video. Therefore, when the embodiment of the invention exposes the video, the improvement coefficient and the punishment coefficient of the current new video are considered, the higher the improvement coefficient is, the higher the quality of the current new video is, and the higher the punishment coefficient is, the worse the quality of the current new video is, so that the video exposure quality of a live broadcast platform can be ensured, and the high-quality video can be preferentially exposed; and when the current new video is exposed, the issuing probability of the current new video can be accurately exposed based on the directional user group, the click rate of the current new video is ensured, and the waste of flow is avoided.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic flow chart of a new video exposure method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a new video exposure apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a computer medium structure for a new video exposure provided by an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device for new video exposure according to an embodiment of the present invention.
Detailed Description
In order to solve the technical problem that a high-quality video cannot be fully exposed in time when a new video is exposed in the prior art, the embodiment of the invention provides a new video exposure method, a device, a medium and computer equipment.
The technical solution of the present invention is further described in detail by the accompanying drawings and the specific embodiments.
The present embodiment provides a new video exposure method, as shown in fig. 1, the method includes:
s110, determining the release flow required by the current new video;
for any current new video, before being published, the publishing flow required by the current new video needs to be determined so as to distribute proper nodes in subsequent publishing. In this embodiment, determining the publishing flow required by the current new video includes:
acquiring all historical videos issued by a publisher of a current new video within a preset time period;
and acquiring the daily average basic flow of the historical video in the preset time period, and determining the daily average basic flow as the release flow required by the current new video.
Wherein, because the video distribution has timeliness, if the preset time period is too long, the real actual flow cannot be reflected because the timeliness video exposure gradually attenuates. In the embodiment, the preset time period is set to be 2-30 days, so that the daily average basic flow in the preset time period can truly reflect the publishing flow required by the current new video, and the distribution precision can be improved during subsequent flow distribution.
S111, determining at least one directional user group of the current new video;
because the user groups facing different types of videos are different, if the videos are exposed in the user groups which are not suitable for matching, the click rate is seriously influenced, the creation enthusiasm of the uploader is influenced, and the flow is wasted.
In order to improve the click rate of the current new video and avoid traffic waste, the present embodiment needs to determine an oriented user group of the current new video, which specifically includes:
based on the formula
Determining target orientation index of current new video in each user groupT；
And if the target orientation index is larger than the preset orientation threshold value, taking the user group corresponding to the target orientation index as the orientation user group of the current new video.
Wherein the content of the first and second substances,
is the first of a user groupmThe type of the attribute is selected from the group,mas an attribute of the user group,jfor the purpose of the category of the attribute,
is as followsmThe second corresponding to the kind attributejThe category of the attribute is that,
is as followsmThe second corresponding to the kind attributejThe method comprises the steps that a user group of a kind of attribute type watches the total duration of a target video in a preset time period, wherein the target video is all videos released by a publisher of a current new video in the preset time period;
is as followsmThe second corresponding to the kind attributejWithin user group of attribute categoriesThe number of users.
The attributes may include gender, age, hobbies, and the like.
For example, assume whenmIf =1, represents sex, then
I.e. representing the gender of the user group, the gender may comprise two, thenj=1 orjAnd (2). When in usejWhen the ratio is not less than 1,
represents a male; when in usejWhen the ratio is not less than =2,
representing a female.
If it is
=60，
=40，
=3000h，
=1000 h; then:
if the orientation threshold is 1, then
Above the orientation threshold value, the orientation of the orientation,
less than the orientation threshold, may be
The corresponding group of female users serves as a directed group of users. Therefore, a suitable directional user group can be found for the current new video, and the click rate of the current new video is improved.
It can be understood that, in this step, it is equivalent to divide all traffic on the platform into a plurality of directed population traffic nodes according to the user group, where each directed user group represents a traffic node, and for example (gender = man, age = 18-25 years), it is referred to as a directed user group or a traffic node; (gender = girl, age = 18-25 years) is another directed user group or called another traffic node, etc., which are mutually exclusive. According to the calculated directional index of the directional user group, the flow node meeting the current new video can be accurately determined.
The principle of the above orientation index formula is as follows:
the viewing time of the user group representing the current attribute category is proportional to the total user group,
the number of the user group representing the current attribute category in the whole user group is proportional; if it is
The larger the value of (a) is, the greater the probability that the user group of the attribute category views the current video is, the greater the probability that the user group of the attribute category is taken as the directed user group is.
In this step, since the new video cannot obtain the relevant historical behavior data, the embodiment determines the watching condition of the user with different attributes in the preset time period to the video publisher corresponding to the current new video according to the attribute cut-in of the user, and then according to the result
The directional user group is determined according to the value of the video index, so that the click probability of the current new video can be improved, and the waste of flow is avoided.
S112, determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video;
because the quality of the new video is related to the content ecological environment of the live broadcast platform, if some low-quality videos are exposed on the platform, the loss of the high-quality videos can be caused, the creation enthusiasm of a publisher of the high-quality videos can be reduced, and the platform flow can be wasted.
Therefore, after determining the directional user group of the current new video, it is further required to determine the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video, and the priority can be understood as the exposure priority.
Specifically, the embodiment can be based on the formula
Determining the priority Z of the current new video; wherein the content of the first and second substances,
to determine that all the directional user groups satisfying the current new video can be currentNew videokSum of the provided flow rates;
for the current new videokRequired publication traffic.
Specifically, before determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video, the method further includes:
based on the formula
Determining a boost coefficient for a current new video
(ii) a Wherein the content of the first and second substances,ein order to be an exponential function of the,athe value range of the factor is 0-1, preferably 0.5, for improving the coefficient influence factor;Lthe video click conversion rate of the video uploader of the current new video within the preset time period is obtained,b(0.5 quantile) of video click conversion rate of all video uploaders of the live platform in a descending ordermAlso understood as the average click conversion rate of the platform). And the video click conversion rate is the ratio of the click rate and the exposure of the video.
The principle of the formula for determining the lifting coefficient is as follows: if the click conversion rate of the video publisherLThe average click conversion rate of the platform is higher, then additional exposure rewards can be obtained, and the higher the click conversion rate is, the larger the promotion coefficient is. The advantage of using an exponential function in the formula for determining the lifting coefficient is: when the click conversion rate is higher, the lifting difficulty of the lifting coefficient is higher, so that the probability of exposure is more related to the extra exposure reward.
For example, assuming that the lifting coefficient impact factor is 1,b=0.05, whenLVery small (e.g. in the case ofL=0.04），LAfter the lifting is carried out for 0.01,Lis 0.05, then the increment of the lifting factor is:
=1-0.99=0.01
when in useLWhen it is too large (e.g. due to the use of a large scale motor)L=0.25），LAfter the lifting is carried out for 0.01,Lis 0.26, then the increment of the lifting factor is
. It can be seen that, due to the marginal utility, the higher the click rate conversion rate is, the larger the boost coefficient is, but the greater the boost difficulty (incremental change) of the boost coefficient is, that is, when the click conversion rate is higher, the greater the boost difficulty of the boost coefficient is, so that the more the probability of exposure is related to the extra exposure reward.
The above boosting coefficients have the benefits that: when the overall click rate of the video publisher is low, more exposure can be obtained as long as a certain click conversion rate is reached, so that the power of the video publisher for improving the video quality can be improved, and the video quality in the platform is improved.
Before determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video, the method further comprises:
according to the formula
Determining penalty coefficients for a current new video
(ii) a Wherein the content of the first and second substances,sin order to be a penalty factor,ifor the sequence number of the penalty factor,
is as followsiThe statistical number of the individual penalty factors,
the first penalty coefficient influence factor is selected, and the value range is 0-1, preferably 0.5;
the value range of the second penalty coefficient influence factor is 0-1, and the value range is preferably 0.5. Among them, the penalty factors may include: number of complaints, video cover violationThe number of times is not specifically listed here.
For example, if the penalty factor includes only 1 type (number of complaints), and the number of complaints is 2, then
。
The principle of the formula for determining the penalty coefficient is as follows: the penalty factor is a factor between 0 and 1, and each penalty factor needs to be considered. Since each penalty factor is independent, the present embodiment measures the influence of each penalty factor by means of multiplication. For a single penalty factor, use is made of
The index function is characterized by the influence of a single penalty factor if
If the value becomes large, the influence value of a single penalty factor becomes large; when the statistical number of the penalty factors is 0, the influence value is 0, namely no influence is generated; meanwhile, the increase is not linear, and as the statistical number of penalty factors increases, the larger the penalty strength required to be applied is, the larger the influence value is, so that an exponential form is selected in the formula, and two penalty factor influence factors are adopted
And
to adjust the impact value. That is, the platform determines the hazard of each penalty factor and the tolerance to that factor, and the higher the hazard level is, the lower the tolerance is, and then the adjustment is made
And
when it is needed to increase
And
to increase the value of the penalty factor.
The benefits of determining the penalty factor described above are: so that videos like the title party, cover party, and edge ball content can get a corresponding penalty. Because such videos often have a higher click rate, if the traffic is occupied by such videos, the overall video creation atmosphere of the platform is affected, and the ecological construction and sustainable development of the platform videos are not facilitated.
In the step, the video quality is judged through the punishment coefficient and the promotion coefficient, and then the exposure priority of the video is determined according to the video quality, so that the high-quality video can obtain more exposure opportunities, the video quality in the platform is further promoted, and the ecological construction and sustainable development of the video in the platform are promoted.
S113, determining the distribution probability of the at least one directional user group to the current new video;
the remaining traffic of each directed user group is different, so the distribution probability of each directed user group to the current new video needs to be determined, so as to improve the distribution success rate of the current new video.
Determining a distribution probability of at least one directed user group to a current new video, comprising:
obtaining the total flow rate that each directed user group can supply aiming at the current new video
And the current remaining traffic for each directed user group
；tIs any directional user group;
according to the formula
Determining the distribution probability of each directional user group to the current new video
(ii) a Wherein the content of the first and second substances, kfor the identification of the current new video,
for the current new videokThe corresponding distribution traffic is sent to the corresponding distribution network,
to satisfy the current new videokIs directed to a set of user groups.
The principle of the above formula is: by passing
Determining the flow which each directional user group should provide for the current new video, if the directional user grouptWhen the remaining traffic is sufficient, the user group can provide the traffic as
(ii) a If user grouptThe remaining traffic is not enough, and the user group is in the momenttThe only flow that can be given is the residual flow
(ii) a Thus, for each user grouptIn the formula, take
And
the minimum value in between. Therefore, all the user groups meeting the conditions can determine the available flow, the sum of the flows available for all the user groups is the display flow available for the current new video, and the sum of the flows should be equal to the distribution flow of the current new video.
Thus, due to each directed user group
、
And the distribution flow of the current new video
Are known, therefore, the distribution probability of each directed user group to the current new video can be solved by the formula
。
Find the optimum
If not, then all the display pit nodes are not enough
=1。
For example, if it is determined that the number of targeted user groups satisfying the current new video includes 6 for the current new video, the flow rate that each user group can provide and the remaining flow rate for each user group are shown in table 1:
TABLE 1
As shown in the table 1 below, the following examples,
is a raw material for the raw material of 1800,
=1400, assuming that the current video requires a traffic of 1000K, then
=1000；
The sum of the residual flow of the six directional user groups; determining publication probability
The steps are as follows:
according to the formula
=
/
=1000/1800= 5/9 determines that the initial issuance probability is 5/9;
substituting the formula to obtain:
min(300, 400* 
) + min(300, 400 * 
) + min(0, 100 * 
)+min(0, 100 *
)+ min(500, 500 *
) +min(300,300*
)= 1000
simplifying to obtain:
400 * 
+ 400 * 
+ 0 +0+ 500 * 
+ 300 * 
= 1000
1600 *
= 1000
that is, there is remaining traffic for the directed user groups 1, 2, 5, 6, and the probability that the current new video will be exposed to the current new video in the directed user groups numbered 1, 2, 5, 6 is 5/8 (5 will be randomly selected to be exposed in every 8 users). However, in practical applications, all users of the directional user group may not be in the live platform at the same time, so that in this embodiment, when the current new video is exposed based on the exposure probability, it is essentially required to perform a random calculation for each user in the directional user groups numbered 1, 2, 5, and 6, specifically for each user, a value between 0 and 1 is randomly selected, and if the value is less than or equal to 5/8, the current new video is exposed to the user; if the value is greater than 5/8, the user is not exposed to the current new video.
For example:
is a raw material for the raw material of 1800,
=1400, assuming that the current video requires 2000K of traffic
= 2000; determining publication probability
The steps are as follows:
according to the formula
=
/
=2000/1800= 10/9 determines that the initial issuance probability is 10/9;
it is obvious that
>1, therefore
= 1；
Substituting the formula yields:
min(300，400 * 1) + min(300，400 * 1) + min(0, 100 * 1) + min(0， 100 * 1)+min(500，500*1)+min(300，300*1) = 2000
because:
300 + 300 + 0 + 0 + 500 + 300 < 2000
therefore, it is not only easy to use
=1 true.
In this example, the current new video needs to have a larger demand for the amount of the browser than the amount of the browser, and therefore, all the amounts of the browser need to be exposed to the current new video. That is, there is remaining traffic for the directional user groups 1, 2, 5, and 6, the probability that the current new video is exposed to the current new video in the directional user groups numbered 1, 2, 5, and 6 is 1, and the current new video is exposed to the users in the directional user groups numbered 1, 2, 5, and 6.
It is noted that the remaining traffic per user is changing in real time, so after a new video is exposed, it needs to be formulated according to the formula
Determining updated remaining flow
。
In the step, the probability of issuing the current new video by each user in the directional user group is determined, and the exposure success rate and the click rate of the current new video can be improved based on issuing the accurate exposure current new video.
S114, exposing the current new video in the corresponding user group based on the priority and the issuing probability of the current new video.
And after the distribution probability of the current new video is determined, exposing the current new video in the corresponding user group based on the priority and the distribution probability of the current new video.
In the step, the exposure sequence is determined according to the priority of the current new video, and the exposure probability of the video with high priority is higher than that of the video with low priority, so that the exposure probability of the video with high quality can be improved, and the video quality in the platform is further improved.
When in exposure, the current new video is exposed according to the issuing probability, so that the exposure success rate and the click rate of the current new video can be ensured.
Based on the same inventive concept as the previous embodiment, an embodiment of the present invention further provides a new video exposure apparatus, as shown in fig. 2, the apparatus including:
a first determining unit 21, configured to determine a distribution flow required by a current new video;
a second determining unit 22, configured to determine at least one directional user group of the current new video;
a third determining unit 23, configured to determine a priority of the current new video based on a boost coefficient of the current new video traffic and a penalty coefficient of the current new video traffic;
a fourth determining unit 24, configured to determine a distribution probability of the at least one directed user group to the current new video;
and the distribution unit is used for exposing the current new video in the corresponding directional user group based on the priority and the issuing probability of the current new video.
Since the apparatus described in the embodiment of the present invention is an apparatus used for implementing the method in the embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the apparatus based on the method described in the embodiment of the present invention, and thus the detailed description is omitted here. All devices adopted by the method of the embodiment of the invention belong to the protection scope of the invention.
Based on the same inventive concept as the previous embodiment, an embodiment of the present invention further provides a computer apparatus, as shown in fig. 3, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320, where the processor 320 executes the computer program 311 to implement the following steps:
determining the release flow required by the current new video;
determining at least one directed user group of the current new video;
determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video;
determining a distribution probability of the at least one directed user group to the current new video;
and exposing the current new video in a corresponding directional user group based on the priority and the release probability of the current new video.
In a specific implementation, when the processor 320 executes the computer program 311, any of the embodiments described above may be implemented.
Since the computer device described in this embodiment is a device used for implementing a new video exposure method in the foregoing embodiment of the present invention, a person skilled in the art can understand a specific implementation manner of the computer device of this embodiment and various variations thereof based on the method described in the foregoing embodiment of the present invention, and therefore, a detailed description of how the server implements the method in the embodiment of the present invention is not provided here. The equipment used by those skilled in the art to implement the method in the embodiments of the present invention is within the scope of the present invention.
Based on the same inventive concept as the previous embodiment, the present embodiment provides a computer-readable storage medium 400, as shown in fig. 4, on which a computer program 411 is stored, the computer program 411 implementing the following steps when executed by a processor:
determining the release flow required by the current new video;
determining at least one directed user group of the current new video;
determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video;
determining a distribution probability of the at least one directed user group to the current new video;
and exposing the current new video in a corresponding directional user group based on the priority and the release probability of the current new video.
In a specific implementation, the computer program 411 may implement any of the above embodiments when executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
The new video exposure method, the device, the medium and the computer equipment provided by the embodiment of the application have the following beneficial effects that:
the invention provides a new video exposure method, a device, a medium and computer equipment, wherein the method comprises the following steps: determining the release flow required by the current new video; determining a directional user group of the current new video; determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video; determining the distribution probability of each user in the directional user group to the current new video; and carrying out flow distribution on the distribution flow in the corresponding user based on the priority and the distribution probability of the current new video, and exposing the current new video. Therefore, when the embodiment of the invention exposes the video, the improvement coefficient and the punishment coefficient of the current new video are considered, the higher the improvement coefficient is, the higher the quality of the current new video is, and the higher the punishment coefficient is, the worse the quality of the current new video is, so that the video exposure quality of a live broadcast platform can be ensured, and the high-quality video can be preferentially exposed; and when the current new video is exposed, the issuing probability of the current new video is accurately exposed based on each directional user group, the click rate of the current new video is ensured, and the waste of flow is avoided.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, and any modifications, equivalents, improvements, etc. that are within the spirit and principle of the present invention should be included in the present invention.
Claims (10)
1. A new video exposure method, the method comprising:
determining the release flow required by the current new video;
determining at least one directed user group of the current new video;
determining the priority of the current new video based on the lifting coefficient of the current new video and the punishment coefficient of the current new video;
determining a distribution probability of the at least one directed user group to the current new video;
and exposing the current new video in a corresponding directional user group based on the priority and the release probability of the current new video.
2. The method of claim 1, wherein said determining the publication traffic required for the current new video comprises:
acquiring all historical videos issued by the issuer of the current new video within a preset time period;
and acquiring the daily average basic flow of the historical videos, and determining the daily average basic flow as the release flow required by the current new video.
3. The method of claim 1, wherein prior to determining the priority of the current new video based on the boost coefficient for the current new video and the penalty coefficient for the current new video, the method further comprises:
based on the formula
Determining a boost factor for the current new video
(ii) a Wherein, theeIs an exponential function ofaTo increase the coefficient-of-influence factor, saidLThe video click conversion rate of the video uploader of the current new video in a preset time period is shown in the specificationbAnd the video click conversion rates of all video uploads of the live platform are 0.5 quantiles in a sequence from small to large.
4. The method of claim 1, wherein prior to determining the priority of the current new video based on the boost coefficient for the current new video and the penalty coefficient for the current new video, the method further comprises:
according to the formula
Determining a penalty factor for the current new video
(ii) a Wherein, thesAs a penalty factor, theiIs the sequence number of the penalty factor, the
Is as followsiA statistical number of penalty factors, said
Is a first penalty factor influence factor, said
Is a second penalty factor impact factor.
5. The method of claim 1, wherein said determining at least one targeted user group for the current new video comprises:
based on the formula
Determining a target orientation index of the current new video in each user groupT；
If the target orientation index is larger than a preset orientation threshold value, taking a user group corresponding to the target orientation index as an oriented user group of the current new video; wherein, the
Is the first of the user groupmA kind of attribute, saidmIs an attribute of the user group, thejIs a category of the attribute, the
Is as followsmThe second corresponding to the kind attributejGenus of attribute, said
Is as followsmThe second corresponding to the kind attributejThe method comprises the steps that a user group of a kind of attribute type watches the total duration of a target video in a preset time period, wherein the target video is all videos published by a publisher of a current new video in the preset time period; the above-mentioned
Is as followsmThe second corresponding to the kind attributejThe number of users within the user group of the category of the attribute.
6. The method of claim 1, wherein the determining the priority of the current new video based on the boost coefficient of the current new video and the penalty coefficient of the current new video comprises:
based on the formula
Determining the priority of the current new video; wherein, the
To determine that all the directional user groups satisfying the current new video can be the current new videokSum of the provided flow rates;
for the current new videokRequired publication traffic, saidkFor identification of the current new video, the
For the lifting coefficient of the current new video, the
And the penalty coefficient is the penalty coefficient of the current new video.
7. The method of claim 1, wherein the determining the distribution probability of the at least one directed user group for the current new video comprises:
obtaining the total flow rate that each directed user group can supply aiming at the current new video
And the current remaining traffic of each of the directed user groups
(ii) a The above-mentionedtIs any directional user group;
according to the formula
Determining the distribution probability of each user in the directional user group to the current new video
(ii) a Wherein, thekFor identification of the current new video, the
For the current new videokCorresponding publication traffic.
8. A new video exposure apparatus, characterized in that the apparatus comprises:
the first determining unit is used for determining the release flow required by the current new video;
a second determining unit, configured to determine at least one directional user group of the current new video;
the third determining unit is used for determining the priority of the current new video based on the lifting coefficient of the current new video flow and the penalty coefficient of the current new video flow;
a fourth determining unit, configured to determine a distribution probability of the at least one directed user group to the current new video;
and the distribution unit is used for exposing the current new video in a corresponding directional user group based on the priority and the distribution probability of the current new video.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110789845.3A CN113242459B (en) | 2021-07-13 | 2021-07-13 | New video exposure method, device, medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110789845.3A CN113242459B (en) | 2021-07-13 | 2021-07-13 | New video exposure method, device, medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113242459A true CN113242459A (en) | 2021-08-10 |
| CN113242459B CN113242459B (en) | 2021-10-15 |
Family
ID=77135467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110789845.3A Active CN113242459B (en) | 2021-07-13 | 2021-07-13 | New video exposure method, device, medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113242459B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114374881A (en) * | 2022-01-05 | 2022-04-19 | 北京百度网讯科技有限公司 | Method and device for distributing user flow, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009303033A (en) * | 2008-06-16 | 2009-12-24 | Hitachi Kokusai Electric Inc | Video reproduction method, video reproduction device and video distribution system |
| JP2015037290A (en) * | 2013-08-15 | 2015-02-23 | Kddi株式会社 | Video control device, video display device, video control system, and method |
| CN106162351A (en) * | 2016-08-02 | 2016-11-23 | 合网络技术（北京）有限公司 | A kind of video recommendation method and device |
| CN106303720A (en) * | 2016-08-02 | 2017-01-04 | 合网络技术（北京）有限公司 | A kind of video recommendation method and system |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
| CN108259939A (en) * | 2017-12-25 | 2018-07-06 | 广州华多网络科技有限公司 | new video push control method, device and server |
| CN109446419A (en) * | 2018-10-17 | 2019-03-08 | 武汉斗鱼网络科技有限公司 | A kind of method and device for recommending video |
| CN110121110A (en) * | 2019-05-07 | 2019-08-13 | 北京奇艺世纪科技有限公司 | Video quality evaluation method, equipment, video processing equipment and medium |
| CN111831838A (en) * | 2019-04-17 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Multimedia information recommendation method and device, and server storage medium |
| CN112131413A (en) * | 2019-06-25 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Multimedia information processing method and device, electronic equipment and storage medium |
| CN112383825A (en) * | 2020-11-16 | 2021-02-19 | 北京百度网讯科技有限公司 | Video recommendation method and device, electronic equipment and medium |
| CN112423072A (en) * | 2020-09-02 | 2021-02-26 | 上海幻电信息科技有限公司 | Video pushing method and system in live scene |
-
2021
- 2021-07-13 CN CN202110789845.3A patent/CN113242459B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009303033A (en) * | 2008-06-16 | 2009-12-24 | Hitachi Kokusai Electric Inc | Video reproduction method, video reproduction device and video distribution system |
| JP2015037290A (en) * | 2013-08-15 | 2015-02-23 | Kddi株式会社 | Video control device, video display device, video control system, and method |
| CN106162351A (en) * | 2016-08-02 | 2016-11-23 | 合网络技术（北京）有限公司 | A kind of video recommendation method and device |
| CN106303720A (en) * | 2016-08-02 | 2017-01-04 | 合网络技术（北京）有限公司 | A kind of video recommendation method and system |
| CN108259939A (en) * | 2017-12-25 | 2018-07-06 | 广州华多网络科技有限公司 | new video push control method, device and server |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
| CN109446419A (en) * | 2018-10-17 | 2019-03-08 | 武汉斗鱼网络科技有限公司 | A kind of method and device for recommending video |
| CN111831838A (en) * | 2019-04-17 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Multimedia information recommendation method and device, and server storage medium |
| CN110121110A (en) * | 2019-05-07 | 2019-08-13 | 北京奇艺世纪科技有限公司 | Video quality evaluation method, equipment, video processing equipment and medium |
| CN112131413A (en) * | 2019-06-25 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Multimedia information processing method and device, electronic equipment and storage medium |
| CN112423072A (en) * | 2020-09-02 | 2021-02-26 | 上海幻电信息科技有限公司 | Video pushing method and system in live scene |
| CN112383825A (en) * | 2020-11-16 | 2021-02-19 | 北京百度网讯科技有限公司 | Video recommendation method and device, electronic equipment and medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114374881A (en) * | 2022-01-05 | 2022-04-19 | 北京百度网讯科技有限公司 | Method and device for distributing user flow, electronic equipment and storage medium |
| CN114374881B (en) * | 2022-01-05 | 2023-09-01 | 北京百度网讯科技有限公司 | Method and device for distributing user traffic, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113242459B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106055666B (en) | Media file delivery method and device | |
| CN108563670B (en) | Video recommendation method and device, server and computer-readable storage medium | |
| CN106294830A (en) | The recommendation method and device of multimedia resource | |
| CN107481029B (en) | Inventory prediction method and device for advertisement orders | |
| CN106296247B (en) | Network information resource online ordering method and device | |
| CN107808309A (en) | A kind of advertisement based on different social networks is integrated, issues system, method and system | |
| CN110059221B (en) | Video recommendation method, electronic device and computer readable storage medium | |
| CN111797250B (en) | Media content push control method and device, computer equipment and storage medium | |
| CN111476602A (en) | Method and server for controlling distribution of advertisement budget | |
| CN113242459B (en) | New video exposure method, device, medium and computer equipment | |
| CN113015010B (en) | Push parameter determination method, device, equipment and computer readable storage medium | |
| CN109003140A (en) | Determination method, equipment and the storage medium that the dispensing of multimedia content is provided funds | |
| CN108932627A (en) | Predictor method, device and the readable storage medium storing program for executing of the depletion rate of CPA advertisement | |
| CN110968772A (en) | Information pushing method and system | |
| JP7085486B2 (en) | User behavior data processing method and equipment | |
| CN108428161B (en) | Method and device for predicting advertising throwing amount and electronic equipment | |
| CN109840807B (en) | Traffic distribution method and equipment for advertisement orders in pre-buried scene | |
| CN116886998B (en) | Interactive processing method for simulating live broadcast environment | |
| CN113222656A (en) | Programmed advertisement putting method, system, device, equipment and storage medium | |
| CN115202890B (en) | Data element production resource space distribution method, system and equipment | |
| CN107742227B (en) | Advertisement putting method and system | |
| CN113038242B (en) | Method, device and equipment for determining display position of live broadcast card and storage medium | |
| US20170098246A1 (en) | Asset orchestration across multiple device types, media spaces, and time | |
| CN113850416A (en) | Advertisement promotion cooperation object determining method and device | |
| CN112712210A (en) | Sudden topic propagation scale prediction method, system, processing terminal and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210810 Assignee: Yidu Lehuo Network Technology Co.,Ltd. Assignor: WUHAN DOUYU YULE NETWORK TECHNOLOGY Co.,Ltd. Contract record no.: X2023980041383 Denomination of invention: A New Video Exposure Method, Device, Media, and Computer Equipment Granted publication date: 20211015 License type: Common License Record date: 20230908 |