CN107944918B - Information delivery management method and device - Google Patents
Information delivery management method and device Download PDFInfo
- Publication number
- CN107944918B CN107944918B CN201711204249.4A CN201711204249A CN107944918B CN 107944918 B CN107944918 B CN 107944918B CN 201711204249 A CN201711204249 A CN 201711204249A CN 107944918 B CN107944918 B CN 107944918B
- Authority
- CN
- China
- Prior art keywords
- time period
- putting
- amount
- grade
- residual error
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a management method and a device for information delivery, wherein the method comprises the following steps: when a target time period within the preset putting time starts, acquiring the current pushing amount and the current putting amount from the starting moment of the preset putting time to the starting moment of the target time period; determining an initial input amount residual error according to the current pushing amount, the current input amount and a target withdrawal ratio; determining a release strategy of a target time period according to the initial release residual error; and releasing the information according to the releasing strategy. The total length of the preset release time is divided into a plurality of time periods, and the release strategy is re-determined in each time period according to the release residual error, so that the release residual error is reduced, the difference between the release residual error and the target release amount is reduced, the cost and resource waste caused by too high return ratio is avoided, and the profit space is effectively improved.
Description
Technical Field
The present application relates to the field of internet information technologies, and in particular, to a method and an apparatus for managing information delivery.
Background
With the development of internet technology, online advertising has become a major revenue source for many internet platforms. In recent years, high-quality media resources in which PDBs (Private Direct Buy) are used as trade, or high-quality advertisement display resources of conventional media, have begun to enter the program purchase market. However, in the PDB delivery process, for the purpose of volume conservation, the back-off ratio needs to be strictly controlled, and the delivery is performed at a relatively optimal flow rate while the back-off ratio is strictly controlled, so as to maximize the delivery effect.
In the prior art, the putting amount is guaranteed preferentially, quality guarantee is carried out when the putting amount is larger than or equal to the target putting amount, and the optimal flow is selected for putting. Resulting in a lower dispensing effect. Therefore, how to improve the dispensing effect on the basis of the amount of the product is an urgent technical problem to be solved.
Disclosure of Invention
The application provides a management method and device for information delivery, which aim to overcome the defects that only the delivery amount can be guaranteed, the delivery effect cannot be guaranteed and the like in the prior art.
A first aspect of the present application provides a method for managing information delivery, including:
when a target time period within preset putting time begins, acquiring a current pushing amount and a current putting amount from the starting time of the preset putting time to the starting time of the target time period, wherein the length of the preset putting time is divided into N time periods, N is an integer greater than 1, and the target time period is one time period of the N time periods;
determining an initial input amount residual error according to the current pushing amount, the current input amount and a target withdrawal amount ratio;
determining a release strategy of the target time period according to the initial release residual error;
and releasing information according to the releasing strategy.
Another aspect of the present application provides an information delivery management apparatus, including:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring a current pushing amount and a current putting amount from a preset putting time starting moment to a target time period starting moment when the target time period in a preset putting time starts, the preset putting time length is divided into N time periods, N is an integer larger than 1, and the target time period is one of the N time periods;
the first determining module is used for determining an initial input amount residual error according to the current pushing amount, the current input amount and a target withdrawal ratio;
the second determination module is used for determining the release strategy of the target time period according to the initial release residual error;
and the processing module is used for releasing information according to the releasing strategy.
According to the information release management method and device, the total length of the preset release time is divided into a plurality of time periods, and the release strategy is determined again in each time period according to the release residual so as to reduce the release residual, reduce the difference between the release residual and the target release, avoid cost and resource waste caused by too high return ratio and effectively improve the profit space.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a management method for information delivery according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a management apparatus for information delivery according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
The embodiment provides a management method for information delivery, which is used for managing a delivery process of a PDB. The execution subject of the embodiment is a management device for information delivery, and the device may be disposed in a terminal device, such as a server, a PC, a tablet computer, and the like.
As shown in fig. 1, a schematic flow chart of a management method for information delivery provided in this embodiment is shown, where the method includes:
The preset release time length is divided into N time periods, wherein N is an integer greater than 1, and the target time period is one of the N time periods.
And step 102, determining an initial input amount residual error according to the current pushing amount, the current input amount and the target withdrawal amount ratio.
And 103, determining a release strategy of the target time period according to the initial release residual error.
And 104, releasing the information according to the releasing strategy.
Specifically, since the back volume ratio is based on day as a time division unit, the preset delivery time may be one day, and one day is divided into N time periods, where N is an integer greater than 1, for example, one hour is used as one time period, and one day is divided into 24 time periods, during the release process of the day, every time a period of time comes, the release strategy needs to be readjusted according to the release situation of the previous period of time, for example when 8 o' clock is reached, the target time period is 8 to 9 points, the current push amount and the current put amount from 0 to 8 points can be obtained, determining an initial input amount residual error of a target time period according to the current push amount, the current input amount and a target withdrawal ratio, determining an input strategy of the target time period according to the initial input amount residual error, i.e. determining whether the target time period should be accelerated or decelerated relative to the previous time period. And after the determination, carrying out information delivery according to the determined delivery strategy, namely accelerating delivery or decelerating delivery, or keeping the speed delivery in the previous time period.
In the PDB delivery mode, in order to achieve the purposes of ensuring the quantity and giving a certain effect optimization space to the advertisement delivery party, the flow owner and the advertisement delivery party agree in advance how much proportion of flow can be selected to be delivered in the delivery process. And the input amount residual error is the difference between the current target input amount and the current actual input amount if the target withdrawal ratio is met. The residual error of the input amount is larger than zero, which proves that the current input amount does not reach the target input amount, namely the current retreat amount ratio is larger than the target retreat amount ratio, so that the retreat flow is too much, the waste of cost is caused, and the profit space is reduced. The residual error of the input amount is less than zero, which proves that the current input amount exceeds the target input amount, namely the current back-off amount ratio is less than the target back-off amount ratio, and the agreement is not met. Therefore, the release strategy needs to be adjusted when the release residual is too large or too small. The push amount refers to the amount of traffic pushed by the traffic owner, and the current push amount refers to the total push amount of the traffic owner from the preset release time to the target time period starting time. The placement amount is the amount of traffic that the information provider (e.g., advertisement provider) has made information placement on the traffic pushed by the traffic owner. For example, 200 traffics are pushed by a traffic owner, 150 traffics are pushed by an advertisement publisher, that is, 50 traffics return, and the current return rate is 25%.
According to the information release management method provided by the embodiment, the total preset release time is divided into a plurality of time periods, and the release strategy is determined again in each time period according to the release residual error, so that the release residual error is reduced, the difference between the release residual error and the target release amount is reduced, the cost and resource waste caused by too high back ratio is avoided, and the profit space is effectively improved.
Example two
The present embodiment further supplements and explains the management method for information delivery provided in the first embodiment.
As a practical manner, on the basis of the first embodiment, optionally, the step 102 specifically includes: according to the current pushing amount, the current input amount and the target withdrawal amount ratio, calculating to obtain an initial input amount residual error by adopting the following formula:
the initial input amount residual is (1-target recession amount ratio) x current pushed amount-current input amount.
As another implementable manner, on the basis of the first embodiment, optionally, the step 103 specifically includes:
if the initial putting amount residual error is equal to 0, determining that the putting strategy of the target time period is as follows: keeping the throwing speed of the previous time period of the target time period;
if the initial putting amount residual error is larger than 0, determining that the putting strategy of the target time period is as follows: accelerating the throwing speed of the previous time period relative to the target time period;
if the initial putting amount residual error is less than 0, determining that the putting strategy of the target time period is as follows: and decelerating the throwing speed of the previous time period relative to the target time period.
Specifically, if the initial input amount residual error of the target time period is greater than zero, it is proved that the current input amount at the current moment does not reach the target input amount, that is, the current withdrawal ratio is greater than the target withdrawal ratio, so that the withdrawal flow is too much, the waste of cost is caused, and the profit space is reduced. Therefore, the throwing needs to be accelerated in the target time period, and the difference between the actual throwing amount and the target throwing amount is reduced. The target input volume is the input volume which is determined according to the current push volume and the appointed target back volume ratio and should be completed currently.
If the initial input amount residual error of the target time period is less than zero, the current input amount is proved to exceed the target input amount, namely the current receding amount ratio is less than the target receding amount ratio, therefore, the input needs to be decelerated in the target time period, and the difference between the actual input amount and the target input amount is reduced.
If the initial putting amount residual error of the target time period is equal to 0, the current putting amount is proved to just meet the target putting amount, and the current putting speed is kept in the target time period.
In this way, the adjustment is continuously performed from the first time period to the last time period, and finally the retreating amount ratio in the preset throwing time (such as the one day) can be kept consistent with the target retreating amount ratio, so that the situation that the retreating amount ratio is too large or too small is avoided.
Optionally, if the initial put amount residual is greater than 0, determining that the putting strategy of the target time period is: accelerating the throwing speed of the previous time period relative to the target time period specifically comprises the following steps:
if the initial input quantity residual error is larger than 0, obtaining the quality grades of M flows divided according to the evaluation standard KPI of the input flow, wherein M is a positive integer;
acquiring the throwing probability of the current flow;
acquiring a first putting probability P (i) corresponding to each quality grade in a previous time period of a target time period, wherein i is 1,2, … and M;
acquiring release information of S time periods before a target time period, wherein S is a positive integer, and the release amount of the S time periods is not empty;
according to the throwing information, calculating the sum U (i) of the throwing amount in the time periods with the S throwing amounts not being empty according to the throwing information, wherein i is 1,2, …, M;
and accelerating according to the grade from good to bad according to the following formula:
P(i)0＝min(1.0,P(i)*(U(i)+R(i))/(U(i)+0.001))；
R(i+1)＝R(i)-U(i)*(P(i)0-P(i))/P(i)；
wherein, P (i)0 is the starting and delivering probability corresponding to the good and bad grade i, P (1)0 is the starting and delivering probability corresponding to the optimal good and bad grade, and P (1)0 is a preset value; min (a, b) represents taking the minimum value of a and b; p (i) is a first putting probability of a time period before a target time period corresponding to the quality grade i; u (i) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade i are not empty; r (i) is a putting quantity residual error corresponding to the quality grade i, R (1) is a putting quantity residual error corresponding to the optimal quality grade, and R (1) is an initial putting quantity residual error;
and determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
Illustratively, one day is divided into 24 time periods, the current time is 8 points, that is, the target time period is 8 points to 9 points, the current pushed amount from 0 point to 8 points is 200, the current put amount is 100, and the target backout ratio is 30%, then the flow is divided into 3 good and bad grades according to the check criterion KPI of the put flow, for example, if the target audience population to be put in the advertisement is mainly female, the 3 good and bad grades from good to bad of the flow are 1 grade-female, 2 grade-unknown, 3 grade-male according to the above calculation formula of the initial put amount residual error, the initial put amount residual error of the target time period is R (1) is 40 and is greater than 0. When a traffic owner pushes a traffic (referred to as a current traffic) in a target time period, an injecting probability of the current traffic may be obtained, for example, the injecting probability of the current traffic is 0.6, and a first injecting probability (which may be specifically obtained by statistics according to injecting conditions in the previous time period) corresponding to the 3 good and bad classes may be obtained in the previous time period of the target time period, for example, a first injecting probability P (1) corresponding to a female is 0.6, a first injecting probability P (2) corresponding to an unknown is 0.3, and a first injecting probability P (3) corresponding to a male is 0.2. The release information of the time slots with the release amounts not being empty S times before the target time slot is also obtained, for example, 8 time slots are total before 8 o' clock, where the release amounts of 5 time slots are not empty, then 5 release information may be obtained, or of course, 4 or 3 release information may be obtained, which may be specifically set according to an actual situation, and is not limited herein. Taking the example of obtaining the delivery information of the time slot in which 5 delivery amounts are not empty, the total delivery amounts corresponding to 3 quality levels in the 5 time slots can be calculated for each quality level according to the delivery information, for example, U (1) for female, U (2) for unknown, and U (3) for male, for example, U (1) is 55, U (2) is 30, and U (3) is 15, and the acceleration is performed according to the quality levels from good to bad, that is:
P(1)0＝min(1.0,P(1)*(U(1)+R(1))/(U(1)+0.001))＝1.0；
R(2)＝R(1)-U(1)*(P(1)0-P(1))/P(1)＝3.33；
P(2)0＝min(1.0,P(2)*(U(2)+R(2))/(U(2)+0.001))＝0.33；
R(3)＝R(2)-U(2)*(P(2)0-P(2))/P(2)＝0.33；
P(3)0＝min(1.0,P(3)*(U(3)+R(3))/(U(3)+0.001))＝0.20；
and determining to deliver the current traffic, namely delivering the advertisement to the current traffic according to the delivery probability of the current traffic being 0.6 and the delivery starting probability of the quality level to which the current traffic belongs, for example, if the quality level to which the current traffic belongs is 1 st level-female, the delivery starting probability of the level is 1, and the delivery probability of the current traffic is 0.6 within the range of 1. If the delivery probability of the current flow is 0.6, but the delivery probability belongs to the 3 rd level-male, and the delivery starting probability corresponding to the male is 0.33, the delivery probability of the current flow is not 0.6 within the range of 0.33, and the current flow is determined not to be delivered, namely, the current flow is returned. Therefore, the putting probability of the optimal grade is improved, and the optimal grade is improved most, so that the high-quality putting proportion in the increased putting quantity is increased in the target time period relative to the previous time period, and the putting effect is effectively improved under the condition of ensuring the quantity withdrawal ratio.
It should be noted that the assessment criterion KPI of the flow is the prior art, and is not described herein again.
Optionally, if the initial put amount residual is less than 0, determining that the put strategy of the target time period is: the deceleration of the throwing speed in the previous time period relative to the target time period specifically comprises the following steps:
if the initial input quantity residual error is less than 0, obtaining the quality grades of M flows divided according to the evaluation standard KPJ of the input flow, wherein M is a positive integer;
acquiring the throwing probability of the current flow;
acquiring a first putting probability P (j) corresponding to each quality grade in a previous time period of a target time period, wherein j is 1,2, … and M;
acquiring release information of S time periods before a target time period, wherein S is a positive integer, and the release amount of the S time periods is not empty;
according to the throwing information, calculating the sum U (j) of the throwing amount in the time periods with the S throwing amounts not being empty according to the throwing information, wherein j is 1,2, …, M;
and decelerating according to the grade from poor to good according to the following formula:
P(j)0＝max(0.0,P(j)*(U(j)+R(j))/(U(j)+0.001))；
R(j+1)＝R(j)-U(j)*(P(j)0-P(j))/P(j)；
wherein, P (j)0 is the starting throwing probability corresponding to the good and bad grade j, P (1)0 is the starting throwing probability corresponding to the worst good and bad grade, and P (1)0 is a preset value; max (a, b) represents the maximum value of a and b; p (j) is a first putting probability of a previous time period of a target time period corresponding to the quality grade j; u (j) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade j are not empty; r (j) is a putting quantity residual error corresponding to the quality grade j, R (1) is a putting quantity residual error corresponding to the worst quality grade, and R (1) is an initial putting quantity residual error;
and determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
The specific deceleration process is similar to the acceleration process, and is not described herein again. Different from the acceleration process, the deceleration process starts from the worst level, so that the reduction of the worst level of the reduction part is the most, and the reduction of the best level is the least, and overall, the delivery of high-quality flow in the delivery volume is also improved, and the delivery effect is improved.
The management device for information delivery provided by this embodiment divides the total length of the preset delivery time into a plurality of time periods, and determines the delivery speed again in each time period according to the delivery amount residual error, so as to reduce the delivery amount residual error, reduce the difference between the target delivery amount and the delivery amount, and avoid the cost and resource waste caused by too high back ratio. And through a residual subtraction method and a flow quality grade layering method, when the initial input quantity residual of a target time period is larger than zero, acceleration is carried out according to the flow grade from good to bad, namely, the input of high-quality flow is increased, and when the initial input quantity residual is smaller than zero, deceleration input is carried out according to the poor to good, namely, the input of poor-quality flow is reduced, so that the input effect is effectively improved under the condition of ensuring the quantity withdrawal ratio.
EXAMPLE III
The present embodiment provides an information delivery management apparatus, configured to execute the information delivery management method provided in the first embodiment.
As shown in fig. 2, it is a schematic structural diagram of the information delivery management device provided in this embodiment. The management apparatus 30 for information delivery includes an obtaining module 31, a first determining module 32, a second determining module 33, and a processing module 34.
The obtaining module 31 is configured to obtain a current pushed amount and a current put-in amount from a preset put-in time starting time to a target time period starting time when the target time period within the preset put-in time starts, where the preset put-in time length is divided into N time periods, N is an integer greater than 1, and the target time period is one time period of the N time periods. The first determining module 32 is configured to determine an initial input amount residual error according to the current pushing amount, the current input amount, and the target backoff ratio. The second determining module 33 is configured to determine a release strategy of the target time period according to the initial release amount residual error; the processing module 34 is configured to perform information delivery according to a delivery policy.
The specific manner in which the respective modules perform operations has been described in detail in relation to the apparatus in this embodiment, and will not be elaborated upon here.
According to the information release management method provided by the embodiment, the total preset release time is divided into a plurality of time periods, and the release strategy is determined again in each time period according to the release residual error, so that the release residual error is reduced, the difference between the release residual error and the target release amount is reduced, the cost and resource waste caused by too high back ratio is avoided, and the profit space is effectively improved.
Example four
This embodiment further supplements the description of the information delivery management device provided in the third embodiment.
As an implementable manner, on the basis of the third embodiment, optionally, the first determining module 32 is specifically configured to:
according to the current pushing amount, the current input amount and the target withdrawal amount ratio, calculating to obtain an initial input amount residual error by adopting the following formula:
the initial input amount residual is (1-target recession amount ratio) x current pushed amount-current input amount.
As another implementable manner, on the basis of the third embodiment, optionally, the second determining module 33 is specifically configured to:
if the initial putting amount residual error is equal to 0, determining that the putting strategy of the target time period is as follows: keeping the throwing speed of the previous time period of the target time period;
if the initial putting amount residual error is larger than 0, determining that the putting strategy of the target time period is as follows: accelerating the throwing speed of the previous time period relative to the target time period;
if the initial putting amount residual error is less than 0, determining that the putting strategy of the target time period is as follows: and decelerating the throwing speed of the previous time period relative to the target time period.
As still another implementable manner, on the basis of the third embodiment, optionally, the second determining module 33 may include a first obtaining sub-module, a first calculating sub-module, a first processing sub-module, and a first determining sub-module.
The first obtaining submodule is used for obtaining the quality grades of M flows divided according to the assessment standard KPI of the input flow if the initial input quantity residual error is larger than 0, wherein M is a positive integer;
the first obtaining submodule is also used for obtaining the putting probability of the current flow;
the first obtaining sub-module is further configured to obtain a first putting probability p (i) corresponding to each quality level in a previous time period of the target time period, where i is 1,2, …, M;
the first obtaining submodule is also used for obtaining the throwing information of time periods with S throwing quantities before the target time period not being empty, and S is a positive integer;
the first calculation submodule is used for calculating the sum U (i) of the input quantities in the S time periods when the input quantities are not empty according to the input information and each quality grade, wherein i is 1,2, … and M;
the first processing submodule is used for accelerating according to the quality grade from good to bad according to the following formula:
P(i)0＝min(1.0,P(i)*(U(i)+R(i))/(U(i)+0.001))；
R(i+1)＝R(i)-U(i)*(P(i)0-P(i))/P(i)；
wherein, P (i)0 is the starting and delivering probability corresponding to the good and bad grade i, P (1)0 is the starting and delivering probability corresponding to the optimal good and bad grade, and P (1)0 is a preset value; min (a, b) represents taking the minimum value of a and b; p (i) is a first putting probability of a time period before a target time period corresponding to the quality grade i; u (i) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade i are not empty; r (i) is a putting quantity residual error corresponding to the quality grade i, R (1) is a putting quantity residual error corresponding to the optimal quality grade, and R (1) is an initial putting quantity residual error;
and the first determining submodule is used for determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
As a further implementable manner, on the basis of the third embodiment, optionally, the second determining module 33 may include a second obtaining sub-module, a second calculating sub-module, a second processing sub-module and a second determining sub-module.
The second obtaining submodule is used for obtaining the quality grades of M flows divided according to the assessment standard KPI of the input flow if the initial input quantity residual error is less than 0, wherein M is a positive integer;
the second obtaining submodule is also used for obtaining the putting probability of the current flow;
the second obtaining submodule is further configured to obtain a first putting probability p (j), where j is 1,2, …, M, corresponding to each quality level in a previous time period of the target time period;
the second obtaining submodule is also used for obtaining the throwing information of time periods with S throwing quantities before the target time period not being empty, and S is a positive integer;
the second calculation submodule is used for calculating the sum of the putting quantities U (j) in the time periods with S putting quantities not being empty according to the putting information and each quality grade, wherein j is 1,2, … and M;
the second processing submodule is used for carrying out deceleration according to the following formula from the inferior to the superior according to the superior and inferior grades:
P(j)0＝max(0.0,P(j)*(U(j)+R(j))/(U(j)+0.001))；
R(j+1)＝R(j)-U(j)*(P(j)0-P(j))/P(j)；
wherein, P (j)0 is the starting throwing probability corresponding to the good and bad grade j, P (1)0 is the starting throwing probability corresponding to the worst good and bad grade, and P (1)0 is a preset value; max (a, b) represents the maximum value of a and b; p (j) is a first putting probability of a previous time period of a target time period corresponding to the quality grade j; u (j) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade j are not empty; r (j) is a putting quantity residual error corresponding to the quality grade j, R (1) is a putting quantity residual error corresponding to the worst quality grade, and R (1) is an initial putting quantity residual error;
and the second determining submodule is used for determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs. The specific manner in which the respective modules perform operations has been described in detail in relation to the apparatus in this embodiment, and will not be elaborated upon here.
It should be noted that the first obtaining submodule, the first calculating submodule, the first processing submodule, and the first determining submodule may be respectively the same submodules as the second obtaining submodule, the second calculating submodule, the second processing submodule, and the second determining submodule, that is, the second determining module may include the obtaining submodule, the calculating submodule, the processing submodule, and the determining submodule, and may process both the acceleration process and the deceleration process, which is not limited herein.
The specific manner in which the respective modules perform operations has been described in detail in relation to the apparatus in this embodiment, and will not be elaborated upon here.
The management device for information delivery provided by this embodiment divides the total length of the preset delivery time into a plurality of time periods, and determines the delivery speed again in each time period according to the delivery amount residual error, so as to reduce the delivery amount residual error, reduce the difference between the target delivery amount and the delivery amount, and avoid the cost and resource waste caused by too high back ratio. And through a residual subtraction method and a flow quality grade layering method, when the initial input quantity residual of a target time period is larger than zero, acceleration is carried out according to the flow grade from good to bad, namely, the input of high-quality flow is increased, and when the initial input quantity residual is smaller than zero, deceleration input is carried out according to the poor to good, namely, the input of poor-quality flow is reduced, so that the input effect is effectively improved under the condition of ensuring the quantity withdrawal ratio.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (6)
1. A method for managing information delivery, comprising:
when a target time period within preset putting time begins, acquiring a current pushing amount and a current putting amount from the starting time of the preset putting time to the starting time of the target time period, wherein the length of the preset putting time is divided into N time periods, N is an integer greater than 1, and the target time period is one time period of the N time periods;
determining an initial input amount residual error according to the current pushing amount, the current input amount and a target withdrawal amount ratio;
determining a release strategy of the target time period according to the initial release residual error;
information is released according to the releasing strategy;
the determining the release strategy of the target time period according to the initial release residual error comprises the following steps:
if the initial putting amount residual error is equal to 0, determining that the putting strategy of the target time period is as follows: maintaining the throwing speed of the time period before the target time period;
if the initial putting amount residual error is larger than 0, determining that the putting strategy of the target time period is as follows: accelerating the throwing speed of the time period before the target time period;
if the initial putting amount residual error is less than 0, determining that the putting strategy of the target time period is as follows: decelerating the throwing speed of the previous time period relative to the target time period;
if the initial putting quantity residual error is larger than 0, determining that the putting strategy of the target time period is as follows: accelerating the throwing speed of the time period before the target time period, wherein the accelerating comprises the following steps:
if the initial input quantity residual error is larger than 0, obtaining the quality grades of M flows divided according to the evaluation standard KPI of input flow, wherein M is a positive integer;
acquiring the throwing probability of the current flow;
acquiring a first putting probability P (i) corresponding to each quality grade in a previous time period of the target time period, wherein i is 1,2, … and M; the quality grade is gradually reduced from the optimal quality grade to the worst quality grade along with the increase of i;
acquiring release information of S time periods before the target time period, wherein S is a positive integer, and the release amount of the S time periods is not empty;
according to the putting information, calculating the sum U (i) of putting amounts in the time periods when the S putting amounts are not empty for each quality grade, wherein i is 1,2, …, M;
and accelerating according to the grade from good to bad according to the following formula:
P(i)0＝min(1.0,P(i)*(U(i)+R(i))/(U(i)+0.001))；
R(i+1)＝R(i)-U(i)*(P(i)0-P(i))/P(i)；
wherein, P (i)0 is the starting and releasing probability corresponding to the good and bad grade i, P (1)0 is the starting and releasing probability corresponding to the optimal good and bad grade, and the starting and releasing probability corresponding to the optimal good and bad grade is a preset value; min (a, b) represents taking the minimum value of a and b; p (i) is a first putting probability of a time period before a target time period corresponding to the quality grade i; u (i) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade i are not empty; r (i) is a putting quantity residual error corresponding to the good and bad grade i, R (1) is a putting quantity residual error corresponding to the optimal good and bad grade, and the putting quantity residual error corresponding to the optimal good and bad grade is the initial putting quantity residual error;
and determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
2. The method of claim 1, wherein determining an initial pay amount residual according to the current pushed amount and current pay amount, and a target backlog ratio comprises:
and calculating to obtain an initial input amount residual error by adopting the following formula according to the current pushing amount, the current input amount and the target withdrawal amount ratio:
the initial input amount residual is (1-target recession amount ratio) x current pushed amount-current input amount.
3. The method of claim 1, wherein if the initial placement amount residual is less than 0, determining the placement strategy for the target time period as: decelerating the throwing speed of the previous time period relative to the target time period, wherein the decelerating comprises the following steps:
if the initial input quantity residual error is less than 0, obtaining the quality grades of M flows divided according to the evaluation standard KPI of input flow, wherein M is a positive integer;
acquiring the throwing probability of the current flow;
acquiring a first putting probability P (j) corresponding to each quality grade in a previous time period of the target time period, wherein j is 1,2, … and M; the quality grade is gradually increased from the worst quality grade to the optimal quality grade along with the increase of j;
acquiring release information of S time periods before the target time period, wherein S is a positive integer, and the release amount of the S time periods is not empty;
according to the putting information, calculating the sum of putting amounts U (j) of the S putting amounts in the time periods not being empty according to the putting information, wherein j is 1,2, …, M;
and decelerating according to the grade from poor to good according to the following formula:
P(j)0＝max(0.0,P(j)*(U(j)+R(j))/(U(j)+0.001))；
R(j+1)＝R(j)-U(j)*(P(j)0-P(j))/P(j)；
wherein, P (j)0 is the starting throwing probability corresponding to the good and bad grade j, P (1)0 is the starting throwing probability corresponding to the worst good and bad grade, and the starting throwing probability corresponding to the worst good and bad grade is a preset value; max (a, b) represents the maximum value of a and b; p (j) is a first putting probability of a previous time period of a target time period corresponding to the quality grade j; u (j) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade j are not empty; r (j) is a putting quantity residual error corresponding to the good grade j, R (1) is a putting quantity residual error corresponding to the worst good grade, and the putting quantity residual error corresponding to the worst good grade is the initial putting quantity residual error;
and determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
4. An information delivery management apparatus, comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring a current pushing amount and a current putting amount from a preset putting time starting moment to a target time period starting moment when the target time period in a preset putting time starts, the preset putting time length is divided into N time periods, N is an integer larger than 1, and the target time period is one of the N time periods;
the first determining module is used for determining an initial input amount residual error according to the current pushing amount, the current input amount and a target withdrawal ratio;
the second determination module is used for determining the release strategy of the target time period according to the initial release residual error;
the processing module is used for releasing information according to the releasing strategy;
the second determining module is specifically configured to:
if the initial putting amount residual error is equal to 0, determining that the putting strategy of the target time period is as follows: maintaining the throwing speed of the time period before the target time period;
if the initial putting amount residual error is larger than 0, determining that the putting strategy of the target time period is as follows: accelerating the throwing speed of the time period before the target time period;
if the initial putting amount residual error is less than 0, determining that the putting strategy of the target time period is as follows: decelerating the throwing speed of the previous time period relative to the target time period;
the second determining module includes:
the first obtaining submodule is used for obtaining the quality grades of M flows divided according to the assessment standard KPI of the input flows if the initial input quantity residual error is larger than 0, wherein M is a positive integer;
the first obtaining submodule is also used for obtaining the putting probability of the current flow;
the first obtaining sub-module is further configured to obtain a first putting probability p (i), where i is 1,2, …, M, corresponding to each quality level in a time period before the target time period; the quality grade is gradually reduced from the optimal quality grade to the worst quality grade along with the increase of i;
the first obtaining submodule is further used for obtaining the throwing information of time periods with non-empty S throwing amounts before the target time period, and S is a positive integer;
a first calculating submodule, configured to calculate, according to the placement information, for each quality level, a total sum u (i) of the placement amounts in the time periods in which the S placement amounts are not empty, where i is 1,2, …, and M;
the first processing submodule is used for accelerating according to the grade from good to bad according to the following formula:
P(i)0＝min(1.0,P(i)*(U(i)+R(i))/(U(i)+0.001))；
R(i+1)＝R(i)-U(i)*(P(i)0-P(i))/P(i)；
wherein, P (i)0 is the starting and releasing probability corresponding to the good and bad grade i, P (1)0 is the starting and releasing probability corresponding to the optimal good and bad grade, and the starting and releasing probability corresponding to the optimal good and bad grade is a preset value; min (a, b) represents taking the minimum value of a and b; p (i) is a first putting probability of a time period before a target time period corresponding to the quality grade i; u (i) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade i are not empty; r (i) is a putting quantity residual error corresponding to the good and bad grade i, R (1) is a putting quantity residual error corresponding to the optimal good and bad grade, and the putting quantity residual error corresponding to the worst good and bad grade is the initial putting quantity residual error;
and the first determining submodule is used for determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
5. The apparatus of claim 4, wherein the first determining module is specifically configured to:
and calculating to obtain an initial input amount residual error by adopting the following formula according to the current pushing amount, the current input amount and the target withdrawal amount ratio:
the initial input amount residual is (1-target recession amount ratio) x current pushed amount-current input amount.
6. The apparatus of claim 4, wherein the second determining module comprises:
the second obtaining submodule is used for obtaining the quality grades of M flows divided according to the evaluation standard KPI of the input flows if the initial input quantity residual error is less than 0, wherein M is a positive integer;
the second obtaining submodule is also used for obtaining the putting probability of the current flow;
the second obtaining sub-module is further configured to obtain a first delivery probability p (j), where j is 1,2, …, M, corresponding to each quality level in a time period before the target time period; the quality grade is gradually increased from the worst quality grade to the optimal quality grade along with the increase of j;
the second obtaining submodule is further configured to obtain the release information of time periods in which S release amounts before the target time period are not empty, where S is a positive integer;
a second calculating submodule, configured to calculate, according to the placement information, for each quality level, a total sum u (j) of the placement amounts in the time periods in which the S placement amounts are not empty, where j is 1,2, …, M;
and the second processing submodule is used for carrying out deceleration according to the following formula from the inferior grade to the superior grade:
P(j)0＝max(0.0,P(j)*(U(j)+R(j))/(U(j)+0.001))；
R(j+1)＝R(j)-U(j)*(P(j)0-P(j))/P(j)；
wherein, P (j)0 is the starting throwing probability corresponding to the good and bad grade j, P (1)0 is the starting throwing probability corresponding to the worst good and bad grade, and the starting throwing probability corresponding to the worst good and bad grade is a preset value; max (a, b) represents the maximum value of a and b; p (j) is a first putting probability of a previous time period of a target time period corresponding to the quality grade j; u (j) is the sum of the putting amount in the time period that S putting amounts before the target time period corresponding to the quality grade j are not empty; r (j) is a putting quantity residual error corresponding to the good grade j, R (1) is a putting quantity residual error corresponding to the worst good grade, and the putting quantity residual error corresponding to the worst good grade is the initial putting quantity residual error;
and the second determining submodule is used for determining whether to release the current flow according to the release probability of the current flow and the release starting probability of the quality grade to which the current flow belongs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711204249.4A CN107944918B (en) | 2017-11-27 | 2017-11-27 | Information delivery management method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711204249.4A CN107944918B (en) | 2017-11-27 | 2017-11-27 | Information delivery management method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107944918A CN107944918A (en) | 2018-04-20 |
| CN107944918B true CN107944918B (en) | 2021-12-14 |
Family
ID=61949931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711204249.4A Active CN107944918B (en) | 2017-11-27 | 2017-11-27 | Information delivery management method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944918B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598598B (en) * | 2019-02-21 | 2024-03-22 | 北京达佳互联信息技术有限公司 | Information delivery method, information delivery device, and computer-readable storage medium |
| CN110443642A (en) * | 2019-07-23 | 2019-11-12 | 恩亿科(北京)数据科技有限公司 | A kind of multi-brand flux exchange, device and DSP |
| CN110544136A (en) * | 2019-09-10 | 2019-12-06 | 恩亿科(北京)数据科技有限公司 | Method, device, equipment and storage medium for calculating synchronous putting probability |
| CN111160991B (en) * | 2019-12-31 | 2023-08-29 | 恩亿科(北京)数据科技有限公司 | PDB advertisement flow optimization method and device, storage medium and electronic equipment |
| CN111242699B (en) * | 2020-02-07 | 2023-04-07 | 恩亿科(北京)数据科技有限公司 | Flow back management method and device, electronic equipment and readable storage medium |
| CN111340532B (en) * | 2020-02-19 | 2021-12-14 | 北京三快在线科技有限公司 | Data delivery method, device, server and computer readable storage medium |
| CN111967921A (en) * | 2020-09-24 | 2020-11-20 | 北京字节跳动网络技术有限公司 | Method, device, equipment and storage medium for determining information delivery cost |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090003413A (en) * | 2007-06-08 | 2009-01-12 | 엔에이치엔(주) | Method for advertising through correcting forecast traffic using trend reflection and system for executing the method |
| CN102122380A (en) * | 2011-02-25 | 2011-07-13 | 北京开心人信息技术有限公司 | Method and system for realizing network advertisement release |
| CN105741133A (en) * | 2016-01-26 | 2016-07-06 | 电子科技大学 | Stepping management method for online advertisement delivery |
| CN106055666A (en) * | 2016-06-02 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Method and device for delivering media files |
| CN106779813A (en) * | 2016-11-28 | 2017-05-31 | 加和（北京）信息科技有限公司 | A kind of advertisement placement method, device and system |
-
2017
- 2017-11-27 CN CN201711204249.4A patent/CN107944918B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090003413A (en) * | 2007-06-08 | 2009-01-12 | 엔에이치엔(주) | Method for advertising through correcting forecast traffic using trend reflection and system for executing the method |
| CN102122380A (en) * | 2011-02-25 | 2011-07-13 | 北京开心人信息技术有限公司 | Method and system for realizing network advertisement release |
| CN105741133A (en) * | 2016-01-26 | 2016-07-06 | 电子科技大学 | Stepping management method for online advertisement delivery |
| CN106055666A (en) * | 2016-06-02 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Method and device for delivering media files |
| CN106779813A (en) * | 2016-11-28 | 2017-05-31 | 加和（北京）信息科技有限公司 | A kind of advertisement placement method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107944918A (en) | 2018-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944918B (en) | Information delivery management method and device | |
| JP6541877B2 (en) | Method and apparatus for delivering media file | |
| CN106055666B (en) | Media file delivery method and device | |
| Rosenfeld | Analysis of bitcoin pooled mining reward systems | |
| CN108876472B (en) | Information delivery method and device | |
| CN107464034A (en) | Order processing method and apparatus | |
| CN109426896A (en) | A kind of method and device of determining region transport power state, electronic equipment | |
| CN107146158B (en) | Electronic data processing method and device | |
| CN111210247B (en) | Advertisement delivery processing method, device and system, computing device and readable medium | |
| US20240185179A1 (en) | Replenishment quantity determination method and apparatus, device, storage medium, and program product | |
| KR20160013278A (en) | Advertisement server and method for determining exposure quantity of advertisement | |
| US20110258100A1 (en) | Systems, methods, and media for placing orders to trade securities | |
| CN110533479B (en) | Identification distribution method and device and electronic equipment | |
| US20170243256A1 (en) | Method and device for controlling displaying of media object and media object display system | |
| CN111242699B (en) | Flow back management method and device, electronic equipment and readable storage medium | |
| CN111160991A (en) | PDB advertisement traffic optimization method, device, storage medium and electronic equipment | |
| CN106971326B (en) | User expectation management system and method for order | |
| CN107590620A (en) | User credit degree assessment system and method | |
| US20160371753A1 (en) | Method, apparatus, and system for controlling publication of network media information | |
| CN111415023B (en) | Multimedia information delivery method and device and electronic equipment | |
| CN114066532A (en) | Server and advertisement putting quantity control method | |
| CN110688584A (en) | User matching method, electronic equipment and computer program product | |
| CN112712408A (en) | Block chain technology-based idle article sharing method, equipment and medium | |
| Forró et al. | Valuation of Zynga | |
| CN110689372A (en) | Control method and device for advertisement putting experiment and advertisement putting experiment platform |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201230 Address after: 136a, 1st floor, D-1 building, Dongsheng Science Park, 66 xixiaokou Road, Haidian District, Beijing 100080 (Dongsheng area) Applicant after: Enyike (Beijing) Data Technology Co.,Ltd. Address before: Room 9014, 9 / F, building 3, yard 30, Shixing street, Shijingshan District, Beijing 100041 Applicant before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |