CN115066702A - Advertisement putting distribution method and device, electronic equipment and storage medium - Google Patents
Advertisement putting distribution method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115066702A CN115066702A CN202080003840.7A CN202080003840A CN115066702A CN 115066702 A CN115066702 A CN 115066702A CN 202080003840 A CN202080003840 A CN 202080003840A CN 115066702 A CN115066702 A CN 115066702A
- Authority
- CN
- China
- Prior art keywords
- user
- sequence
- newly
- added
- newly added
- 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 54
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims description 15
- 230000003203 everyday effect Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 abstract description 10
- 238000005457 optimization Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000013011 mating Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 230000002354 daily effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 108090000623 proteins and genes Proteins 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
Abstract
In the method, after a first user newly-added sequence is obtained, a preset number of second user newly-added sequences are obtained through copying, then elements in each second user newly-added sequence are randomly changed, a third user newly-added sequence obtained after the change is used as a second user newly-added sequence, and the process is continued until a preset convergence condition is met. And then, taking the user newly increased sequence corresponding to the maximum return on investment in the whole process as a target user newly increased sequence, and carrying out advertisement putting distribution according to the target user newly increased sequence. According to the method, a plurality of second user newly-added sequences are firstly obtained through copying, elements in each second user newly-added sequence are randomly changed, and the problem of local optimization in a short period is avoided through the operation, so that the final advertisement putting distribution is more reasonable.
Description
The invention relates to the technical field of product popularization, in particular to an advertisement putting distribution method and device, electronic equipment and a storage medium.
The user of the product increases, except for the natural increase brought by the brand effect, and the situation that the user cannot put advertisements on the market to refresh is avoided. Channels involved in advertising include different countries, different platforms, different advertisers, etc. The cost of product promotion is limited, and each large APP wants to achieve rapid growth of users through advertisement delivery. In the face of a fierce advertisement market, how to reasonably distribute advertisement delivery is a difficult problem faced at present.
Most of the existing advertisement putting and distributing methods are based on a heuristic greedy algorithm. Specifically, the limiting conditions are set, including budget, the number of target daily active users DAU and target revenue, and after the advertisement delivery distribution scheme is adjusted each time, information such as cost, income and newly added users of each channel for recent advertisement delivery is obtained. Based on the objective function (return on investment rate ROI function), the maximum value and the minimum value of the objective function are selected under the condition of guaranteeing the limiting conditions. And increasing the putting amount of the channel corresponding to the maximum value of the objective function, reducing the putting amount of the channel corresponding to the minimum value of the objective function, calculating the maximum value of the objective function and the minimum value of the objective function again, and repeating the steps until the objective function is converged. The existing advertisement delivery distribution scheme has the problem that the existing advertisement delivery distribution scheme is easy to fall into local optimization in a short term.
Disclosure of Invention
The embodiment of the invention provides an advertisement putting distribution method, an advertisement putting distribution device, electronic equipment and a storage medium, which are used for solving the problem that the existing advertisement putting distribution scheme is easy to fall into local optimization in a short term, so that the advertisement putting distribution is unreasonable.
The embodiment of the invention provides an advertisement putting and distributing method, which comprises the following steps:
acquiring a first user newly increased sequence within a preset first time length, wherein elements in the first user newly increased sequence are the newly increased number of users corresponding to each advertisement delivery channel;
copying the first user newly added sequence to obtain a preset number of second user newly added sequences, and randomly changing elements in the second user newly added sequence aiming at each second user newly added sequence to obtain a third user newly added sequence corresponding to the second user newly added sequence;
determining the return on investment of the newly added user sequence according to the corresponding relationship between the newly added user number and the unit price of the user and the corresponding relationship between the newly added user number and the individual user income under each predetermined advertisement delivery channel, judging whether a preset convergence condition is met, and if not, taking each newly added third user sequence as a second newly added user sequence; if so, taking the user newly-added sequence corresponding to the maximum return on investment as a target user newly-added sequence; and performing advertisement putting distribution according to the target user newly added sequence.
In another aspect, an embodiment of the present invention provides an advertisement delivery distribution apparatus, where the apparatus includes:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a first user newly-increased sequence within a preset first time length, and elements in the first user newly-increased sequence are newly-increased number of users corresponding to each advertisement delivery channel;
the first determining module is used for copying the first user newly added sequence to obtain a preset number of second user newly added sequences, and randomly changing elements in the second user newly added sequence aiming at each second user newly added sequence to obtain a third user newly added sequence corresponding to the second user newly added sequence;
a second determining module, configured to determine, according to a predetermined correspondence between the newly added user number and the unit price of the user in each advertisement delivery channel and a predetermined correspondence between the newly added user number and the individual user revenue, an investment return rate of the newly added user sequence, and determine whether a preset convergence condition is met, and if not, take each newly added third user sequence as a second newly added user sequence; if so, taking the user newly increased sequence corresponding to the maximum return on investment as a target user newly increased sequence; and performing advertisement putting distribution according to the target user newly added sequence.
On the other hand, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
a processor for implementing any of the above method steps when executing a program stored in the memory.
In another aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps of any one of the above.
The embodiment of the invention provides an advertisement putting distribution method, an advertisement putting distribution device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a first user newly-increased sequence within a preset first time length, wherein elements in the first user newly-increased sequence are the newly-increased number of users corresponding to each advertisement delivery channel; copying the first user newly added sequence to obtain second user newly added sequences of a preset number, and randomly changing elements in the second user newly added sequences aiming at each second user newly added sequence to obtain third user newly added sequences corresponding to the second user newly added sequences; determining the return on investment of the newly added user sequence according to the corresponding relationship between the newly added user number and the unit price of the user and the corresponding relationship between the newly added user number and the individual user income under each predetermined advertisement delivery channel, judging whether a preset convergence condition is met, and if not, taking each newly added third user sequence as a second newly added user sequence; if so, taking the user newly increased sequence corresponding to the maximum return on investment as a target user newly increased sequence; and performing advertisement putting distribution according to the target user newly added sequence.
In the embodiment of the invention, after the first user adding sequence is obtained, the second user adding sequences with the preset number are obtained by copying, then elements in each second user adding sequence are randomly changed, the third user adding sequence obtained after the change is used as the second user adding sequence, and the process is continued until the preset convergence condition is met. And then, taking the user newly increased sequence corresponding to the maximum return on investment in the whole process as a target user newly increased sequence, and carrying out advertisement putting distribution according to the target user newly increased sequence. According to the embodiment of the invention, firstly, a plurality of second user newly-added sequences are obtained by copying, and secondly, elements in each second user newly-added sequence are randomly changed, so that the problem of local optimization in a short period is avoided through the operation, and the final advertisement putting distribution is more reasonable.
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of an advertisement delivery distribution process provided in embodiment 1 of the present invention;
fig. 2 is a flow chart of advertisement placement allocation provided in embodiment 6 of the present invention;
FIG. 3 is a schematic diagram of the mating variation of the newly added user sequences provided in embodiment 6 of the present invention;
fig. 4 is a schematic structural diagram of an advertisement delivery distribution device provided in embodiment 7 of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to embodiment 8 of the present invention.
The present invention will be described in further detail with reference to the attached drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
Example 1:
fig. 1 is a schematic diagram of an advertisement placement allocation process provided in an embodiment of the present invention, where the process includes the following steps:
s101: and acquiring a first user newly-increased sequence within a preset first time length, wherein elements in the first user newly-increased sequence are the newly-increased number of users corresponding to each advertisement delivery channel.
S102: and copying the first user newly added sequence to obtain second user newly added sequences of a preset number, and randomly changing elements in the second user newly added sequence aiming at each second user newly added sequence to obtain a third user newly added sequence corresponding to the second user newly added sequence.
S103: determining the return on investment of the newly added user sequence according to the corresponding relationship between the newly added user number and the unit price of the user and the corresponding relationship between the newly added user number and the individual user income under each predetermined advertisement delivery channel, judging whether a preset convergence condition is met, and if not, taking each newly added third user sequence as a second newly added user sequence; if so, taking the user newly-added sequence corresponding to the maximum return on investment as a target user newly-added sequence; and performing advertisement putting distribution according to the target user newly added sequence.
The advertisement putting and distributing method provided by the embodiment of the invention is applied to electronic equipment, and the electronic equipment can be equipment such as a PC (personal computer), a tablet personal computer and the like.
When counting the number of newly added users, the statistics is generally performed on a daily basis, that is, the number of newly added users per day is counted. And the statistics of the number of the newly added users every day is performed for each advertisement delivery channel, and the advertisement delivery channels can be subdivided into countries, advertisers and platforms. The electronic equipment acquires the newly increased number of users within a preset first time span aiming at each advertisement delivery channel. The preset first time length may be the last day, the last week, or the like. And if the number is the latest week, acquiring the newly increased number of the users for each advertisement delivery channel every day in the latest week, and then calculating the average value of the newly increased number of the users for each day in the latest week to be used as the newly increased number of the users corresponding to the advertisement delivery channel. And the newly increased number of the users corresponding to each advertisement delivery channel is used as an element to form a first newly increased user sequence.
After acquiring the first user adding sequence, the electronic device copies the first user adding sequence to obtain a preset number of second user adding sequences, where the preset number may be 100, 200, and the like. And for each second user newly added sequence, randomly changing elements in the second user newly added sequence, for example, randomly increasing a certain numerical value or randomly decreasing a certain numerical value or keeping unchanged for each element in the second user newly added sequence, so as to obtain a third user newly added sequence corresponding to the second user newly added sequence.
In the process of advertisement putting distribution, the obtained return on investment of each user newly added sequence can be determined. It should be noted that the terms "first", "second", and the like in the first user adding sequence, the second user adding sequence, and the like in the embodiments of the present invention are used for descriptive purposes only, and are not to be construed as indicating or implying relative importance, nor as indicating or implying order. The first user adding sequence, the second user adding sequence, the third user adding sequence and the like are user adding sequences. And the electronic equipment determines the return on investment of the newly added user sequence according to the corresponding relationship between the newly added user number and the unit price of the user and the corresponding relationship between the newly added user number and the single user income under each predetermined advertisement delivery channel. Specifically, for the user new number corresponding to each advertisement delivery channel in each user new sequence, the cost of the advertisement delivery channel can be determined according to the corresponding relationship between the user new number and the user unit price under the predetermined advertisement delivery channel, and the cost of each advertisement delivery channel in the user new sequence is summed to obtain the total cost of the user new sequence. And aiming at the user new quantity corresponding to each advertisement delivery channel in each user new sequence, determining the income of the advertisement delivery channel according to the corresponding relation between the user new quantity under the advertisement delivery channel and the user individual income, and summing the income of each advertisement delivery channel in the user new sequence to obtain the total income of the user new sequence. And then calculating the ratio of the total income to the total cost to obtain the return on investment of the newly added sequence of the user.
The electronic device is preset with a convergence condition, and the preset convergence condition may be that convergence is determined when the determined maximum return on investment is greater than a preset return rate threshold. Preferably, the determining whether the preset convergence condition is satisfied includes: and judging whether the iteration times of the second user newly added sequence reach a preset time threshold or not, or judging whether the difference value of the determined maximum return on investment rate in two adjacent iterations is smaller than a preset convergence threshold or not. In the embodiment of the invention, whether the preset convergence condition is met is judged, if not, each third user newly added sequence is taken as a second user newly added sequence, and the steps of randomly changing elements in the second user newly added sequence aiming at each second user newly added sequence to obtain a third user newly added sequence corresponding to the second user newly added sequence are continuously carried out until the preset convergence condition is met. And after the condition that the preset convergence condition is met is judged, taking the user adding sequence corresponding to the maximum return on investment as a target user adding sequence.
And performing advertisement putting distribution according to the newly added sequence of the target user. Specifically, according to the predetermined corresponding relationship between the number of newly added users and the unit price of the users in each advertisement delivery channel and the newly added target user sequence, the cost of each advertisement delivery channel can be determined, and advertisements are delivered to each advertisement delivery channel according to the determined cost of each advertisement delivery channel.
In the embodiment of the invention, after the first user adding sequence is obtained, the second user adding sequences with the preset number are obtained by copying, then elements in each second user adding sequence are randomly changed, the third user adding sequence obtained after the change is used as the second user adding sequence, and the process is continued until the preset convergence condition is met. And then, taking the user newly increased sequence corresponding to the maximum investment return rate in the whole process as a target user newly increased sequence, and carrying out advertisement putting distribution according to the target user newly increased sequence. According to the embodiment of the invention, firstly, a plurality of second user newly-added sequences are obtained by copying, and secondly, elements in each second user newly-added sequence are randomly changed, so that the problem of local optimization in a short period is avoided through the operation, and the final advertisement putting distribution is more reasonable.
Example 2:
in order to further increase the randomness of the user addition sequence, on the basis of the foregoing embodiment, in an embodiment of the present invention, the randomly changing, for each second user addition sequence, elements in the second user addition sequence to obtain a third user addition sequence corresponding to the second user addition sequence includes:
randomly changing elements in the second user newly-added sequence aiming at each second user newly-added sequence to obtain a fourth user newly-added sequence corresponding to the second user newly-added sequence;
for each fourth user newly-added sequence, exchanging elements of a corresponding channel in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to a preset random probability to obtain a fifth user newly-added sequence corresponding to the fourth user newly-added sequence;
and taking each fifth user newly added sequence as a third user newly added sequence.
In the embodiment of the invention, for each second user newly added sequence, elements in the second user newly added sequence are randomly changed to obtain a fourth user newly added sequence corresponding to the second user newly added sequence. And then, according to each element in each fourth user newly added sequence, determining whether to exchange the element with the corresponding element in the corresponding second user newly added sequence according to a preset random probability. And in the second user newly-increased sequence and the corresponding second user newly-increased sequence, the element of the same advertisement delivery channel is the corresponding element. The preset random probability may be, for example, 40%, 50%, etc. If the preset random probability is 0.4, for each element in each fourth user newly added sequence, 40% of the probability exchanges the element with the corresponding element in the corresponding second user newly added sequence, and 60% of the probability does not exchange the element with the corresponding element in the corresponding second user newly added sequence. And aiming at each fourth user newly-added sequence, exchanging elements of a corresponding channel in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to a preset random probability to obtain a fifth user newly-added sequence corresponding to the fourth user newly-added sequence, and then taking each fifth user newly-added sequence as the third user newly-added sequence.
In the embodiment of the invention, for each second user newly-added sequence, elements in the second user newly-added sequence are randomly changed to obtain a fourth user newly-added sequence corresponding to the second user newly-added sequence; for each fourth user newly-added sequence, exchanging elements of a corresponding channel in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to a preset random probability to obtain a fifth user newly-added sequence corresponding to the fourth user newly-added sequence; and taking each fifth user newly added sequence as a third user newly added sequence. Therefore, the randomness of the newly added sequence of the user is further increased, the problem of local optimization in a short term is better avoided, and the final advertisement putting distribution is more reasonable.
Example 3:
in order to further make the final distribution of advertisement delivery more reasonable, on the basis of the foregoing embodiments, in the embodiments of the present invention, a concept of "superior-inferior and survival of suitable persons" in genetics is introduced, and before, after the fourth user new sequence corresponding to the second user new sequence is obtained, and for each fourth user new sequence, exchanging elements of a corresponding channel in the fourth user new sequence and the corresponding second user new sequence according to a preset random probability, the method further includes:
determining the probability of selecting each fourth user new sequence according to the return on investment of each fourth user new sequence, wherein the probability of selecting the fourth user new sequence with larger return on investment is larger;
and selecting preset times in each fourth user newly-added sequence according to the selected probability of each fourth user newly-added sequence, adopting the fourth user newly-added sequence selected each time, and carrying out subsequent steps of exchanging elements of corresponding channels in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to preset random probability aiming at each fourth user newly-added sequence.
In the embodiment of the invention, after the electronic equipment determines the fourth user newly-increased sequence corresponding to each second user newly-increased sequence, the return on investment of each fourth user newly-increased sequence is determined according to the predetermined corresponding relation between the newly-increased number of the users and the unit price of the users under each advertisement delivery channel and the corresponding relation between the newly-increased number of the users and the single income of the users. And determining the probability of selecting each fourth user new sequence according to the return on investment of each fourth user new sequence, wherein the probability of selecting the fourth user new sequence with larger return on investment is larger.
And selecting preset times in each fourth user newly added sequence according to the probability of selecting each fourth user newly added sequence. The preset times and the preset number can be the same or different. It should be noted that each selection is not taken out from each fourth user adding sequence, but is copied from each fourth user adding sequence. That is, each time the fourth user added sequence is selected, there is still a chance to be selected at the next time. And then, adopting the fourth user newly-increased sequence selected each time to carry out the subsequent step of exchanging the elements of the channels corresponding to the fourth user newly-increased sequence and the corresponding second user newly-increased sequence according to the preset random probability. The probability that the fourth user newly-added sequence with higher return on investment is selected is higher, namely the application of the thought of 'winning or losing and survival of suitable persons' in genetics further ensures that the final advertisement putting distribution is more reasonable.
Example 4:
in order to further increase the randomness of the user new sequence, on the basis of the foregoing embodiment, in an embodiment of the present invention, after the fifth user new sequence corresponding to the fourth user new sequence is obtained, before each fifth user new sequence is used as a third user new sequence, the method further includes:
randomly changing elements in the fifth user newly increased sequence aiming at each fifth user newly increased sequence to obtain a sixth user newly increased sequence corresponding to the fifth user newly increased sequence; and updating the fifth user newly added sequence by adopting the sixth user newly added sequence.
In the embodiment of the present invention, in order to further increase the randomness of the user adding sequence, after a fifth user adding sequence corresponding to the fourth user adding sequence is obtained, elements in each fifth user adding sequence are randomly changed, so as to obtain a sixth user adding sequence corresponding to the fifth user adding sequence. The process of randomly changing the elements in the fifth user adding sequence is similar to the process of randomly changing the elements in the second user adding sequence, and is not described herein again. And aiming at each fifth user newly added sequence, randomly changing elements in the fifth user newly added sequence to obtain a sixth user newly added sequence corresponding to the fifth user newly added sequence, and then updating the fifth user newly added sequence by adopting the sixth user newly added sequence. And then, performing the subsequent step of taking each fifth user newly added sequence as a third user newly added sequence.
In the embodiment of the invention, after each fifth user newly added sequence is obtained, elements in the fifth user newly added sequence are randomly changed, so that the randomness of the user newly added sequence is further increased, the problem of local optimization in a short period is further avoided, and the final advertisement putting distribution is more reasonable.
Example 5:
on the basis of the foregoing embodiments, in an embodiment of the present invention, after determining a new sequence of a user, the method further includes:
determining the cost of the user newly-added sequence according to the corresponding relation between the predetermined user newly-added quantity and the user unit price, and determining the income of the user newly-added sequence according to the corresponding relation between the predetermined user newly-added quantity and the user single income;
and when the income of the user newly added sequence is not less than a preset income threshold value, the cost of the user newly added sequence is not more than a preset cost threshold value, and the number of newly added users of the user newly added sequence is not less than a preset user number threshold value, retaining the user newly added sequence, otherwise, deleting the user newly added sequence.
After the electronic equipment determines the user newly added sequence through random change or element exchange every time, firstly, whether the determined user newly added sequence meets the requirement is judged according to a preset limiting condition, if not, the user newly added sequence is deleted, and if so, the user newly added sequence is reserved.
The preset limiting conditions comprise that the profit of the user newly added sequence is not less than a preset profit threshold, the cost of the user newly added sequence is not more than a preset cost threshold, and the number of newly added users of the user newly added sequence is not less than a preset user number threshold. If the three judgments are simultaneously satisfied, the newly added user sequence is considered to satisfy the preset limiting condition, otherwise, the newly added user sequence is considered not to satisfy the preset limiting condition.
Specifically, after the user adding sequence is determined, the cost of the user adding sequence is determined according to the corresponding relation between the predetermined user adding number and the user unit price. And determining the income of the newly added sequence of the user according to the corresponding relation between the predetermined newly added number of the user and the income of the user monomer. And the sum of the newly increased number of each user in the user newly increased sequence is the number of the newly increased users of the user newly increased sequence. After the value is calculated, whether the newly added user sequence meets the preset limiting condition is judged. And if the new sequence is not satisfied, deleting the user new sequence, and if the new sequence is satisfied, reserving the user new sequence.
It should be noted that, if the user new sequence is deleted, in order to ensure the quantity requirement of the user new sequence, the user new sequence corresponding to the previous level of the deleted user new sequence may be determined, and the user new sequence corresponding to the previous level changes to obtain the deleted user new sequence. And then, carrying out random change or element exchange on the user newly-added sequence corresponding to the previous stage to obtain the user newly-added sequence until the obtained user newly-added sequence meets the preset limiting condition. Therefore, the user new sequences meeting the preset limiting conditions are reserved, and the number of the user new sequences is also ensured.
In the embodiment of the invention, after the user newly added sequence is determined, whether the user newly added sequence meets the preset limiting condition is judged. And if the new sequence is not satisfied, deleting the user new sequence, and if the new sequence is satisfied, reserving the user new sequence. Therefore, the problems that convergence is slow due to the existence of the user new sequence which does not meet the preset limiting condition in the iteration process, and the finally obtained target user new sequence is not the optimal user new sequence possibly are solved. And the advertisement putting distribution scheme is further optimized.
Example 6:
on the basis of the foregoing embodiments, in the embodiments of the present invention, the process of predetermining the corresponding relationship between the user newly-added number and the user unit price in each advertisement delivery channel includes:
within a preset second time span, aiming at each advertisement delivery channel, acquiring the number of newly added users and the unit price of the users per day under the advertisement delivery channel; performing curve fitting on the newly increased user number and the user unit price every day, and determining the corresponding relation between the newly increased user number and the user unit price under the advertisement delivery channel;
the process of predetermining the corresponding relationship between the user newly increased number and the user individual profit under each advertisement delivery channel comprises the following steps:
within a preset second time span, aiming at each advertisement delivery channel, acquiring the number of newly added users and the individual user gains of the users under the advertisement delivery channel every day; and performing curve fitting on the newly increased user number and the user individual income every day, and determining the corresponding relation between the newly increased user number and the user individual income under the advertisement delivery channel.
When the electronic equipment determines the corresponding relation between the newly increased number of the users and the unit price of the users under each advertisement delivery channel in advance, the newly increased number of the users and the unit price of the users under the advertisement delivery channel are obtained for each advertisement delivery channel within a preset second time span. The preset second length of time may be the last year, the last 6 months, etc. Specifically, for each advertisement delivery channel, the number of newly added users per day in the advertisement delivery channel can be obtained, and in addition, the user unit price per day can be determined by obtaining the investment cost of the advertisement delivery channel per day and the number of newly added users per day. And then performing curve fitting on the newly increased number of the users and the unit price of the users every day, and determining the corresponding relation between the newly increased number of the users and the unit price of the users under the advertisement delivery channel.
And when the electronic equipment determines the corresponding relation between the newly increased number of the users and the individual user gains under each advertisement delivery channel in advance, acquiring the newly increased number of the users and the individual user gains under the advertisement delivery channel every day aiming at each advertisement delivery channel within a preset second time length. Specifically, for each advertisement delivery channel, the number of newly added users per day under the advertisement delivery channel can be obtained, and in addition, the individual user gains per day can be determined by obtaining the gains obtained by the advertisement delivery channel per day and the number of newly added users per day. And then performing curve fitting on the newly increased number of the users and the individual user gains every day, and determining the corresponding relation between the newly increased number of the users and the individual user gains under the advertisement delivery channel.
The correspondence between the newly added number of users in each advertisement delivery channel and the unit price of the user and the correspondence between the newly added number of users in each advertisement delivery channel and the individual user profit may be a one-dimensional quadratic equation. Each parameter in the unitary quadratic equation is obtained through curve fitting, and the corresponding relation is obtained.
Fig. 2 is a flow chart of advertisement delivery distribution according to an embodiment of the present invention, where firstly, a user presets a limiting condition, and the limiting condition includes a preset profit threshold, a preset cost threshold, and a preset user number threshold DAU. And within a preset second time span, acquiring the newly increased number of users, the unit price of the users and the single user income of each day under each advertisement delivery channel, and determining the corresponding relation between the newly increased number of users and the unit price CPI of the users and the corresponding relation between the newly increased number of users and the single user income LTV of the users under each advertisement delivery channel through curve fitting. Acquiring a first user newly added sequence within a preset first time length, copying the first user newly added sequence to obtain a preset number of second user newly added sequences, and randomly changing elements in each second user newly added sequence to obtain a corresponding third user newly added sequence. Judging whether a preset convergence condition is met, and if not, taking each third user newly added sequence as a second user newly added sequence; if so, taking the user adding sequence corresponding to the maximum return on investment rate ROI as a target user adding sequence; and performing advertisement putting distribution according to the target user newly added sequence. Wherein, the DAU: the Daily Active User means the number of Active users on day, which is represented as the number of newly added users per day in the embodiment of the invention. CPI: average the unit price of the new user per purchase amount. LTV: and the new user brings the benefits such as consumption and recharge to the product on average for each purchase amount. ROI: return on investment, the ratio of value that should be returned by investment, i.e., the ratio of revenue to cost. The purchase quantity means to be promoted in an advertisement putting mode, and the increased number of newly added users using products is increased.
In the embodiment of the invention, the newly increased number of users corresponding to each advertisement delivery channel within the preset first time length is regarded as a first user newly increased sequence, the first user newly increased sequence is copied to obtain a second user newly increased sequence with the preset number, and different second user newly increased sequences are randomly changed. Random variation is largely divided into selection and reproduction, where reproduction includes mating and mutation. The selection is related according to the investment return rate of the user added sequence, and the probability that the user added sequence with higher investment return rate is selected is higher. The user new sequences with gradually larger return on investment are inherited in the iteration, and the user new sequences with gradually smaller return on investment disappear in the iteration process. The selected user added sequence will enter the mating process. In the mating process, the selected new user sequence and the previous new user sequence have certain probability and can exchange respective elements mutually, so that a new user sequence is generated to replace the original 'old' new user sequence. After mating, elements in the new user added sequence are mutated with a certain probability, and the final new user added sequence is generated through mutation. Fig. 3 is a schematic diagram of a variation of a mating sequence provided by An embodiment of the present invention, as shown in fig. 3, a user newly added sequence is [ a1 a2 A3 a4 … … An ], a user newly added sequence is [ B1B 2B 3B 4 … … Bn ], and a user newly added sequence is a sub-user newly added sequence [ a 1B 2 A3B 4 … … Bn ] obtained by mating the user newly added sequence a with the user newly added sequence B. And (3) carrying out mutation on the new sequences of the sub-users to obtain a final new sequence of the user [ A1B 2+ rand () A3-rand () B4 … … Bn ]. The process is similar to the biological reproduction process, and offspring continuously obtain good genes from parents and then achieve the effect of adjustment through changes.
In the iterative process, each user newly-added sequence needs to meet the following constraint conditions to ensure that the optimization direction must meet the requirements.
Condition 1:
condition 2:
condition 3:
Dau_predict(Ins i ) The number of the newly added users in each advertisement delivery channel of the user newly added sequence.Wherein, the user newly adds the number Ins i Will correspondingly influence the user unit price Cpi i And user individual revenue Ltv i Thus affecting the cost and benefit of the user's new sequence, Cpi _ predict (Ins) i ) And Ltv _ predict (Ins) i ) The user unit price and the user unit income are determined according to the corresponding relation between the newly increased user quantity and the user unit price under each advertisement delivery channel and the corresponding relation between the newly increased user quantity and the user unit income under each advertisement delivery channel.
Example 7:
fig. 4 is a schematic structural diagram of an advertisement delivery distribution device provided in an embodiment of the present invention, where the device includes:
an obtaining module 41, configured to obtain a first user adding sequence within a preset first time length, where elements in the first user adding sequence are new user adding quantities corresponding to each advertisement delivery channel;
a first determining module 42, configured to copy the first user adding sequence to obtain a preset number of second user adding sequences, and randomly change elements in the second user adding sequence for each second user adding sequence to obtain a third user adding sequence corresponding to the second user adding sequence;
a second determining module 43, configured to determine, according to a predetermined corresponding relationship between the newly added user number and the unit price of the user in each advertisement delivery channel and a predetermined corresponding relationship between the newly added user number and the individual user revenue, an investment return rate of the newly added user sequence, and determine whether a preset convergence condition is met, if not, take each newly added third user sequence as a second newly added user sequence; if so, taking the user newly-added sequence corresponding to the maximum return on investment as a target user newly-added sequence; and performing advertisement putting distribution according to the target user newly added sequence.
The first determining module 42 is specifically configured to, for each second user addition sequence, randomly change elements in the second user addition sequence to obtain a fourth user addition sequence corresponding to the second user addition sequence; for each fourth user newly-added sequence, exchanging elements of a corresponding channel in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to a preset random probability to obtain a fifth user newly-added sequence corresponding to the fourth user newly-added sequence; and taking each fifth user newly added sequence as a third user newly added sequence.
The device further comprises:
the selecting module 44 is configured to determine, according to the return on investment of each fourth user added sequence, a probability that each fourth user added sequence is selected, where the probability that the fourth user added sequence with the larger return on investment is selected is larger; and selecting preset times in each fourth user newly-added sequence according to the probability of selecting each fourth user newly-added sequence, and triggering the first determining module 42 by adopting the fourth user newly-added sequence selected each time.
The device further comprises:
an updating module 45, configured to randomly change, for each fifth user added sequence, an element in the fifth user added sequence to obtain a sixth user added sequence corresponding to the fifth user added sequence; and updating the fifth user newly added sequence by adopting the sixth user newly added sequence.
The device further comprises:
a deleting module 46, configured to determine a cost of the user new sequence according to a predetermined correspondence between the user new number and the user unit price, and determine a benefit of the user new sequence according to a predetermined correspondence between the user new number and a user single benefit; and when the income of the user newly added sequence is not less than a preset income threshold value, the cost of the user newly added sequence is not more than a preset cost threshold value, and the number of newly added users of the user newly added sequence is not less than a preset user number threshold value, retaining the user newly added sequence, otherwise, deleting the user newly added sequence.
The second determining module 43 is specifically configured to determine whether the iteration number of the second user new sequence reaches a preset number threshold, or determine whether a difference between the maximum return on investment rates determined in two adjacent iterations is smaller than a preset convergence threshold.
The device further comprises:
a third determining module 47, configured to obtain, for each advertisement delivery channel, a user added number and a user unit price per day in a preset second time period; performing curve fitting on the newly increased user number and the user unit price every day, and determining the corresponding relation between the newly increased user number and the user unit price under the advertisement delivery channel;
the third determining module 47 is further configured to, within a preset second time period, obtain, for each advertisement delivery channel, a user newly-added number and a user individual profit for each day of the advertisement delivery channel; and performing curve fitting on the newly increased user number and the user individual income every day, and determining the corresponding relation between the newly increased user number and the user individual income under the advertisement delivery channel.
Example 8:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides an electronic device, as shown in fig. 5, including: the system comprises a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 complete mutual communication through the communication bus 304;
the memory 303 has stored therein a computer program which, when executed by the processor 301, performs the steps of: the method comprises the steps of firstly obtaining a first user newly increased sequence within a preset first time length, obtaining a preset number of second user newly increased sequences through copying, and obtaining a third user newly increased sequence corresponding to the second user newly increased sequence through random variation of elements in each second user newly increased sequence. And taking each third user newly added sequence as a second user newly added sequence, and repeating the random change operation until a preset convergence condition is met. Then, taking the user newly increased sequence corresponding to the maximum return on investment as a target user newly increased sequence; and performing advertisement putting distribution according to the target user newly added sequence.
The electronic device provided by the embodiment of the invention can be used for executing the advertisement putting distribution method provided by any embodiment, and has corresponding functions and beneficial effects.
Example 9:
on the basis of the foregoing embodiments, an embodiment of the present invention further provides a computer storage readable storage medium, in which a computer program executable by an electronic device is stored, and when the program runs on the electronic device, the electronic device is caused to perform the following steps: the method comprises the steps of firstly obtaining a first user newly-added sequence within a preset first time length, obtaining a preset number of second user newly-added sequences through copying, and randomly changing elements in each second user newly-added sequence to obtain a third user newly-added sequence corresponding to the second user newly-added sequence. And taking each third user newly added sequence as a second user newly added sequence, and repeating the random change operation until a preset convergence condition is met. Then, taking the user newly increased sequence corresponding to the maximum return on investment as a target user newly increased sequence; and performing advertisement putting distribution according to the target user newly added sequence.
The computer storage readable storage medium provided by the embodiment of the present invention stores therein a computer program executable by an electronic device, and when the program runs on the electronic device, the computer storage readable storage medium can be used to execute the advertisement delivery distribution method provided by any of the above embodiments, and has corresponding functions and advantages.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
- An advertisement placement distribution method, the method comprising:acquiring a first user newly-increased sequence within a preset first time length, wherein elements in the first user newly-increased sequence are the newly-increased number of users corresponding to each advertisement delivery channel;copying the first user newly added sequence to obtain second user newly added sequences of a preset number, and randomly changing elements in the second user newly added sequences aiming at each second user newly added sequence to obtain third user newly added sequences corresponding to the second user newly added sequences;determining the return on investment of the newly added user sequence according to the corresponding relationship between the newly added user number and the unit price of the user and the corresponding relationship between the newly added user number and the individual user income under each predetermined advertisement delivery channel, judging whether a preset convergence condition is met, and if not, taking each newly added third user sequence as a second newly added user sequence; if so, taking the user newly increased sequence corresponding to the maximum return on investment as a target user newly increased sequence; and performing advertisement putting distribution according to the target user newly added sequence.
- The method of claim 1, wherein the randomly changing the elements in the second user addition sequence for each second user addition sequence to obtain a third user addition sequence corresponding to the second user addition sequence comprises:randomly changing elements in the second user newly-added sequence aiming at each second user newly-added sequence to obtain a fourth user newly-added sequence corresponding to the second user newly-added sequence;aiming at each fourth user newly increased sequence, exchanging elements of a channel corresponding to the fourth user newly increased sequence and the corresponding second user newly increased sequence according to a preset random probability to obtain a fifth user newly increased sequence corresponding to the fourth user newly increased sequence;and taking each fifth user newly added sequence as a third user newly added sequence.
- The method of claim 2, wherein after obtaining the fourth user adding sequence corresponding to the second user adding sequence, before exchanging, for each fourth user adding sequence, elements of a channel corresponding to the fourth user adding sequence and the corresponding second user adding sequence according to a preset random probability, the method further comprises:determining the probability of selecting each fourth user new sequence according to the return on investment of each fourth user new sequence, wherein the probability of selecting the fourth user new sequence with larger return on investment is larger;and selecting preset times in each fourth user newly-added sequence according to the selected probability of each fourth user newly-added sequence, adopting the fourth user newly-added sequence selected each time, and carrying out subsequent steps of exchanging elements of corresponding channels in the fourth user newly-added sequence and the corresponding second user newly-added sequence according to preset random probability aiming at each fourth user newly-added sequence.
- The method of claim 2, wherein after obtaining the fifth user addition sequence corresponding to the fourth user addition sequence, before using each fifth user addition sequence as the third user addition sequence, the method further comprises:randomly changing elements in the fifth user newly increased sequence aiming at each fifth user newly increased sequence to obtain a sixth user newly increased sequence corresponding to the fifth user newly increased sequence; and updating the fifth user newly added sequence by adopting the sixth user newly added sequence.
- The method of any of claims 1 to 4, wherein each time a user-added sequence is determined, the method further comprises:determining the cost of the user newly-added sequence according to the corresponding relation between the predetermined user newly-added quantity and the user unit price, and determining the income of the user newly-added sequence according to the corresponding relation between the predetermined user newly-added quantity and the user single income;and when the income of the user newly added sequence is not less than a preset income threshold value, the cost of the user newly added sequence is not more than a preset cost threshold value, and the number of newly added users of the user newly added sequence is not less than a preset user number threshold value, retaining the user newly added sequence, otherwise, deleting the user newly added sequence.
- The method of claim 1, wherein the determining whether a preset convergence condition is satisfied comprises:and judging whether the iteration times of the second user newly added sequence reach a preset time threshold or not, or judging whether the difference value of the determined maximum return on investment rate in two adjacent iterations is smaller than a preset convergence threshold or not.
- The method of claim 1, wherein the step of predetermining the correspondence between the user's new number and the user's unit price for each advertisement delivery channel comprises:within a preset second time span, aiming at each advertisement delivery channel, acquiring the number of newly added users and the unit price of the users per day under the advertisement delivery channel; performing curve fitting on the newly increased user number and the user unit price every day, and determining the corresponding relation between the newly increased user number and the user unit price under the advertisement delivery channel;the process of predetermining the corresponding relationship between the newly increased number of the users and the individual user profits under each advertisement delivery channel comprises the following steps:within a preset second time span, aiming at each advertisement delivery channel, acquiring the number of newly added users and the individual user gains of the users under the advertisement delivery channel every day; and performing curve fitting on the newly increased user number and the user individual income every day, and determining the corresponding relation between the newly increased user number and the user individual income under the advertisement delivery channel.
- An advertisement placement distribution device, characterized in that the device comprises:the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first user newly increased sequence within a preset first time span, and elements in the first user newly increased sequence are the newly increased number of users corresponding to each advertisement delivery channel;the first determining module is used for copying the first user newly added sequence to obtain a preset number of second user newly added sequences, and randomly changing elements in the second user newly added sequence aiming at each second user newly added sequence to obtain a third user newly added sequence corresponding to the second user newly added sequence;a second determining module, configured to determine, according to a predetermined correspondence between the newly added user number and the unit price of the user in each advertisement delivery channel and a predetermined correspondence between the newly added user number and the individual user revenue, an investment return rate of the newly added user sequence, and determine whether a preset convergence condition is met, and if not, take each newly added third user sequence as a second newly added user sequence; if so, taking the user newly-added sequence corresponding to the maximum return on investment as a target user newly-added sequence; and performing advertisement putting distribution according to the target user newly added sequence.
- The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;a memory for storing a computer program;a processor for implementing the method steps of any one of claims 1 to 7 when executing a program stored in the memory.
- A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/142288 WO2022141456A1 (en) | 2020-12-31 | 2020-12-31 | Advertisement delivery allocation method and apparatus, and electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115066702A true CN115066702A (en) | 2022-09-16 |
Family
ID=82258924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080003840.7A Pending CN115066702A (en) | 2020-12-31 | 2020-12-31 | Advertisement putting distribution method and device, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115066702A (en) |
| WO (1) | WO2022141456A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980477B (en) * | 2010-10-09 | 2013-01-30 | 北京星网锐捷网络技术有限公司 | Method and device for detecting number of shadow users, and network equipment |
| CN102708496B (en) * | 2012-01-09 | 2015-05-20 | 合一网络技术(北京)有限公司 | Adaptive video advertisement release method and device |
| US10803480B2 (en) * | 2019-01-07 | 2020-10-13 | Alphonso Inc. | Bidding agent with optimized reach limitation |
| CN110991875B (en) * | 2019-11-29 | 2023-09-26 | 广州市百果园信息技术有限公司 | Platform user quality evaluation system |
| CN112036963B (en) * | 2020-09-24 | 2023-12-08 | 深圳市万佳安物联科技股份有限公司 | Webpage advertisement putting device and method based on multilayer random hidden feature model |
| CN112150219A (en) * | 2020-10-22 | 2020-12-29 | 广州万唯邑众信息科技有限公司 | Online advertisement delivery system and use method thereof |
-
2020
- 2020-12-31 CN CN202080003840.7A patent/CN115066702A/en active Pending
- 2020-12-31 WO PCT/CN2020/142288 patent/WO2022141456A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022141456A1 (en) | 2022-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11823236B1 (en) | Generating a proposed bid | |
| US20100082442A1 (en) | Demand forecasting system and method for online advertisements | |
| CN106296247B (en) | Network information resource online ordering method and device | |
| US20150134462A1 (en) | Dynamic bid price selection | |
| CN110348908B (en) | Advertisement delivery budget control method and device | |
| US20120303464A1 (en) | Unified yield management for display advertising | |
| Johnson | The impact of privacy policy on the auction market for online display advertising | |
| JP4859825B2 (en) | Advertisement server and advertisement management method | |
| CN111582947A (en) | Coupon processing method and related device | |
| US20150134463A1 (en) | Performance metric based bid placement | |
| CN109087136B (en) | Method and device for adjusting advertisement resource value | |
| WO2020244468A1 (en) | Financial product recommendation method and apparatus, and electronic device and computer storage medium | |
| CN111899041A (en) | Information delivery processing method, information delivery device, information delivery equipment and storage medium | |
| CN108564404B (en) | Method and device for predicting return on investment of advertisement | |
| JP2012503246A (en) | Advertisement providing method and system using bid start price | |
| CN115066702A (en) | Advertisement putting distribution method and device, electronic equipment and storage medium | |
| CN113822722A (en) | Virtual resource distribution control method and device and server | |
| CN111311310A (en) | Advertisement order pushing method and device, storage medium and electronic device | |
| CN111882359B (en) | Advertisement putting method and device | |
| CN113393269A (en) | Method and device for determining conversion rate of contact medium, electronic equipment and storage medium | |
| CN111598631A (en) | Cross-channel keyword price optimization method with effect target oriented | |
| Choi et al. | Optimizing reserve prices in display advertising auctions | |
| CN112418901A (en) | Advertisement inventory control method and device and storage medium | |
| CN117909601B (en) | Payment social matching method, device, equipment and readable storage medium | |
| KR100666202B1 (en) | Method for providing a search service and system for executing the method |
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 |