CN111967921A - Method, device, equipment and storage medium for determining information delivery cost - Google Patents
Method, device, equipment and storage medium for determining information delivery cost Download PDFInfo
- Publication number
- CN111967921A CN111967921A CN202011019502.0A CN202011019502A CN111967921A CN 111967921 A CN111967921 A CN 111967921A CN 202011019502 A CN202011019502 A CN 202011019502A CN 111967921 A CN111967921 A CN 111967921A
- Authority
- CN
- China
- Prior art keywords
- cost
- target
- activation rate
- activation
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004913 activation Effects 0.000 claims abstract description 157
- 230000001186 cumulative effect Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000001994 activation Methods 0.000 description 127
- 230000000694 effects Effects 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
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
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/0249—Advertisements based upon budgets or funds
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a method, a device, equipment and a storage medium for determining information delivery cost. The method comprises the following steps: acquiring total input cost and total display quantity of target information in target time and an activation rate estimated value of the target information; determining a confidence interval of the activation rate estimated value, and acquiring a target value of the activation rate estimated value corresponding to the confidence interval; and determining the putting cost of the target information according to the total putting cost and the total display amount and the target value. In this way, the placement cost of the recommendation information can be accurately determined when the data volume is small, and the policy can be accurately adjusted for the recommendation information.
Description
Technical Field
Embodiments of the present disclosure relate generally to the field of internet technology, and more particularly, to a method, an apparatus, a device, and a storage medium for determining information delivery cost.
Background
In the recommendation information delivery, in order to determine an adjustment strategy for a recommendation information bid, budget, and the like in time, effect data of one recommendation information in a short time period is generally used as a judgment basis. For example, the cost of placement, which is related to the total cost consumed by the recommendation information and the amount of application activation due to the recommendation information, can be used to measure the goodness and badness of a piece of recommendation information.
However, there is a certain time difference, i.e., activation delay, from when the user clicks the recommendation information to when the application corresponding to the recommendation information is downloaded and activated, which results in a problem that the number of activations counted in a short period of time is small and the activation cost is high. For the recommendation information which is just created and still in the cold start period, because the data volume is too small, the data (including the display volume, the activation volume and the like) of the recommendation information collected by the background server cannot truly reflect the quality of the recommendation information, and meanwhile, because the data volume is small, the confidence coefficient of the data is low, the putting cost of the obtained recommendation information is inaccurate, and the establishment of an adjustment strategy for the recommendation information is influenced.
Disclosure of Invention
According to the embodiment of the disclosure, the determination scheme of the information delivery cost, which can accurately determine the delivery cost of the recommendation information under the condition of small data volume, can be formulated according to the recommendation information, and therefore an accurate adjustment strategy can be formulated.
In a first aspect of the present disclosure, a method for determining an information delivery cost is provided, including:
acquiring total input cost and total display quantity of target information in target time and an activation rate estimated value of the target information;
determining a confidence interval of the activation rate estimated value, and acquiring a target value of the activation rate estimated value corresponding to the confidence interval;
and determining the putting cost of the target information according to the total putting cost and the total display amount and the target value.
The above-described aspects and any possible implementation further provide an implementation, further including: the activation rate pre-estimated value is obtained according to the accumulated display amount, the accumulated activation amount and the accumulated activation amount ratio of each unit time period in a preset period before the target time.
The above-described aspect and any possible implementation further provide an implementation, where the activation rate prediction value is obtained by:
and determining a first sum of the ratio of the cumulative active amount to the cumulative active amount in each unit time period in the preset period and a second sum of the cumulative display amount in each unit time period in the preset period, and taking the ratio of the first sum to the second sum as an active rate pre-estimated value of the target information.
The foregoing aspect and any possible implementation manner further provide an implementation manner, where the determining a confidence interval of the activation rate estimated value and obtaining an upper limit of the confidence interval of the activation rate estimated value include:
and determining an interval with the value probability of the activation rate pre-estimated value larger than a preset threshold value by adopting a confidence interval algorithm as the confidence interval of the activation rate pre-estimated value, and acquiring the upper limit of the confidence interval of the activation rate pre-estimated value.
The above-described aspect and any possible implementation further provide an implementation, where the activation rate prediction value is obtained by:
determining a first sum of a ratio of an accumulated activation amount to an accumulated activation amount in the preset period and a second sum of the accumulated display amount, and taking the ratio of the first sum to the second sum as a first activation rate pre-estimated value of the target information;
taking the ratio of the display amount and the activation amount before the preset period as a second activation rate estimated value;
and summing the product of the first activation rate estimated value and a first adjusting coefficient and the product of the second activation rate estimated value and a second adjusting coefficient to obtain the activation rate estimated value of the target information, wherein the sum of the first adjusting coefficient and the second adjusting coefficient is 1.
The above-described aspect and any possible implementation manner further provide an implementation manner, where the determining the placement cost of the target information according to the total placement cost and the total exposure, and the upper limit of the confidence interval of the activation rate pre-estimation value includes:
and taking the product of the total putting cost and the total display quantity ratio and the upper limit of the confidence interval of the activation rate estimated value as the putting cost of the target information.
The above-described aspects and any possible implementation further provide an implementation, further including:
judging whether the delivery cost of the target information is greater than the target delivery cost of the target information;
and stopping delivering the target information in response to the delivering cost of the target information being larger than the target delivering cost of the target information.
In a second aspect of the present disclosure, there is provided an information placement cost determination apparatus, including:
the data acquisition module is used for acquiring the total input cost and the total display amount of the target information in the target time and the activation rate estimated value of the target information;
the activation rate predicted value determining module is used for determining a confidence interval of the activation rate predicted value and acquiring a target value of the activation rate predicted value corresponding to the confidence interval;
and the putting cost determining module is used for determining the putting cost of the target information according to the total putting cost and the total display amount and the target value.
In a third aspect of the present disclosure, an electronic device is provided, comprising a memory having stored thereon a computer program and a processor implementing the method as described above when executing the program.
In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method as set forth above.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
By the information putting cost determining method, the putting cost of the recommendation information can be accurately determined under the condition of small data volume, so that an accurate adjusting strategy can be formulated for the recommendation information.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:
fig. 1 shows a flowchart of a method for determining information placement cost according to a first embodiment of the present disclosure;
fig. 2 shows a flowchart of a method for determining information placement cost according to a second embodiment of the present disclosure;
fig. 3 is a functional structure diagram of an information placement cost determination apparatus according to a third embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a device for determining information placement cost according to a fourth embodiment of the present disclosure;
fig. 5 shows a distribution graph of target information click and application activation time difference fitted to impression effect data for 7 days somewhere.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
According to the method for determining the information delivery cost, the delivery cost of the target information can be determined according to the total delivery cost and the total display amount of the target time of the target information and the activation rate estimated value determined by the data in the preset period before the target time, the delivery cost of the target information does not need to be determined by obtaining the activation amount brought by the target information, and the problem that the delivery cost of the determined target information is too high due to activation delay is solved. Meanwhile, the confidence interval of the activation rate pre-evaluation value is calculated, the upper limit of the confidence interval is used as the upper limit of the activation rate pre-evaluation value, the lower limit of the launching cost of the target information is determined, the phenomenon that the advertisement cold start is mistakenly shut down due to cost abnormity is avoided, and the passing rate of the cold start advertisement is improved.
Specifically, as shown in fig. 1, it is a flowchart of a method for determining information placement cost according to a first embodiment of the present disclosure. As shown in fig. 1, the method of this embodiment may include the following steps:
s101: and acquiring the total putting cost and the total display amount of the target information at the target time and an activation rate estimated value of the target information.
The target information in this embodiment may be one of a plurality of information, where the information may be an advertisement or recommended content, etc. The target time in this embodiment refers to a current time point, that is, a time point corresponding to when the cost of delivering the target information is determined. The preset period in this embodiment refers to a time period before the target time point.
The present embodiment and the following embodiments take advertisement as an example to explain the technical solutions of the present disclosure. In advertisement delivery, in order to measure the quality of an advertisement, it is necessary to collect effectiveness data of advertisement delivery over a period of time. However, if the set time is long, the recent change of the advertisement is not reflected well, and if the set time is short, the activation delay is greatly affected. In the automatic delivery, in order to respond to the performance of the advertisement in time, only advertisement effect data in a short time period can be selected as a judgment basis, so that the problem of activation delay needs to be solved, and a method for estimating the advertisement cost more accurately needs to be found.
In the process of implementing the technical scheme of the present disclosure, the applicant finds that the time difference between advertisement clicking and application activation and the application activation ratio are in accordance with logarithmic distribution through multiple practices, and as shown in fig. 5, a distribution graph of target information clicking and application activation time difference is fitted to delivery effect data within 7 days of a certain place. The abscissa of fig. 5 represents a time difference between an advertisement click and application activation, the ordinate represents an application activation ratio in hours, points in the graph are statistical actual data, the curve is a fitted logarithmic function curve, and the time difference between the advertisement click and application activation and the application activation ratio satisfy a functional relationship of y-alni + b, where y represents the application activation ratio, i represents the time difference between the advertisement click and application activation, and a and b are constant coefficients.
Since the ratio of the total placement cost of the advertisement to the activation amount of the application needs to be known when the average cost of the advertisement is determined in a short time period, but there is a certain time difference (i.e., activation delay) from when the user clicks the recommendation information to when the application is downloaded and activated, the activation amount of the application cannot be accurately determined, which may cause the problems that the counted activation number is small in a short time period and the determined average cost of the advertisement is high. And the display amount of the advertisement can be acquired from time to time, so that the data for determining the average cost of the advertisement and participating in calculation by using the total placement cost of the advertisement and the display amount of the advertisement is accurate, and the determined average cost of the advertisement is more accurate.
Generally, the following relationship exists between advertisement clicking and application activation, wherein an advertisement is displayed first and then browsed by a user to acquire information related to an application, and the user clicks the information related to the application to download and activate the application according to personal interests. At the same time, the average cost of the advertisement Where CPA is the average Cost of the ad, which is the ratio of the total Cost of placement (Cost) of the ad to the amount of activation of the application (activities). And (Impression/Actives) ((expressions/Clicks) ((Clicks/Active) ((CTR/CVR)), wherein Clicks is click rate, CTR is click rate, and CVR is activation rate. Meanwhile, the time difference between the advertisement click and the application activation ratio satisfy the functional relationship of y-alni + b, so that the advertisement click and the application activation ratio can be adjustedIs converted into Wherein,expressed for a function related to the functional relationship y-alni + b, thus optimizedThe average cost of the advertisement can be estimated.
Therefore, the average cost of the target advertisement can be obtained by multiplying the ratio of the current placement cost and the current exposure amount by a prediction coefficient, wherein the prediction coefficient is the reciprocal of the product of the advertisement click rate and the advertisement conversion rate. According to the embodiment of the disclosure, the average cost of the target advertisement is estimated by fitting and optimizing the estimation coefficient and taking the approximate value of the estimation coefficient.
In this embodiment, when determining the placement cost of the target information, it is necessary to obtain the total placement cost and the total exposure of the target time of the target information, and the ratio of the cumulative exposure, the cumulative activation, and the cumulative activation of the target information in a unit time period in a preset period before the target time.
From the above, it can be known that when determining the placement cost of the target information, the total placement cost and the total exposure of the target time for obtaining the target information are needed, that is, the above-mentionedThe accumulated display amount of the unit time period in the preset period before the target time,The cumulative activation amount and the ratio of the cumulative activation amount are used to determineAboutSee the subsequent step S102.
And S102, determining a confidence interval of the activation rate estimated value, and acquiring a target value of the activation rate estimated value corresponding to the confidence interval. .
In the present embodiment, it is preferred that,that is, the activation rate estimation value is obtained, and RR is 1/(expressions/cicks) × (clincks/Active) ═ Active/expressions. That is, an approximate estimate of Active/expressions is determinedAnd determining the delivery cost of the target information. Meanwhile, the time difference between the advertisement click and the application activation ratio satisfy the functional relation of y being alni + b, wherein y represents the application activation ratio, i represents the time difference between the advertisement click and the application activation, and a and b are constant coefficients. Therefore, in this embodiment, when determining the activation rate pre-estimated value of the target information according to the cumulative exposure amount, the cumulative activation amount, and the cumulative activation amount ratio, a first sum of ratios of the cumulative activation amount and the cumulative activation amount ratio in the preset period and a second sum of the cumulative exposure amount may be determined, and the ratio of the first sum and the second sum may be used as the activation rate pre-estimated value of the target information. The estimated activation rate is determined using the following equation:
wherein,wherein y is the cumulative percentage of the activation number at the ith hour in the preset period, and i can be substituted intoTo obtain MiIs the advertisement display amount of the ith hour in the preset period, AiThe activation amount of the advertisement in the ith hour in the preset period can be directly obtained from a background server for advertisement delivery, and 0.01 is used for avoiding the occurrence of a 0 value. After the cumulative percentage of activation and the advertisement display amount per hour in the preset period and the advertisement activation amount are obtained, the obtained data can be substituted into the formula to obtain the value of RR.
In the present embodiment, the preset period is 24 hours. In other embodiments, the preset period may be set manually according to actual needs, and may be, for example, 48 hours, one week, and the like.
After determining the activation rate estimate of the target information, a confidence interval of the activation rate estimate, that is, a confidence interval of the RR, may be further determined. The essence of the confidence interval is to correct the confidence level to compensate for the effect of too small a sample size. If a plurality of samples exist, the confidence is proved to be relatively credible, and large correction is not needed, so the confidence interval is relatively narrow, and the lower limit value is relatively large; if the number of samples is small, the confidence is not necessarily reliable, and a large correction is necessary, so that the confidence interval is relatively wide and the lower limit value is relatively small. For advertisements during cold start periods, the corresponding confidence interval also needs to be determined due to the small data size of the sample. Due to average cost of advertisingThe RR of an ad may be overestimated, i.e., the ad may be more likely to be considered a premium ad without knowing the goodness of the ad. Therefore, after the estimated RR of the advertisement is obtained, the estimated CPA of the advertisement can be deduced reversely, and then the adjustment of the advertisement is determined by taking the estimated CPA as a standard. Applied to a particular scenario of advertisement delivery, i.e. toAn estimated lower CPA bound can be obtained:
specifically, a Wilson confidence interval algorithm may be adopted to determine the confidence interval of the activation rate estimated value, and an upper limit of the confidence interval of the activation rate estimated value may be obtained.
Wherein,
where z is z statistic representing some confidence level, z ∈ (0,1), typically 0.95 for z, Impedents is the exposure of the ad,
the result is that the greater the amount of ad activation, the smaller the CPA-to-CPA gap, and vice versa.
S104: and determining the putting cost of the target information according to the total putting cost and the total display amount and the target value.
And taking the product of the total putting cost and the total display quantity ratio and the upper limit of the confidence interval of the activation rate estimated value as the putting cost for searching the target information.
In thatAfter substituting data, RR can be obtained+And then further obtain CPA_I.e., the lower bound of the average cost of the advertisement (target information), i.e., the lowest average cost of the target time of the target information, and the placement cost of the target information can be adjusted according to the lowest average cost.
Generally, in the initial stage of advertisement delivery, the revenue caused by the activation amount of the advertisement can be calculated, so as to estimate the target cost of advertisement delivery, and if the average cost estimated according to the current presentation amount exceeds the target cost, the advertisement should be stopped from being continuously delivered, so that after the average cost of the target advertisement is estimated, the target cost of the target advertisement needs to be further acquired, and whether the advertisement is continuously delivered is determined. For example, if the lowest average cost of the target time of the target information is lower than the target cost of the target information, the target information may be continuously delivered, and if the lowest average cost of the target time of the target information is higher than the target cost of the target information, the target information may not be continuously delivered.
According to the method for determining the information delivery cost, the delivery cost of the target information can be determined according to the total delivery cost and the total display amount of the target time of the target information and the activation rate estimated value determined by the data in the preset period before the target time, the delivery cost of the target information does not need to be determined by obtaining the activation amount brought by the target information, and the problem that the delivery cost of the determined target information is too high due to activation delay is solved. Meanwhile, the confidence interval of the activation rate pre-evaluation value is calculated, the upper limit of the confidence interval is used as the upper limit of the activation rate pre-evaluation value, the lower limit of the launching cost of the target information is determined, the phenomenon that the advertisement cold start is mistakenly shut down due to cost abnormity is avoided, and the passing rate of the cold start advertisement is improved.
Fig. 2 shows a flowchart of a method for determining information placement cost according to a second embodiment of the present disclosure. The method of the embodiment may include the following steps:
s201: the method comprises the steps of obtaining the total input cost and the total display amount of target time of target information, the cumulative display amount, the cumulative activation amount and the cumulative activation amount ratio of unit time period in a preset period before the target time, and the display amount and the activation amount before the preset period.
In this embodiment, when determining the placement cost of the target information, it is necessary to obtain the total placement cost and the total exposure of the target time of the target information, and the ratio of the cumulative exposure, the cumulative activation, and the cumulative activation of the unit time period in the preset period before the target time.
S202: determining a first sum of a ratio of an accumulated activation amount to an accumulated activation amount in the preset period and a second sum of the accumulated display amount, and taking the ratio of the first sum to the second sum as a first activation rate pre-estimated value of the target information; taking the ratio of the display amount and the activation amount before the preset period as a second activation rate estimated value; and summing the product of the first activation rate estimated value and a first adjusting coefficient and the product of the second activation rate estimated value and a second adjusting coefficient to form the activation rate estimated value of the target information, wherein the sum of the first adjusting coefficient and the second adjusting coefficient is 1.
The estimated activation rate is determined using the following equation:
wherein,wherein y is the cumulative percentage of the activation number at the ith hour in the preset period, and i can be substituted intoTo obtain MiIs the advertisement display amount of the ith hour in the preset period, AiThe activation amount of the advertisement in the ith hour in the preset period can be directly obtained from a background server for advertisement delivery, and 0.01 is used for avoiding the occurrence of a 0 value. M0Is the advertisement display amount before the preset period, A0The advertisement activation amount before the preset period. In this embodiment, the first adjustment coefficient is 0.3, and the second adjustment coefficient is 0.7, which respectively indicate that the weight of the data in the preset period is at least 30% and the weight of the data before the preset period is at most 70%, and can be determined according to actual requirementsThe values of the first adjustment factor and the second adjustment factor. 20000 is to limit the negative effect caused by too much advertisement display before the preset period, and these values are not fixed and can be adjusted according to the actual situation. After the cumulative percentage of activation, the advertisement display amount, and the advertisement activation amount per hour in the preset period, and the display amount and the activation amount before the preset period are obtained, the obtained data may be substituted into the above formula to obtain the value of RR.
S203: and determining a confidence interval of the activation rate estimated value, and acquiring an upper limit of the confidence interval of the activation rate estimated value.
S204: and determining the release cost of the target information according to the total release cost and the total display amount and the upper limit of the confidence interval of the activation rate estimated value.
In this embodiment, specific implementation manners of step S203 and step S204 refer to step S103 and step S104 in the first embodiment, and details are not repeated here.
S205: and judging whether the putting cost of the target information is greater than the target putting cost of the target information.
After this embodiment, after the placement cost of the target information is determined according to the total placement cost and the total display amount, and the upper limit of the confidence interval of the activation rate estimated value, the placement cost of the target information may be compared with the target placement cost of the target information, and it is determined whether the placement cost after overestimating the activation amount of the target information is greater than the target placement cost of the target information.
Generally, in the initial stage of advertisement delivery, the revenue caused by the activation amount of the advertisement can be calculated, so as to estimate the target cost of advertisement delivery, and if the average cost estimated according to the current presentation amount exceeds the target cost, the advertisement should be stopped from being continuously delivered, so that after the average cost of the target advertisement is estimated, the target cost of the target advertisement needs to be further acquired, and whether the advertisement is continuously delivered is determined. For example, if the lowest average cost of the target time of the target information is lower than the target cost of the target information, the target information may be continuously delivered, and if the lowest average cost of the target time of the target information is higher than the target cost of the target information, the target information may not be continuously delivered.
S206: and stopping the cost delivery of the target information in response to the delivery cost of the target information being greater than the target delivery cost of the target information.
According to the method for determining the information delivery cost, the delivery cost of the target information can be determined according to the total delivery cost and the total display amount of the target time of the target information and the activation rate estimated value determined by the data in the preset period before the target time, the delivery cost of the target information does not need to be determined by obtaining the activation amount brought by the target information, and the problem that the delivery cost of the determined target information is too high due to activation delay is solved. Meanwhile, the confidence interval of the activation rate pre-evaluation value is calculated, the upper limit of the confidence interval is used as the upper limit of the activation rate pre-evaluation value, the lower limit of the launching cost of the target information is determined, the phenomenon that the advertisement cold start is mistakenly shut down due to cost abnormity is avoided, and the passing rate of the cold start advertisement is improved.
It is noted that while for simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present disclosure is not limited by the order of acts, as some steps may, in accordance with the present disclosure, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that acts and modules referred to are not necessarily required by the disclosure.
The above is a description of embodiments of the method, and the embodiments of the apparatus are further described below.
As shown in fig. 3, a functional structure diagram of a device for determining information distribution cost according to a third embodiment of the present disclosure is shown, where the device for determining information distribution cost according to the present embodiment includes:
a data obtaining module 301, configured to obtain a total release cost and a total display amount of the target information at a target time, and an activation rate pre-estimated value of the target information.
An activation rate estimated value determining module 302, configured to determine a confidence interval of the activation rate estimated value, and obtain a target value of the activation rate estimated value corresponding to the confidence interval.
And an investment cost determining module 303, configured to determine an investment cost of the target information according to the total investment cost and the total exposure, and the target value.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the described module may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
Fig. 4 shows a schematic structural diagram of a device for determining information placement cost according to a fourth embodiment of the present disclosure. The terminal device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 4, the computer system includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes based on a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for system operation are also stored. The CPU 401, ROM 402, and RAM403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. Drivers 410 are also connected to the I/O interface 405 on an as needed basis. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 on an as-needed basis, so that a computer program read out therefrom is mounted on the storage section 408 on an as-needed basis.
In particular, based on the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 401.
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. A method for determining information placement cost is characterized by comprising the following steps:
acquiring total input cost and total display quantity of target information in target time and an activation rate estimated value of the target information;
determining a confidence interval of the activation rate estimated value, and acquiring a target value of the activation rate estimated value corresponding to the confidence interval;
and determining the putting cost of the target information according to the total putting cost, the total display amount and the target value.
2. The method for determining information delivery cost according to claim 1, wherein the activation rate pre-estimated value is obtained according to a cumulative exposure amount, a cumulative activation amount, and a cumulative activation amount ratio of each unit time period in a preset period before the target time.
3. The method for determining information placement cost according to claim 2, wherein the activation rate estimate is obtained by:
and determining a first sum of the ratio of the cumulative active amount to the cumulative active amount in each unit time period in the preset period and a second sum of the cumulative display amount in each unit time period in the preset period, and taking the ratio of the first sum to the second sum as an active rate pre-estimated value of the target information.
4. The method according to claim 3, wherein the determining the confidence interval of the activation rate estimate and obtaining the upper limit of the confidence interval of the activation rate estimate comprise:
and determining an interval with the value probability of the activation rate pre-estimated value larger than a preset threshold value by adopting a confidence interval algorithm as the confidence interval of the activation rate pre-estimated value, and acquiring the upper limit of the confidence interval of the activation rate pre-estimated value.
5. The method for determining information placement cost according to claim 1, wherein the activation rate estimate is obtained by:
determining a first sum of a ratio of an accumulated activation amount to an accumulated activation amount in the preset period and a second sum of the accumulated display amount, and taking the ratio of the first sum to the second sum as a first activation rate pre-estimated value of the target information;
taking the ratio of the display amount and the activation amount before the preset period as a second activation rate estimated value;
and summing the product of the first activation rate estimated value and a first adjusting coefficient and the product of the second activation rate estimated value and a second adjusting coefficient to obtain the activation rate estimated value of the target information, wherein the sum of the first adjusting coefficient and the second adjusting coefficient is 1.
6. The method for determining information placement cost according to claim 5, wherein said determining placement cost of said target information according to said total placement cost and total exposure, and an upper limit of a confidence interval of said estimated activation rate value comprises:
and taking the product of the total putting cost and the total display quantity ratio and the upper limit of the confidence interval of the activation rate estimated value as the putting cost of the target information.
7. The method for determining information placement cost according to claim 6, further comprising:
judging whether the delivery cost of the target information is greater than the target delivery cost of the target information;
and stopping delivering the target information in response to the delivering cost of the target information being larger than the target delivering cost of the target information.
8. An information placement cost determination apparatus, comprising:
the data acquisition module is used for acquiring the total input cost and the total display amount of the target information in the target time and the activation rate estimated value of the target information;
the activation rate predicted value determining module is used for determining a confidence interval of the activation rate predicted value and acquiring a target value of the activation rate predicted value corresponding to the confidence interval;
and the putting cost determining module is used for determining the putting cost of the target information according to the total putting cost and the total display amount and the target value.
9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011019502.0A CN111967921A (en) | 2020-09-24 | 2020-09-24 | Method, device, equipment and storage medium for determining information delivery cost |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011019502.0A CN111967921A (en) | 2020-09-24 | 2020-09-24 | Method, device, equipment and storage medium for determining information delivery cost |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111967921A true CN111967921A (en) | 2020-11-20 |
Family
ID=73387440
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011019502.0A Pending CN111967921A (en) | 2020-09-24 | 2020-09-24 | Method, device, equipment and storage medium for determining information delivery cost |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111967921A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113011927A (en) * | 2021-03-31 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
CN113065066A (en) * | 2021-03-31 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Prediction method, prediction device, server and storage medium |
CN113570403A (en) * | 2021-06-30 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Promotion information release effect prediction method and device and server |
CN114466061A (en) * | 2022-01-25 | 2022-05-10 | 北京快乐茄信息技术有限公司 | Information processing method, information processing apparatus, server, and storage medium |
CN114500639A (en) * | 2022-01-11 | 2022-05-13 | 北京达佳互联信息技术有限公司 | Multimedia data delivery method and device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1294826A (en) * | 1999-02-26 | 2001-05-09 | 诺基亚网络有限公司 | Method for determining confidence limit |
US20130275580A1 (en) * | 2012-04-11 | 2013-10-17 | Taboola.Com Ltd. | Click through rate estimation in varying display situations |
CN107944918A (en) * | 2017-11-27 | 2018-04-20 | 精硕科技(北京)股份有限公司 | The management method and device that information is launched |
CN110033314A (en) * | 2019-03-18 | 2019-07-19 | 北京品友互动信息技术股份公司 | Advertisement data processing method and device |
CN111667312A (en) * | 2020-06-08 | 2020-09-15 | 腾讯科技(深圳)有限公司 | Advertisement delivery method, related device, equipment and storage medium |
-
2020
- 2020-09-24 CN CN202011019502.0A patent/CN111967921A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1294826A (en) * | 1999-02-26 | 2001-05-09 | 诺基亚网络有限公司 | Method for determining confidence limit |
US20130275580A1 (en) * | 2012-04-11 | 2013-10-17 | Taboola.Com Ltd. | Click through rate estimation in varying display situations |
CN107944918A (en) * | 2017-11-27 | 2018-04-20 | 精硕科技(北京)股份有限公司 | The management method and device that information is launched |
CN110033314A (en) * | 2019-03-18 | 2019-07-19 | 北京品友互动信息技术股份公司 | Advertisement data processing method and device |
CN111667312A (en) * | 2020-06-08 | 2020-09-15 | 腾讯科技(深圳)有限公司 | Advertisement delivery method, related device, equipment and storage medium |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113011927A (en) * | 2021-03-31 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
CN113065066A (en) * | 2021-03-31 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Prediction method, prediction device, server and storage medium |
CN113011927B (en) * | 2021-03-31 | 2023-10-13 | 北京奇艺世纪科技有限公司 | Information delivery method and device, electronic equipment and storage medium |
CN113065066B (en) * | 2021-03-31 | 2024-05-07 | 北京达佳互联信息技术有限公司 | Prediction method, prediction device, server and storage medium |
CN113570403A (en) * | 2021-06-30 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Promotion information release effect prediction method and device and server |
CN114500639A (en) * | 2022-01-11 | 2022-05-13 | 北京达佳互联信息技术有限公司 | Multimedia data delivery method and device, electronic equipment and storage medium |
CN114466061A (en) * | 2022-01-25 | 2022-05-10 | 北京快乐茄信息技术有限公司 | Information processing method, information processing apparatus, server, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111967921A (en) | Method, device, equipment and storage medium for determining information delivery cost | |
CN112184293A (en) | Method, device, equipment and storage medium for adjusting information delivery cost | |
US20140157270A1 (en) | Virtual machine management | |
US20100088719A1 (en) | Generating reach and frequency data for television advertisements | |
CN105306539B (en) | Service information display control method and device and Internet service information display platform | |
US10657559B2 (en) | Generating and utilizing a conversational index for marketing campaigns | |
CN108932627B (en) | Estimation method and device for consumption speed of CPA (continuous advertisement access) advertisement and readable storage medium | |
US9292336B1 (en) | Systems and methods providing optimization data | |
CN108009862B (en) | Method and device for early warning of balance of advertising expense | |
CN110889725B (en) | Online advertisement CTR estimation method, device, equipment and storage medium | |
CN108564404B (en) | Method and device for predicting return on investment of advertisement | |
US20090150198A1 (en) | Estimating tv ad impressions | |
CN117370329A (en) | Intelligent management method and system for equipment data based on industrial Internet of things | |
CN113543195A (en) | Communication base station evaluation method and device and electronic equipment | |
CN107038492A (en) | Daily Order volume Forecasting Methodology and device based on Arma models | |
CN110569190B (en) | Transaction pressure testing method and device, electronic device and readable storage medium | |
CN107944737A (en) | Information processing method, device, electronic equipment and computer-readable recording medium | |
US10565613B2 (en) | Simulating advertising campaigns | |
CN112001563A (en) | Method and device for managing phone bill amount, electronic equipment and storage medium | |
Garber et al. | Nursing home discharges and exhaustion of Medicare benefits | |
US8744947B1 (en) | System and method for optimizing media portfolio allocation | |
CN113689224B (en) | Advertisement traffic processing method, device and equipment | |
CN115242626B (en) | Cloud resource allocation prediction method, device, equipment, storage medium and program product | |
US11869042B2 (en) | Bidding assistance device, bidding assistance method, and computer-readable medium storing bidding assistance program | |
CN112446740B (en) | Advertisement data curve generation method, system, electronic equipment and storage 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 |