Methods, equipment, and media for internet advertising cost control

Abstract

The present invention discloses a method, device and medium for controlling the cost of Internet advertising, including the steps of: S1, obtaining the t-th transaction price and the t-th simulated transaction price; S2, comparing the t-th simulated transaction price and the t-th transaction price to obtain the current error; the t is a positive integer greater than or equal to 1; S3, obtaining the difference of the errors in the last two times and the total sum of the errors; and establishing a feedback adjustment algorithm based on the current error, the difference of the errors in the last two times and the total sum of the errors; S4, adjusting the feedback adjustment algorithm based on the simulated transaction price and the current transaction price. By monitoring the current error, the total sum of the errors and the difference of the last two cost errors, the accuracy of the Internet advertising cost control method is improved, thereby preventing malicious competition during Internet advertising bidding.

Description

Technical Field

[0001] The present technology relates to the field of communication technology, and in particular to a method, device and medium for controlling the cost of Internet advertising dissemination. Background Art

[0002] In the process of Internet advertising, advertisers will formulate advertising strategies and budgets based on business goals, and expect the actual advertising costs to be close to the budget. When the actual advertising costs exceed the budget, it will have a negative effect on the advertising.

[0003] The Internet advertising delivery system is very complex. Due to the special bidding and transaction mechanism, such as multi-party bidding and two-price transactions, the actual transaction price of the advertisement is often not equal to the bid. As a result, the actual delivery cost is often difficult to match the delivery budget initially set by the advertiser.

[0004] A second-price transaction is one in which the second highest price among all the auctioned prices is used as the transaction price. Its purpose is to prevent malicious competition between manufacturers during advertising bidding. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the defect in the prior art that Internet advertising placement is very complicated and the advertising cost cannot be accurately calculated, which leads to malicious competition during advertising auctions, and to provide a method, device and medium for Internet advertising cost control.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] A method for controlling Internet advertising costs, comprising the steps of:

[0008] S1. Obtaining a transaction price sequence, wherein the transaction price sequence includes a number of historical transaction prices arranged in chronological order and a number of simulated transaction prices arranged in chronological order;

[0009] S2, obtaining a first data sequence, a second data sequence and a third data;

[0010] The first data sequence includes a plurality of first data arranged in chronological order, and the t-th first data is the difference between the t-th historical transaction price and the t-th simulated transaction price;

[0011] The second data sequence includes a plurality of second data arranged in time sequence, and the second data at the t+1th time is the difference between the first data at the t+1th time and the first data at the tth time;

[0012] The third data is the sum of the first data;

[0013] Said t is a positive integer;

[0014] S3. Perform negative feedback adjustment on the simulated transaction price using the first data, the second data, and the third data.

[0015] Preferably, the negative feedback adjustment of the simulated transaction price by using the first data, the second data and the third data is performed by a negative feedback algorithm;

[0016] The negative feedback algorithm is

[0017] The err(t) represents the first data;

[0018] Said represents the second data;

[0019] The ∫err(t)dt represents the third data;

[0020] The U(t+1) represents the simulated transaction price at the t+1th time.

[0021] Preferably, when the given value remains unchanged, the K is adjusted according to the difference between the tth simulated transaction price and the t+1th simulated transaction price. p .

[0022] Preferably, the

[0023] Preferably, the T is adjusted according to the size of the first data within the unit number of times. d .

[0024] Preferably, a preset first data is obtained, and when the first data of the t+1th time is smaller than the preset first data, the adjustment of K is stopped. p , the T i And the T d .

[0025] Preferably, the obtaining of the t-th historical transaction price; and the t-th simulated transaction price are performed by simulating the historical transaction price through a statistical regression model.

[0026] Preferably, the statistical regression model is:

[0027] Performing overall standard deviation calculation on all the t-th historical transaction prices and the simulated transaction prices corresponding to the time when the bid price is equal to the t-th historical transaction price;

[0028] Perform a linear fit on the overall standard deviation;

[0029] Establishing a probability model of the historical transaction price;

[0030] The result of the linear fitting and the result of the probability model are added together to obtain the tth simulated transaction price.

[0031] As a second aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for controlling Internet advertising costs when executing the computer program.

[0032] As a second aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned method for controlling Internet advertising costs.

[0033] The positive and progressive effects of the present invention are:

[0034] By using the first data, the second data and the third data, the error of the transaction price simulation for the Internet advertisement is reduced, thereby more accurately predicting the transaction price and preventing malicious competition during the Internet advertisement bidding. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a method for controlling Internet advertising costs according to Embodiment 1 of the present invention.

[0036] Figure 2 The figure is a schematic diagram of the bidding process of the method for controlling the cost of Internet advertising according to the first embodiment of the present invention.

[0037] Figure 3 This is a flow chart of simulating historical transaction prices in the method for controlling Internet advertising costs according to Example 1 of the present invention.

[0038] Figure 4 This is a schematic diagram of the negative feedback algorithm parameter adjustment process of the method for controlling Internet advertising costs in Example 1 of the present invention.

[0039] Figure 5 This is a schematic diagram of the structure of an electronic device according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0040] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0041] Example 1

[0042] See also Figure 1 As shown, this embodiment provides a method for controlling Internet advertising costs. The method includes the following steps:

[0043] S1. Obtain transaction price sequence;

[0044] The transaction price sequence includes a number of historical transaction prices arranged in chronological order and a number of simulated transaction prices arranged in chronological order;

[0045] S2, obtaining a first data sequence, a second data sequence and a third data; the first data sequence includes a plurality of first data arranged in chronological order, and the t-th first data is the difference between the t-th historical transaction price and the t-th simulated transaction price;

[0046] The second data sequence includes a plurality of second data arranged in time sequence, and the t+1th second data is the difference between the t+1th first data and the tth first data;

[0047] The third data is the sum of the first data;

[0048] t is a positive integer;

[0049] S3. Perform negative feedback adjustment on the simulated transaction price using the first data, the second data, and the third data.

[0050] Specifically, the simulated transaction price is negatively feedback-regulated by the first data, the second data, and the third data through a negative feedback algorithm;

[0051] The negative feedback algorithm is

[0052] err(t) represents the first data;

[0053] represents the second data;

[0054] ∫err(t)dt represents the third data;

[0055] U(t+1) represents the t+1th simulated transaction price.

[0056] Specifically, when the given value is constant, K is adjusted according to the first data. p .

[0057] Specifically, according to the given amount, When the historical bid remains unchanged, t approaches infinity, and the limit of the first data is not 0, T i When t approaches infinity, the limit of the first data is 0 and the tth first data does not meet a preset value, T i Become smaller.

[0058] Specifically, T is adjusted according to the size of the first data within the unit number of times. d If the simulated transaction price does not meet the preset first data in the tth time, then d Get bigger.

[0059] Specifically, a preset first data is obtained, and when the first data of the t+1th time is less than the preset first data, the adjustment of K is stopped. p , T i and T d .

[0060] Specifically, the t-th historical transaction price is obtained; and the t-th simulated transaction price is simulated by using a statistical regression model to simulate the historical transaction price.

[0061] Specifically, the statistical regression model is:

[0062] Perform overall standard deviation calculation on all t-th historical transaction prices and the corresponding simulated transaction prices when the bid price is equal to the t-th historical transaction price;

[0063] Perform a linear fit on the overall standard deviation;

[0064] Establishing a probability model of the historical transaction price;

[0065] Add the results of the linear fitting and the probability model together to obtain the tth simulated transaction price.

[0066] In this embodiment, the given value is a value that the output value in the feedback control system infinitely approaches. Specifically in this embodiment, the given value is an approximate transaction price that the simulated transaction price infinitely approaches when the historical transaction price remains unchanged, that is, the transaction price when the first data is 0 when the historical transaction price remains unchanged.

[0067] See also Figure 2 As shown, in this embodiment, there are n advertisers bidding for the ad space. If advertiser 2 wins, the transaction price of advertiser 2 is the second highest price. The purpose of the second-price transaction is to avoid malicious competition among advertisers.

[0068] See also Figure 3 As shown, in this embodiment,

[0069] Schematic diagram of the process of simulating historical transaction prices in Example 1 of the present invention.

[0070] The linear fitting parameters are as follows:

[0071] y l =ax+b

[0072] Among them, y l is the average transaction price when the bid is equal to x, a is the parameter term of the linear function to be determined, and b is the bias term.

[0073] The formula for calculating the population standard deviation is as follows:

[0074]

[0075] Among them, x (t) is the t-th historical transaction price; y l (x (t) ) is the bid price equal to x (t) The corresponding simulated transaction price; is the average of t transaction prices, and m is the number of training sets.

[0076] Since Internet advertising uses a multi-party bidding and two-price transaction mechanism, when the bids are the same, the transaction price will still fluctuate randomly with a certain probability distribution. Therefore, through statistical analysis of historical transaction prices, a probability model between transaction prices and random disturbance items is established:

[0077] P(y r )=P(x (i) |θ)

[0078] Among them, P(y r ) means when the bid is x (t) When , the probability distribution of the disturbance term is, where θ can be obtained by the maximum likelihood estimation method.

[0079]

[0080] The final simulated transaction price formula can be given by the following formula:

[0081] y=y l +y r

[0082] See also Figure 4 As shown,

[0083] In this embodiment, the t-th simulated transaction price is brought into the feedback algorithm, and the t+1-th simulated transaction price is calculated. The t+1-th simulated transaction price is compared with the t+1-th transaction price, thereby obtaining a first data. When the first data satisfies a preset first data, the feedback algorithm adjustment ends; when it does not satisfy the preset first data, the various parameters in the feedback algorithm will continue to be adjusted. Specifically, in this feedback algorithm, that is, in the following feedback algorithm:

[0084]

[0085] The parameters that need to be adjusted are: K p , and T d .

[0086] Example 2

[0087] Figure 5This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the method for controlling the cost of Internet advertising in embodiment 1 is implemented when the processor executes the program. Figure 5 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0088] like Figure 5 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0089] The bus 33 includes a data bus, an address bus, and a control bus.

[0090] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0091] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0092] The processor 31 executes various functional applications and data processing by running the computer programs stored in the memory 32, such as the method for controlling the cost of Internet advertising in Example 1 of the present invention.

[0093] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model-generated device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via a bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0094] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0095] Example 3

[0096] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the method for controlling the cost of Internet advertising in Embodiment 1 are implemented.

[0097] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0098] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the method for controlling Internet advertising costs in Example 1.

[0099] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0100] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for controlling Internet advertising costs, characterized in that: Includes steps: S1. Obtaining a transaction price sequence, wherein the transaction price sequence includes a number of historical transaction prices arranged in chronological order and a number of simulated transaction prices arranged in chronological order; Obtain the t-th historical transaction price; and simulate the t-th simulated transaction price by using a statistical regression model to simulate the historical transaction price; the statistical regression model is: perform overall standard deviation calculation on all t-th historical transaction prices and the simulated transaction price corresponding to the bid price equal to the t-th historical transaction price; perform linear fitting on the overall standard deviation; establish a probability model for the historical transaction price; add the result of the linear fitting and the result of the probability model to obtain the t-th simulated transaction price; S2, obtaining a first data sequence, a second data sequence and a third data; The first data sequence includes a plurality of first data arranged in chronological order, and the t-th first data is the difference between the t-th historical transaction price and the t-th simulated transaction price; The second data sequence includes a plurality of second data arranged in time sequence, and the second data at the t+1th time is the difference between the first data at the t+1th time and the first data at the tth time; The third data is the sum of the first data; Said t is a positive integer; S3, performing negative feedback adjustment on the simulated transaction price by using the first data, the second data and the third data through a negative feedback algorithm; The negative feedback algorithm is The err(t) represents the first data; Said represents the second data; The ∫err(t)dt represents the third data; The U(t+1) represents the simulated transaction price for the t+1th time; Obtain a preset first data, and stop adjusting the K when the first data of the t+1th time is less than the preset first data p , the T i And the T d .

2. The method for controlling Internet advertising costs according to claim 1, characterized in that: When the given amount remains unchanged, the K is adjusted according to the difference between the tth simulated transaction price and the t+1th simulated transaction price. p .

3. The method for controlling Internet advertising costs according to claim 1, characterized in that: Adjust the 4. The method for controlling Internet advertising costs according to claim 1, characterized in that: The T is adjusted according to the size of the first data within the unit number of times. d .

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for controlling Internet advertising costs according to any one of claims 1 to 4 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for controlling Internet advertising costs as claimed in any one of claims 1 to 4 is implemented.

Images