Advertisement delivery processing method and device

Abstract

The present invention discloses an advertisement delivery processing method and device, and relates to the field of computer technology. A specific implementation of the method includes receiving a basic bid combination, obtaining a marketing combination optimization model, and then calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm; and sending the rounded basic bid combination to a platform to execute an online advertisement delivery program. Thus, the implementation of the present invention can solve the problem that the marketing effect of the online advertisement delivery program executed by the existing platform is poor and the business guarantee cannot be met.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an advertisement delivery processing method and device. Background Art

[0002] When advertisers place online advertisements on online advertising marketing platforms (hereinafter referred to as platforms), they need to select advertising channels (such as search, recommendation, display, etc.), establish advertising plans, and set advertising plan budgets. Multiple advertising units can be set under one plan, and the bid for each advertising unit in each auction is determined by the product of the basic bid and the premium system.

[0003] The platform generally limits the granularity of the basic bid, for example, requiring the basic bid to be an integer multiple of 0.1 yuan. However, the basic bid output by the existing intelligent bidding system generally does not meet the platform granularity requirements. For example, a basic bid of 0.4325 yuan is output. Therefore, the output of the intelligent bidding system is usually rounded (for example, rounding up, rounding down, rounding to the nearest integer (i.e. rounding off)) to meet the granularity requirements of the basic bid.

[0004] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0005] Applying the existing rounding scheme to the basic bid output by the smart bidding system cannot ensure that the constraints of online advertising are still complied with. For example, if the bids of all ad units are rounded up, the final total expenditure may exceed the total budget limit. In addition, the existing rounding scheme does not take into account the impact of bid changes on the overall marketing goals across ad units during the platform's online advertising process. Applying the existing rounding scheme may deteriorate the overall marketing effect. Summary of the invention

[0006] In view of this, the embodiments of the present invention provide an advertisement delivery processing method and device, which can solve the problem that the marketing effect of executing online advertisement delivery programs on existing platforms is poor and business guarantees cannot be met.

[0007] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, there is provided an advertising delivery processing method, including receiving a basic bid combination, obtaining a marketing combination optimization model, and then calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm; and sending the rounded basic bid combination to a platform to execute an online advertising delivery program.

[0008] Optionally, after receiving the basic bid combination, the following steps are included:

[0009] According to the basic bidding combination, the marketing objective function and the business constraint function are obtained to generate a marketing combination optimization model.

[0010] Optionally, according to the basic bidding combination, a preset function interface is called to obtain the marketing objective function and the business constraint function corresponding to the basic bidding combination.

[0011] Optionally, calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm includes:

[0012] According to the basic bid combination and the marketing mix optimization model, the first-order Taylor approximation estimation rounding algorithm is used to calculate the impact of the basic bid of each advertising unit in the basic bid combination on the marketing mix optimization model after rounding;

[0013] A preset planning model is obtained, and the optimal rounded basic bid combination is obtained based on the impact information and outputted.

[0014] Optionally, obtaining a preset planning model and obtaining an optimal rounded basic bid combination based on the impact information includes:

[0015] The mixed integer linear programming solver is called, and the planning model and influence information are used as input to find the optimal rounded basic bid combination.

[0016] Optionally, obtaining a preset planning model and obtaining an optimal rounded basic bid combination based on the impact information includes:

[0017] The impact information is substituted into the planning model, and the heuristic greedy algorithm is used to iteratively solve the problem. In each iteration, one basic bid of an advertising unit in the basic bid combination is selected for rounding, and each rounding minimizes the business constraint function in the marketing mix optimization model until the basic bids of all advertising units are rounded, and the optimal basic bid combination after rounding is obtained.

[0018] Optionally, the planning model is configured as a 0-1 planning model.

[0019] In addition, the present invention also provides an advertising delivery processing device, including an acquisition module for receiving a basic bid combination, acquiring a marketing combination optimization model, and then calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm; a processing module for sending the rounded basic bid combination to a platform to execute an online advertising delivery program.

[0020] One embodiment of the above invention has the following advantages or beneficial effects: the present invention can realize a basic bid rounding that takes into account the business constraints of the entire advertising unit combination, that is, establish a TMM (Touchpoint Mixed Modeling, marketing combination optimization) model, and make an approximate estimate of the marketing effect changes (such as spending, conversion, GMV, etc.) caused by rounding up and down for each advertising unit in the marketing combination based on the first-order Taylor approximation principle; thereby establishing a planning model to obtain an advertising unit combination rounding scheme that maximizes the marketing goal without destroying the business constraints; and, in order to efficiently solve the planning model, a heuristic algorithm scheme or a mixed integer linear programming solver is proposed; thereby, the online advertising delivery of the platform after rounding meets the business constraints, and the impact of rounding on the overall marketing effect is considered globally, so that the deterioration of the marketing effect caused by rounding is controlled. In addition, it is presented in the form of a specific interface, with the input being the basic bid combination and the TMM model, and the output being the basic bid combination after rounding, which is more conducive to efficient calling and security.

[0021] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0023] Figure 1 is a schematic diagram of the main process of the advertisement delivery processing method according to the first embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of the main process of the advertisement delivery processing method according to the second embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of the main process of the advertisement delivery processing method according to the third embodiment of the present invention;

[0026] Figure 4 is a schematic diagram of main modules of an advertisement delivery processing device according to an embodiment of the present invention;

[0027] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0028] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] Figure 1 FIG. 1 is a schematic diagram of the main process of the advertisement delivery processing method according to the first embodiment of the present invention. Figure 1 As shown, the advertisement delivery processing method includes:

[0031] Step S101, receiving a basic bid combination, obtaining a marketing combination optimization model, and then calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm.

[0032] In some embodiments, after receiving the basic bid combination, the method includes: obtaining a marketing objective function and a business constraint function according to the basic bid combination to generate a marketing combination optimization model, namely a TMM (Touchpoint Mixed Modeling, marketing combination optimization) model:

[0033]

[0034] subject to i (x)≥0, for i=1,...,m

[0035] x is the basic bid vector, which represents the basic bid combination, where each dimension represents the basic bid of an ad unit in the marketing combination; f0(x) is the marketing target function, which estimates the marketing target performance corresponding to the basic bid combination x, such as total GMV, total conversion, etc.; f i (x) is the business constraint function, which needs to ensure f i (x)≥0, and i=1,…,m to achieve the business constraints. For example, the total budget constraint can be written as f i (x) = total budget - total expenditure (x) ≥ 0.

[0036] It is worth noting that a function interface is specially provided so that the preset function interface can be called to obtain the marketing objective function and business constraint function corresponding to the basic bidding combination. In addition, the marketing objective function and the business constraint function can also be collectively referred to as an effect function.

[0037] As some other embodiments, the basic bid combination rounding interface is called to obtain the rounded basic bid combination using the first-order Taylor approximation rounding algorithm. The specific implementation process may include: according to the basic bid combination and the marketing combination optimization model, the first-order Taylor approximation rounding algorithm is used to calculate the impact information of the basic bid of each advertising unit in the basic bid combination on the marketing combination optimization model after rounding; then the preset planning model is obtained, and the optimal rounded basic bid combination is obtained based on the impact information and output. It should be noted that the present invention provides a set of basic bids across advertising units, and for any basic bid, two types of rounding are considered: rounding up and rounding down. For example: for rounding of 0.43 yuan, assuming the rounding granularity is 0.1 yuan, then 0.07 yuan can be increased to round up to 0.5 yuan, or 0.03 yuan can be reduced to round down to 0.4 yuan. If there are n advertising units in the marketing mix, the first-order Taylor approximation principle and the solution based on the planning model can be used to achieve an efficient rounding process, from which the solution that meets the business constraints and maximizes the marketing goal can be selected (i.e., the marketing mix optimization model).

[0038] In a further embodiment, the present invention adopts a first-order Taylor approximation prediction rounding algorithm, which can achieve low cost and influence on the marketing objective function and the business constraint function respectively. If the result of rounding the basic bid combination x is expressed as x+Δx, then the influence of the rounding behavior on the effect function (i.e., the marketing objective function or the business constraint function) can be calculated using a first-order Taylor approximation prediction rounding algorithm:

[0039]

[0040] Among them, when i=0, the effect function f i (x) is the marketing objective function, and the effect function f is when i=1,…,m i (x) is the business constraint function. is the effect function f i The gradient of (x), the right side of the equation is the vector inner product, which is the sum of the multiplication of each component of the gradient by each component of Δx, indicating that the impact of the rounding of each ad unit on the final effect change is approximately independent and additive. Therefore, we can pre-calculate the impact of each effect function f when the ad unit j is rounded up or down i (x) Impact information: in, are rounded up or down for ad unit j, and the i-th effect function f i (x) Changes:

[0041]

[0042]

[0043] Where, i = 0, 1, ..., m; j = 1, ..., n; Indicates rounding up; Indicates rounding down.

[0044] Preferably, the planning model is configured as a 0-1 planning model. The specific implementation process includes: obtaining After that, a 0-1 programming model is established to obtain the optimal rounding combination. The 0-1 programming model is as follows:

[0045]

[0046]

[0047] y j ∈{0, 1}, for j=1,...,n.

[0048] The rounding direction decision variable y for ad unit j j is a 0-1 variable. j =1 means that ad unit j should be rounded up; y j =0 indicates that ad unit j should be rounded down.

[0049] In a further embodiment, a mixed integer linear programming solver, i.e., an open source or commercial MILP (Mixed Integer Linear Programming) solver is called, and the planning model and the influence information are used as input to obtain the optimal rounded basic bid combination. Alternatively, the influence information is substituted into the planning model, and a heuristic greedy algorithm is used to iteratively solve the problem.

[0050] Preferably, in the process of iterative solution using a heuristic greedy algorithm, each iteration selects one advertising unit basic bid in the basic bid combination for rounding, and each rounding minimizes the business constraint function in the marketing mix optimization model until all advertising unit basic bids are rounded, thereby obtaining the optimal rounded basic bid combination.

[0051] It should be noted that the constraint with a smaller business constraint function value is described as "tight", and vice versa. The heuristic algorithm of the present invention uses a greedy method to iterate and select one unit for rounding. Each rounding makes the constraint as tight as possible and still holds until all units are rounded. As an embodiment, the specific calculation execution process can be:

[0052] Assuming the initial set Represents the remaining ad units. When calculating the collection for In , all ad units that still hold true even if the constraint is tightened are rounded individually, including: then The advertising units in are rounded separately (both upward and downward), and the advertising unit j and its rounding direction that makes the business constraint function the tightest are found; otherwise There are no ad units and rounding directions that would tighten the constraint and still hold, so Find the ad unit j and its rounding direction whose single rounding behavior can maximize the value of the current tightest constraint business constraint function. Finally, apply the rounding direction to ad unit j, and select Remove ad unit j from .

[0053] Step S102, sending the rounded basic bidding combination to the platform to execute the online advertising delivery procedure.

[0054] In an embodiment, the rounded basic bid combination obtained in step S101 may be sent to the platform, so that the platform may start an online advertising delivery program to conduct bidding marketing based on the rounded basic bid combination.

[0055] In summary, the advertising delivery processing method of the present invention adopts the first-order Taylor approximation principle to quickly estimate the rounding effect; and, a planning model is constructed to optimally solve the rounding, so as to ensure that the marketing objective function is maximized under the premise of the constraints being established; moreover, the present invention adopts a heuristic algorithm for efficiently approximating the solution of the 0-1 planning rounding model of this scenario, which is based on the constraints corresponding to the optimal solution in the optimization model, and is usually tighter than the constraints corresponding to the general solution; at the same time, the present invention is fully adaptable to the marketing combination optimization scenario subject to business constraints, that is, it can achieve the result of maintaining the business constraints of online advertising delivery and controlling the degradation of marketing objectives.

[0056] Figure 2 1 is a schematic diagram of the main process of the advertising delivery processing method according to the second embodiment of the present invention, which is applied to the intelligent bidding system. The advertising delivery processing method may include:

[0057] Get the basic bid combination and the corresponding TMM model, call the basic bid combination rounding interface, take the basic bid combination and the TMM model as input, output the rounded basic bid combination, and then send the rounded basic bid combination to the platform to execute the online advertising program.

[0058] Among them, after calling the basic bid combination rounding interface, the input basic bid combination and TMM model can be used to obtain the impact information of the basic bid of each ad unit in the basic bid combination on the TMM model after rounding, that is, the rounding effect. Then, the optimal rounding combination is obtained through the established 0-1 programming model, and when obtaining the optimal rounding combination, an open source or commercial MILP solver can be used for solution or a heuristic greedy algorithm can be used for iterative solution.

[0059] Figure 3 is a schematic diagram of the main process of the advertisement delivery processing method according to the third embodiment of the present invention. The advertisement delivery processing method may include:

[0060] Step S301, receiving a basic bidding combination and calling a preset function interface.

[0061] Step S302, obtaining the marketing objective function and the business constraint function corresponding to the basic bidding combination, and generating a marketing combination optimization model.

[0062] Step S303, calling the basic bid combination rounding interface.

[0063] Step S304, based on the basic bid combination and the marketing mix optimization model, using a first-order Taylor approximation estimation rounding algorithm, calculate the impact information of the rounded basic bid of each advertising unit in the basic bid combination on the marketing mix optimization model.

[0064] Step S305, calling the 0-1 planning model.

[0065] Step S306, determining whether the number of advertising units in the basic bidding combination is greater than a preset quantity threshold, if so, proceeding to step S307, if not, proceeding to step S308.

[0066] In an embodiment, when the number of advertising units is small, step S307 can be directly used for solving, but when the number of advertising units is large, step S308 can be used to accurately solve and achieve a quick response.

[0067] Step S307, substitute the impact information into the planning model, adopt the heuristic greedy algorithm to iteratively solve, obtain the basic bid combination after rounding, and then proceed to step S309.

[0068] In an embodiment, the heuristic greedy algorithm is used for iterative solution, and one basic bid of an advertising unit in the basic bid combination is selected in each iteration for rounding, and each rounding minimizes the business constraint function in the marketing combination optimization model until all basic bids of advertising units are rounded, and the optimal rounded basic bid combination is obtained.

[0069] Step S308, calling a mixed integer linear programming solver, taking the programming model and the impact information as input, obtaining the optimal rounded basic bid combination, and then proceeding to step S309.

[0070] Step S309, sending the rounded basic bidding combination to the platform to execute the online advertising delivery program.

[0071] Figure 4 is a schematic diagram of the main modules of the advertisement delivery processing device according to an embodiment of the present invention. Figure 4 As shown, the advertising delivery processing device 400 includes an acquisition module 401 and a processing module 402. The acquisition module 401 receives the basic bid combination, obtains the marketing combination optimization model, and then calls the basic bid combination rounding interface to obtain the rounded basic bid combination using the first-order Taylor approximation rounding algorithm; the processing module 402 sends the rounded basic bid combination to the platform to execute the online advertising delivery program.

[0072] In some embodiments, after the acquisition module 401 receives the basic bidding combination, it includes:

[0073] According to the basic bidding combination, the marketing objective function and the business constraint function are obtained to generate a marketing combination optimization model.

[0074] In some embodiments, the acquisition module 401 is further used to:

[0075] According to the basic bidding combination, the preset function interface is called to obtain the marketing objective function and the business constraint function corresponding to the basic bidding combination.

[0076] In some embodiments, the acquisition module 401 calls the basic bid combination rounding interface to obtain the rounded basic bid combination using a first-order Taylor approximation rounding algorithm, including:

[0077] According to the basic bid combination and the marketing mix optimization model, the first-order Taylor approximation estimation rounding algorithm is used to calculate the impact information of the basic bid of each advertising unit in the basic bid combination on the marketing mix optimization model after rounding; obtain the preset planning model, and based on the impact information, obtain the optimal rounded basic bid combination and output it.

[0078] In some embodiments, the acquisition module 401 acquires a preset planning model and obtains an optimal rounded basic bid combination based on the impact information, including:

[0079] The mixed integer linear programming solver is called, and the planning model and influence information are used as input to find the optimal rounded basic bid combination.

[0080] In some embodiments, the acquisition module 401 acquires a preset planning model and obtains an optimal rounded basic bid combination based on the impact information, including:

[0081] The impact information is substituted into the planning model, and the heuristic greedy algorithm is used to iteratively solve the problem. In each iteration, one basic bid of an advertising unit in the basic bid combination is selected for rounding, and each rounding minimizes the business constraint function in the marketing mix optimization model until the basic bids of all advertising units are rounded, and the optimal basic bid combination after rounding is obtained.

[0082] In some embodiments, the planning model is configured as a 0-1 planning model.

[0083] It should be noted that the advertisement delivery processing method and the advertisement delivery processing device of the present invention have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0084] Figure 5 An exemplary system architecture 500 is shown to which the advertisement delivery processing method or advertisement delivery processing device according to the embodiment of the present invention can be applied.

[0085] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0086] The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 501, 502, 503.

[0087] The terminal devices 501, 502, 503 may be various electronic devices having an advertisement delivery processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0088] The server 505 may be a server that provides various services, such as a background management server (only an example) that provides support for users to use the terminal devices 501, 502, and 503. The background management server may analyze and process the received data such as the product information query request, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0089] It should be noted that the advertisement delivery processing method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the computing device is generally disposed in the server 505 .

[0090] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0091] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device 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.

[0092] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0093] The following components are connected to the I / O interface 605: an input section 605 including a keyboard, a mouse, etc.; an output section 606 including a cathode ray tube (CRT), a liquid crystal display processor (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0094] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0095] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0096] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0097] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, it may be described as follows: a processor includes an acquisition module and a processing module. The names of these modules do not, in some cases, limit the modules themselves.

[0098] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes receiving a basic bid combination, obtaining a marketing combination optimization model, and then calling a basic bid combination rounding interface to obtain a rounded basic bid combination using a first-order Taylor approximation rounding algorithm; and sending the rounded basic bid combination to the platform to execute an online advertising delivery program.

[0099] The technical solution according to the embodiment of the present invention can solve the problem that the marketing effect of executing online advertising delivery programs on existing platforms is poor and business guarantees cannot be met.

[0100] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An advertisement delivery processing method, characterized in that: include: Receive the basic bid combination, obtain the marketing objective function and the business constraint function, generate the marketing combination optimization model, and then call the basic bid combination rounding interface to use the first-order Taylor approximate estimation rounding algorithm to obtain the rounded basic bid combination, including: according to the basic bid combination and the marketing combination optimization model, use the first-order Taylor approximate estimation rounding algorithm to calculate the impact information of the basic bid of each advertising unit in the basic bid combination on the marketing combination optimization model after rounding; obtain the preset planning model, and obtain the optimal rounded basic bid combination based on the impact information and output it; The rounded basic bid combination is sent to the platform to execute the online advertising delivery procedure.

2. The method according to claim 1, characterized in that include: According to the basic bidding combination, the preset function interface is called to obtain the marketing objective function and the business constraint function corresponding to the basic bidding combination.

3. The method according to claim 1, characterized in that Obtaining a preset planning model, and seeking an optimal rounded basic bid combination based on the impact information, including: The mixed integer linear programming solver is called, and the planning model and influence information are used as input to find the optimal rounded basic bid combination.

4. The method according to claim 1, characterized in that Obtaining a preset planning model, and seeking an optimal rounded basic bid combination based on the impact information, including: The impact information is substituted into the planning model, and the heuristic greedy algorithm is used to iteratively solve the problem. In each iteration, one basic bid of an advertising unit in the basic bid combination is selected for rounding, and each rounding minimizes the business constraint function in the marketing mix optimization model until the basic bids of all advertising units are rounded, and the optimal basic bid combination after rounding is obtained.

5. The method according to any one of claims 1 to 4, characterized in that: include: The planning model is configured as a 0-1 planning model.

6. An advertisement delivery processing device, characterized in that: include: The acquisition module is used to receive the basic bid combination, obtain the marketing objective function and the business constraint function, generate the marketing combination optimization model, and then call the basic bid combination rounding interface to obtain the rounded basic bid combination using the first-order Taylor approximate estimation rounding algorithm, including: according to the basic bid combination and the marketing combination optimization model, using the first-order Taylor approximate estimation rounding algorithm, calculate the impact information of the basic bid of each advertising unit in the basic bid combination after rounding on the marketing combination optimization model; obtain the preset planning model, and obtain the optimal rounded basic bid combination based on the impact information and output it; The processing module is used to send the rounded basic bidding combination to the platform to execute the online advertising delivery program.

7. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images