Marketing optimization device, system, method and program

Abstract

An input means 81 receives an input of numerical information in which conditions, effects, and costs are associated with one another. An effect suppression designating means 82 receives designation of a tactic for suppressing the influence of an effect. A coefficient calculation means 83 calculates a first coefficient for a cost function representing an effect of the tactic and a second coefficient for a cost function representing a cost for the tactic by using a reduction process of reducing a value, which represents the effect corresponding to the designated tactic, among the numerical information. An object function defining means 84 defines, through combinations of the conditions and by using the first and second coefficients, an energy function, as an object function, which defines a relationship where: the greater the effect increases, the more the value decreases; and the more the cost increases, the more the value increases. An optimization process execution means 85 causes a quantum computer to execute an optimization process of transmitting the defined object function to minimize the value of the object function.

Description

[Technical Field]

[0001] The present disclosure relates to a marketing optimization device, a marketing optimization system, a marketing optimization method, and a marketing optimization program that optimize marketing strategies. [Background technology]

[0002] In order to increase the effectiveness of advertising in web marketing, it is necessary to use the appropriate media and the right type of advertising to target the right people.

[0003] For example, Patent Document 1 describes an advertisement distribution device that distributes advertisements so that a brand is recognized by more viewers. The advertisement distribution device described in Patent Document 1 calculates the expected number of times that multiple viewers will view an advertisement and the number of viewers whose expected value is equal to or greater than a threshold, and determines the number of advertisements to distribute to multiple programs so as to increase the number of viewers whose expected value is equal to or greater than the threshold within a specified budget. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-9558 Summary of the Invention [Problem to be solved by the invention]

[0005] The advertisement distribution device described in Patent Document 1 aims to distribute advertisements efficiently by focusing on the number of views, but does not take into consideration the target audience for brand recognition. Therefore, it is difficult to say that the advertisement distribution device described in Patent Document 1 is necessarily able to market to the target audience.

[0006] Therefore, an object of the present disclosure is to provide a marketing optimization device, a marketing optimization system, a marketing optimization method, and a marketing optimization program that can derive optimal marketing measures to be taken for a target. [Means for solving the problem]

[0007] The marketing optimization device according to the present disclosure is characterized by comprising: input means for receiving input of numerical information that associates conditions, effects, and costs of marketing actions, the numerical information being generated based on performance data that associates the conditions of the actions with the effects achieved by the actions and the costs required for the actions; effect suppression designation means for receiving designation of an action that suppresses the influence of the effects; coefficient calculation means for performing a reduction process to reduce a value indicating the effect corresponding to the designated action among the numerical information, and calculating a first coefficient, which is the coefficient of a cost function indicating the effect of the action, and a second coefficient, which is the coefficient of a cost function indicating the cost of the action, using both the numerical information that has been reduced and the numerical information that has not been reduced; objective function definition means for defining, using the first coefficient and the second coefficient, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of conditions; optimization process execution means for transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process that minimizes the value of the objective function; and output means for outputting the results of the optimization process.

[0008] The marketing optimization system according to the present disclosure includes a quantum computer that executes an optimization process for a transmitted objective function, and a marketing optimization device connected to the quantum computer. The marketing optimization device includes: input means for accepting input of numerical information that associates conditions, effects, and costs for marketing actions, the numerical information being generated based on performance data that associates the conditions for the actions with the effects achieved by the actions and the costs required for the actions; effect suppression designation means for accepting designation of actions that suppress the influence of the effects; coefficient calculation means for performing a reduction process to reduce a value indicating the effect corresponding to the designated action among the numerical information, and calculating a first coefficient, which is the coefficient of a cost function indicating the effect of the action, and a second coefficient, which is the coefficient of a cost function indicating the cost of the action, using both the numerical information that has been reduced and the numerical information that has not been reduced; objective function definition means for using the first coefficient and the second coefficient to define as the objective function an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of conditions; optimization process execution means for transmitting the defined objective function to the quantum computer and causing it to execute an optimization process that minimizes the value of the objective function; and output means for outputting the results of the optimization process.

[0009] The marketing optimization method according to the present disclosure is characterized in that it accepts input of numerical information that associates conditions, effects, and costs of marketing actions, the numerical information being generated based on performance data that associates the conditions of the marketing actions with the effects achieved by the actions and the costs required for the actions; it accepts the specification of an action that will suppress the influence of the effects; it performs a reduction process to reduce the value of the numerical information that indicates the effect corresponding to the specified action; it calculates a first coefficient, which is the coefficient of a cost function that indicates the effect of the action, and a second coefficient, which is the coefficient of a cost function that indicates the cost of the action, using both the numerical information that has been reduced and the numerical information that has not been reduced; it defines, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of conditions, it sends the defined objective function to a quantum computer, and causes it to execute an optimization process that minimizes the value of the objective function; and it outputs the results of the optimization process.

[0010] The marketing optimization program according to the present disclosure has a computer that executes an input process that accepts input of numerical information that associates conditions, effects, and costs of marketing actions, the numerical information being generated based on performance data that associates the conditions of the actions with the effects achieved by the actions and the costs required for the actions; an effect suppression designation process that accepts the designation of an action that suppresses the influence of the effects; a coefficient calculation process that performs a reduction process that reduces a value of the numerical information that indicates the effect corresponding to the designated action, and calculates a first coefficient, which is the coefficient of a cost function that indicates the effect of the action, and a second coefficient, which is the coefficient of a cost function that indicates the cost of the action, using both the numerical information that has been reduced and the numerical information that has not been reduced; an objective function definition process that uses the first coefficient and the second coefficient to define, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of conditions; an optimization process execution process that transmits the defined objective function to a quantum computer and causes the quantum computer to execute an optimization process that minimizes the value of the objective function; and an output process that outputs the results of the optimization process. [Effects of the Invention]

[0011] According to the present disclosure, it is possible to derive the optimal marketing strategy to be implemented for the target. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram illustrating a configuration example of an embodiment of a marketing optimization system according to the present disclosure. [Figure 2] FIG. 10 is an explanatory diagram showing an example of performance data. [Figure 3] FIG. 10 is an explanatory diagram showing an example of defined conditions. [Figure 4] FIG. 10 is an explanatory diagram showing an example of a screen for accepting designation of conditions for a target advertisement; [Figure 5] FIG. 10 is an explanatory diagram showing an example of an energy function. [Figure 6] 10 is a flowchart illustrating an example of the operation of the marketing optimization system. [Figure 7] 1 is a block diagram illustrating an overview of a marketing optimization device according to the present disclosure. [Figure 8] FIG. 1 is a block diagram illustrating an overview of a marketing optimization system according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0014] 1 is a block diagram showing an example configuration of an embodiment of a marketing optimization system according to the present disclosure. The marketing optimization system 100 of this embodiment includes a marketing optimization device 10 and a quantum computer 20. The marketing optimization device 10 is mutually connected to the quantum computer 20 via a communication line.

[0015] The marketing optimization system 100 is a system that derives the optimal action to be taken for a subject (hereinafter sometimes referred to as a target). Here, an action is an activity carried out for a target, such as advertising or market research. In this embodiment, a specific example of an action is an advertisement to a target.

[0016] That is, the marketing optimization system 100 of this embodiment aims to derive the optimal combination of targets to which advertising should be delivered (hereinafter sometimes referred to as advertising targets) and the type of advertising to be used when delivering advertising to those advertising targets (hereinafter sometimes referred to as advertising types). This is because deriving the optimal combination can prevent ineffective and wasteful advertising from being delivered. Hereinafter, each element included in the combination may be referred to as a condition.

[0017] Examples of advertising types include listing ads, display ads, and email ads (email newsletters). These advertising types are further subdivided depending on the advertising media in which they are displayed. Advertising targets are classified according to criteria such as gender, age, hobbies / interests, family structure, and place of residence. The above-described classifications of advertising types and advertising targets are merely examples, and other types of advertising and classifications may also be used.

[0018] Furthermore, the marketing optimization system 100 of this embodiment utilizes a quantum computer 20 to select the optimal combination of conditions with the highest cost-effectiveness from among a vast number of conditions, thereby making it possible to derive an optimal solution within a realistic time frame.

[0019] The quantum computer 20 is a computer that realizes parallel computation using quantum mechanical phenomena and is a device that performs optimization processing of an objective function transmitted from another device. For example, a quantum annealing quantum computer (hereinafter referred to as a quantum annealing machine) is a dedicated device that calculates the ground state of the Hamiltonian of an Ising model and performs annealing based on the Ising model. More specifically, the quantum annealing machine is a device that probabilistically calculates the value of a binary variable that minimizes or maximizes the objective function (i.e., Hamiltonian) of an Ising model that takes binary variables as arguments.

[0020] The quantum computer 20 of this embodiment may take any form. The quantum computer 20 may be configured with any hardware that probabilistically determines the value of a binary variable that minimizes or maximizes an objective function that takes binary variables as arguments. The quantum computer 20 may be, for example, a non-von Neumann computer in which the objective function is implemented by hardware in the form of an Ising model. Furthermore, the quantum computer 20 may be a quantum annealing machine or a general annealing machine.

[0021] The marketing optimization device 10 includes a memory unit 11, a numerical information generation unit 12, an input unit 13, an effect suppression designation unit 14, a coefficient calculation unit 15, an objective function definition unit 16, an optimization process execution unit 17, and an output unit 18.

[0022] The storage unit 11 stores various types of information used for processing by the marketing optimization device 10. The storage unit 11 of this embodiment stores data (hereinafter referred to as performance data) that associates, for each advertisement that has been made in the past, conditions including the advertisement type and the advertisement target targeted by that advertisement, the cost required for that advertisement, and the effect obtained by that advertisement.

[0023] The storage unit 11 may also store information about incentives set for target actions (advertisements) as measures (hereinafter, also referred to as incentive measures). The storage unit 11 is realized by, for example, a magnetic disk or the like.

[0024] 2 is an explanatory diagram showing an example of performance data and an incentive measure list, in which a list of advertisements placed on the web (web advertisement list) is shown as an example of performance data.

[0025] The example of a web ad list shown in Figure 2 indicates that display ads and interest-based ads using multiple media were selected as the ad type, and that multiple ads have been run in the past. The example shown in Figure 2 also indicates that gender, interest range, etc. were used as ad targeting criteria. Furthermore, the example shown in Figure 2 indicates that the number of impressions, number of sessions, etc. are tallied as effects.

[0026] In this embodiment, a case will be described in which advertisements for one project and one advertising type are treated as one advertisement. In the example shown in FIG. 2, a combination of each campaign and each advertising type is treated as one advertisement. For example, in a web advertising list, three items with the campaign name "Light Mountain Climbing Stamp Rally" and the advertising type "Display Advertising" correspond to one advertisement. Note that one advertisement may also be referred to as one move. Therefore, the total values ​​of the costs and effects of each move in each media are treated as the costs and effects of each advertisement.

[0027] The performance data illustrated in FIG. 2 is merely an example, and advertisements made by other methods may be associated with the costs and effects of the advertisements.

[0028] The numerical information generating unit 12 generates numerical information that associates the conditions of the action (specifically, the conditions under which the advertisement was placed) with the effect and cost of the action (specifically, the advertisement) based on the performance data. Note that in this embodiment, an example is shown in which the number of sessions is used as the effect. However, the aggregate value used as the effect is not limited to the number of sessions.

[0029] The method of calculating the costs and effects is arbitrary. For example, the numerical information generating unit 12 may calculate the costs by adding the time required to advertise, in addition to the cost of the advertisement itself, converted into costs based on hourly labor costs. Furthermore, if an incentive is applied, the numerical information generating unit 12 may calculate the costs by adding the amount of the reward.

[0030] As shown in the above process, the numerical information generating unit 12 calculates the effectiveness and cost of each advertisement.

[0031] Next, the numerical information generation unit 12 quantifies the conditions of the move (specifically, the conditions satisfied by the advertisement). Specifically, the numerical information generation unit 12 generates numerical information by quantifying each condition of the move indicated by the performance data using one bit or a string of multiple bits. Note that the conditions in the performance data to be quantified may be determined in advance. Figure 3 is an explanatory diagram showing an example of defined conditions. The example shown in Figure 3 shows that the conditions satisfied by the advertisement are quantified using a 50-bit binary variable, and the conditions satisfied by the advertisement are represented by one bit or a string of multiple bits.

[0032] Fig. 3 illustrates two cases: one where whether a predetermined condition is satisfied is represented by 1 (satisfied) or 0 (not satisfied), and one where the content of the condition is represented by multiple bit strings. In the example shown in Fig. 3, the bit string from bit 1 to bit 3 represents the content of one of six types of advertisement, and each bit from bit 4 to bit 8 represents the use or non-use of each medium by 1 or 0. Note that the advertisement types from bit 1 to bit 3 are controlled based on constraints so that undefined bit strings are not selected.

[0033] The following is a specific explanation of the digitization process for the first advertisement shown in Figure 2. The first advertisement shown in Figure 2 uses a display advertisement. Among the conditions shown in Figure 3, advertisement type {3} expresses the advertisement type condition with three variables (3 bits), x1 to x3. The numerical values ​​0 to 5 assigned to each advertisement type are converted to binary notation, and the variables are assigned in the order of (x3, x2, x1). 0 (000): PPC 1(001):Display advertising 2(010):Retargeting ads 3(011):Interest Advertising 4(100): Dynamic Ads 5(101):Email advertising (mail magazine)

[0034] According to the above definitions, x1=1, x2=0, and x3=0 are set.

[0035] Similarly, the first advertisement shown in Figure 2 uses media 1 to 3. Among the conditions shown in Figure 3, advertising media {5} uses five variables x4 to x8 to represent the media conditions. Each variable x n is set to 0 (not in use) or 1 (in use). As shown in Figure 3, each media variable corresponds to the following media. 0th bit (=x4): Media 1 1st bit (=x5): Media 2 2nd bit (=x6): Media 3 3rd bit (=x7): Media 4 4th bit (=x8): Media 5

[0036] According to the above definitions, x4=1, x5=1, x6=1, x7=0, and x8=0 are set. The same applies to other conditions. As described above, since the bit strings 6 (110) and 7 (111) are undefined in the advertisement type, they are controlled based on constraints so that they are not selected. In the case of a condition that allows only one of a condition to be selected, for example, a one-hot constraint may be set.

[0037] The numerical information generating unit 12 stores the generated numerical information in the storage unit 11.

[0038] The input unit 13 receives the input of the above-mentioned numerical information. The input unit 13 may receive the input of the numerical information by reading it from the storage unit 11, or may receive the input of the numerical information directly from the numerical information generation unit 12.

[0039] The effect suppression designation unit 14 receives a designation to suppress the effect of a move (specifically, an advertisement) in optimization, which will be described later. Specifically, the effect suppression designation unit 14 receives a designation of a move (advertisement) whose influence is to be suppressed in optimization. Note that the degree to which the effect is to be suppressed may be predetermined, and the effect suppression designation unit 14 may receive a designation of the desired degree of suppression.

[0040] For example, suppose there is performance data for Advertisement A targeting people whose hobby is skiing. However, if you try to advertise in August, Advertisement A targeting people whose hobby is skiing will be less effective. In other words, if you try to advertise in August, it is preferable to be able to suppress and optimize the impact of the effect obtained from Advertisement A.

[0041] Therefore, in this embodiment, the effect suppression designation unit 14 accepts designation of advertisements for which the influence of the effect is to be suppressed. As a result, in optimization by the optimization process execution unit 17 (to be described later), the optimal marketing measures to be taken for the target can be derived according to the advertisement content.

[0042] The effect suppression designation unit 14 may directly receive designation of advertisements from a user. Alternatively, the relationship between the content of an advertisement and the advertisement to be suppressed may be determined in advance according to the time period and the target demographic, and the effect suppression designation unit 14 may automatically determine the advertisement to be suppressed based on the content of the advertisement.

[0043] Furthermore, to improve user interpretability, the effect suppression designation unit 14 may accept the designation of conditions indicating the target of the action (advertisement). In this case, the effect suppression designation unit 14 may determine that an action including conditions different from the designated conditions is an action that suppresses the influence of the effect. Here, different conditions refer to contradictory conditions, and for example, a correspondence relationship is defined in advance by an administrator or the like. Also, different conditions can be said to be conditions that designate non-target (non-target) advertising targets.

[0044] Fig. 4 is an explanatory diagram showing an example of a screen for accepting the specification of conditions for a target advertisement target. Since the conditions for a target advertisement target are specified on the screen shown in Fig. 4, the effect suppression specification unit 14 determines that an advertisement including conditions different from the specified conditions is an advertisement for which the influence of the effect should be suppressed.

[0045] For example, if "August" is specified as the target month, advertisements that were aired in "January" or advertisements that target people whose hobby is skiing are considered inappropriate. Therefore, advertisements for which the influence of the effect should be suppressed may be determined in advance for the specified conditions, and the effect suppression specification unit 14 may determine the advertisements for which the influence of the effect should be suppressed based on the specified conditions.

[0046] Specific examples of suppression are explained below. As a first specific example, there is a case where a target month is specified. In this case, the effect suppression specifying unit 14 may determine that a move that is not suitable for the specified month has been specified as a specification for suppressing the influence of the effect. This makes it easier to select a combination of conditions that is suitable for the specified month. Examples of an inappropriate move include a different month, a different season, etc.

[0047] As a second specific example, the performance data may be categorized in advance by content type and compared with the category of the specified play. In this case, the effect suppression designation unit 14 may determine the category of the specified play and determine that non-target content (content of a different category) has been designated as a designation for suppressing the influence of the effect. This makes it easier to select similar conditions for similar content.

[0048] For example, suppose that the advertisement content is about "city running" and you want to advertise it as one of the "activity" categories. In this case, the effect suppression designation unit 14 determines that a content category other than "activity" has been designated as a designation to suppress the influence of the effect.

[0049] As a third specific example, the attribute of the target user is specified. In this case, the effect suppression specifying unit 14 may determine that a move that is not suitable for the attribute of the specified user is specified as a specification for suppressing the influence of the effect. This makes it easier to select a combination of conditions that is suitable for a user with the specified attribute.

[0050] For example, suppose the advertisement content is "about a cosmetic product as a souvenir" and is recommended especially for women. In this case, the effect suppression designation unit 14 determines that a target user attribute other than "women only" has been designated as a designation to suppress the influence of the effect.

[0051] As a fourth specific example, the performance data may be categorized in advance according to the product status of the content (for example, new, updated, revived, recognized, etc.) and compared with the product status of the content of the designated player. In this case, the effect suppression designation unit 14 may determine the product status of the content of the designated player and determine that an out-of-target situation (a different situation) has been designated as a designation to suppress the influence of the effect. This makes it easier to select similar conditions for similar situations.

[0052] For example, suppose the advertisement content is new and unknown to the public, and you want people to know about it first. In this case, the effect suppression designation unit 14 determines that the content status is a measure other than "awareness" to suppress the effect.

[0053] The specific examples of suppression shown above may be implemented individually or in combination. Furthermore, various suppression specifications other than the specific examples of suppression shown above may be implemented.

[0054] For example, as a combination of the second and fourth specific examples, assume that the advertising content is "notifying people that applications for the agricultural experience campaign that was recently advertised" and that the advertiser wants people to apply. In this case, the effect suppression designation unit 14 determines that the content category is "experience" and the content status is a measure other than "purchase" as a designation to suppress the influence of the effect.

[0055] Based on the above numerical information, the coefficient calculation unit 15 calculates a coefficient (hereinafter referred to as a first coefficient) of a cost function (hereinafter referred to as a first cost function) indicating the effect of a move and a coefficient (hereinafter referred to as a second coefficient) of a cost function (hereinafter referred to as a second cost function) indicating the cost. In this embodiment, it is assumed that the effect and cost are determined by a combination of quantified conditions. Therefore, the coefficient calculation unit 15 defines a cost function in which the conditions of the move (more specifically, the conditions of the quantified performance data) are used as explanatory variables, and the effect and cost of the move are used as objective variables, respectively.

[0056] In this embodiment, the cost function indicating the effect of a move is a cost function that formulates the effect obtained depending on the content of the conditions satisfied by the move, and the cost function indicating the cost of a move is a cost function that formulates the cost incurred depending on the content of the conditions satisfied by the move. These cost functions are linear models formulated based on the above-mentioned numerical information (specifically, performance data).

[0057] For example, the cost function of the dth effect is y sd , the cost of the dth expense is calculated as function y cd If the advertisement is quantified using a 50-bit variable as shown in Figure 3, the cost function y s1 and the cost function y of the first cost c1 can be defined by the following formulas 1 and 2. d,n represents the nth variable when the data index is d.

[0058] y s1 =q s0 +q s1 x 1,1 +···+q s49,50 x 1,49 x 1,50 (Formula 1) y c1 =q c0 +q c1 x 1,1 +···+q c49,50 x 1,49 x 1,50 (Formula 2)

[0059] When formulas 1 and 2 are expressed as vectors, they are expressed as formulas 3 and 4 shown below. Qs in formula 3 corresponds to the first coefficient, and Qc in formula 4 corresponds to the second coefficient.

[0060]

number

[0061] The cost function defined in this way is x1 (vector) as explanatory variable, y s1 and y c1 This corresponds to a linear model with the objective variable.

[0062] The coefficient calculation unit 15 calculates the coefficient of the first cost function (i.e., the first coefficient) and the coefficient of the second cost function (i.e., the second coefficient) defined in this manner. Here, in this embodiment, the coefficient calculation unit 15 performs a process of decreasing the value indicating the effectiveness corresponding to the advertisement designated to suppress the effectiveness among the above-mentioned numerical information (hereinafter referred to as a decrease process). Specifically, the coefficient calculation unit 15 performs a process of multiplying the value indicating the effectiveness of the designated advertisement by a positive number less than 1. Note that the positive number to be multiplied may be a predetermined number such as 0.01.

[0063] The coefficient calculation unit 15 calculates a coefficient Qs of the first cost function and a coefficient Qc of the second cost function using both the numerical information that has been subjected to the reduction process and the numerical information that has not been subjected to the reduction process. Note that any method for calculating the coefficients of the cost functions may be used. The coefficient calculation unit 15 may calculate the coefficients using, for example, the least squares method.

[0064] A specific example of a method for calculating the coefficients of the first cost function (i.e., the cost function indicating the effect) will be described below. In this embodiment, the goal is to find Qs so that the following formula 5 holds true as much as possible for each piece of performance data. Note that d is an index of the performance data.

[0065]

number

[0066] In this case, it is sufficient to calculate Qs such that the difference between the right-hand side and the left-hand side of Equation 5 is as small as possible, so the coefficient calculation unit 15 may calculate Qs as shown in the following Equation 6. The coefficients of the second cost function can be calculated in the same manner.

[0067]

number

[0068] The objective function definition unit 16 uses the calculated coefficient Qs of the first cost function and the coefficient Qc of the second cost function to define an objective function (Hamiltonian) that the quantum computer 20 uses in the optimization process.

[0069] In this embodiment, each condition of the move is x i Since it is treated as a binary value ∈{0,1}, it is possible to obtain high effectiveness at low cost. i As a problem for obtaining the combination, consider the problem of minimizing the energy function E(x) shown in the following equation 7.

[0070]

number

[0071] On the other hand, to solve the above problem using the quantum computer 20, the above problem needs to be expressed in the form of an energy function H(x) (objective function) (QUBO (Quadratic Unconstrained Binary Optimization)) as exemplified in the following equation 8.

[0072]

number

[0073] In this embodiment, Q={q ij} is the interaction term for each condition (an upper triangular matrix with all zeros in the lower left), and we consider the interaction terms Qs and Qc for the effect (number of sessions) and cost, respectively. Then, we define the energy function for the effect as H session (x,Qs), and the energy function related to the cost is H cost Given (x, Qc), the problem becomes one of minimizing the energy function shown in the following equation 9 (λ is a weighting coefficient).

[0074]

number

[0075] That is, the energy function shown in Equation 9 is an objective function defined using the first coefficient and the second coefficient, and can be said to be an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases depending on the combination of conditions. Note that, depending on the necessary constraints, a term representing a constraint (such as a one-hot constraint or a constraint that suppresses the output of undefined bit strings) may be further added to Equation 9.

[0076] Fig. 5 is an explanatory diagram showing an example of an energy function. The energy function shown in Fig. 5 is an example of an energy function (Hamiltonian) set when the conditions shown in Fig. 3 are defined. By including necessary constraints in the energy function other than the term in Equation 9 shown above, it becomes possible to obtain a more appropriate optimal solution.

[0077] The optimization process execution unit 17 transmits the defined objective function (Hamiltonian) to the quantum computer 20, causing it to execute an optimization process to derive an optimal combination of play conditions. Note that, since the method of causing a quantum computer to execute an optimization process based on an objective function (Hamiltonian) is widely known, a detailed description thereof will be omitted here.

[0078] The output unit 18 outputs the result of the optimization process performed by the quantum computer 20. The method for outputting the result is arbitrary. For example, the output unit 18 may output the obtained combination of advertisement conditions in association with the name of each condition.

[0079] The numerical information generation unit 12, input unit 13, effect suppression designation unit 14, coefficient calculation unit 15, objective function definition unit 16, optimization process execution unit 17, and output unit 18 are realized by a computer processor (e.g., a CPU (Central Processing Unit)) that operates according to a program (marketing optimization program).

[0080] For example, the program may be stored in the memory unit 11 of the marketing optimization device 10, and the processor may read the program and, in accordance with the program, operate as the numerical information generation unit 12, input unit 13, effect suppression designation unit 14, coefficient calculation unit 15, objective function definition unit 16, optimization process execution unit 17, and output unit 18. Furthermore, the functions of the marketing optimization device 10 may be provided in the form of SaaS (Software as a Service).

[0081] Furthermore, the numerical information generation unit 12, input unit 13, effect suppression specification unit 14, coefficient calculation unit 15, objective function definition unit 16, optimization process execution unit 17, and output unit 18 may each be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program.

[0082] Furthermore, when some or all of the components of the marketing optimization device 10 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each device is connected via a communication network.

[0083] Next, a description will be given of the operation of the marketing optimization system 100 of this embodiment. Fig. 6 is a flowchart showing an example of the operation of the marketing optimization system 100 of this embodiment.

[0084] The input unit 13 accepts input of numerical information generated based on performance data (step S11). The effect suppression designation unit 14 accepts designation of a play move for suppressing the influence of an effect (step S12). The coefficient calculation unit 15 performs a reduction process to reduce the value indicating the effect corresponding to the designated play move among the numerical information (step S13). Then, the coefficient calculation unit 15 calculates a first coefficient and a second coefficient using both the numerical information that has been subjected to the reduction process and the numerical information that has not been subjected to the reduction process (step S14). The first coefficient is a coefficient of a cost function that indicates the effect of the play move, and the second coefficient is a coefficient of a cost function that indicates the cost of the play move.

[0085] The objective function definition unit 16 defines an energy function defined using the first coefficient and the second coefficient as the objective function (step S15). The optimization process execution unit 17 transmits the defined objective function to the quantum computer 20, causing it to execute an optimization process to minimize the value of the objective function (step S16). Then, the output unit 18 outputs the result of the optimization process (step S17).

[0086] As described above, in this embodiment, the input unit 13 accepts input of numerical information, and the effect suppression designation unit 14 accepts designation of a move to suppress the influence of an effect. The coefficient calculation unit 15 performs a reduction process to reduce the value of the numerical information indicating the effect corresponding to the designated move, and calculates a first coefficient and a second coefficient using this numerical information. The optimization process execution unit 17 then transmits an energy function defined using the first coefficient and the second coefficient to the quantum computer 20 to execute an optimization process, and the output unit 18 outputs the results of the optimization process. This configuration makes it possible to derive the optimal marketing move to be taken against the target.

[0087] Next, an overview of the present disclosure will be described. Fig. 7 is a block diagram showing an overview of a marketing optimization device according to the present disclosure. A marketing optimization device 80 according to the present disclosure (for example, the marketing optimization device 10) includes an input means 81 (for example, the input unit 13) that accepts input of numerical information that associates conditions, effects, and costs, which is generated based on performance data (for example, the data exemplified in Fig. 2) that is data that associates the conditions of a marketing strategy (for example, advertising), the effects (for example, the number of sessions) achieved by the strategy, and the costs required for the strategy; an effect suppression designation means 82 (for example, the effect suppression designation unit 14) that accepts designation of a strategy that suppresses the influence of the effect; and a control unit 83 that performs a reduction process (for example, multiplying by 0.01) that reduces a value indicating the effect corresponding to the designated strategy among the numerical information, and calculates a cost that indicates the effect of the strategy using both the numerical information that has been subjected to the reduction process and the numerical information that has not been subjected to the reduction process. The system includes a coefficient calculation means 83 (e.g., the coefficient calculation unit 15) that calculates a first coefficient (e.g., the above Qs) which is the coefficient of a cost function and a second coefficient (e.g., the above Qc) which is the coefficient of a cost function that indicates the cost of a move; an objective function definition means 84 (e.g., the objective function definition unit 16) that uses the first coefficient and the second coefficient to define, as an objective function, an energy function (e.g., the energy function shown in the above equation 9) that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases depending on the combination of conditions; an optimization process execution means 85 (e.g., the optimization process execution unit 17) that transmits the defined objective function to a quantum computer (e.g., the quantum computer 20) and causes the quantum computer to execute an optimization process that minimizes the value of the objective function; and an output means 86 (e.g., the output unit 18) that outputs the results of the optimization process.

[0088] Such a configuration makes it possible to derive the optimal marketing strategy to be implemented for the target.

[0089] Furthermore, the input means 81 may receive input of numerical information in which each condition of the move is quantified using a binary variable, and the objective function definition means 84 may define the objective function using QUBO (for example, the above formula 8).

[0090] In addition, the effect suppression designation means 82 may accept the designation of conditions indicating the target of the move, and may determine that a move that includes conditions different from the designated conditions is a move that will have the influence of the effect suppressed.

[0091] Specifically, the effect suppression designation means 82 may determine whether a condition different from the designated condition is satisfied based on a relationship between predetermined conditions.

[0092] The marketing optimization device 80 may also include a numerical information generation means (e.g., the numerical information generation unit 12) that generates numerical information that quantifies each condition of the move indicated by the performance data using one bit or a string of multiple bits. The input means 81 may then accept input of the numerical information.

[0093] Alternatively, the cost function indicating the effect of a move may be expressed by a first linear model with the quantified conditions as explanatory variables and the effect as a response variable, and the cost function indicating the cost of a move may be expressed by a second linear model with the quantified conditions as explanatory variables and the cost as a response variable. Then, the coefficient calculation means 83 may calculate the first coefficient, which is the coefficient of the first linear model, and the second coefficient, which is the coefficient of the second linear model, using the least squares method.

[0094] Furthermore, the coefficient calculation means 83 may perform a reduction process of multiplying the value indicating the effect by a positive number less than 1 to reduce the value.

[0095] 8 is a block diagram showing an overview of a marketing optimization system according to the present disclosure. A marketing optimization system 90 (e.g., marketing optimization system 100) according to the present disclosure includes a quantum computer 91 (e.g., quantum computer 20) that performs optimization processing of a transmitted objective function, and a marketing optimization device 80 (e.g., marketing optimization device 10) connected to the quantum computer 91. The configuration of the marketing optimization device 80 is similar to the configuration of the marketing optimization device 80 illustrated in FIG. 7.

[0096] With such a configuration, it is possible to derive the optimal marketing strategy to be implemented for the target.

[0097] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0098] (Supplementary Note 1) An input means for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation means for accepting designation of the player for suppressing the influence of the effect; a coefficient calculation means for performing a reduction process to reduce a value indicating the effect of a designated play from among the numerical information, and calculating a first coefficient, which is a coefficient of a cost function indicating the effect of the play, and a second coefficient, which is a coefficient of a cost function indicating the cost of the play, using both the numerical information that has been reduced and the numerical information that has not been reduced; an objective function definition means for defining, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions, using the first coefficient and the second coefficient; an optimization process execution means for transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and an output means for outputting the results of the optimization process. A marketing optimization device characterized by:

[0099] (Appendix 2) The input means accepts input of numerical information in which each condition of the move is quantified as a binary variable, The objective function definition means defines the objective function in QUBO. 2. The marketing optimization apparatus of claim 1.

[0100] (Note 3) The effect suppression designation means accepts the designation of conditions indicating the target of the action, and determines that an action that includes a condition different from the designated condition is an action that suppresses the influence of the effect. 10. The marketing optimization device of claim 1 or 2.

[0101] (Note 4) The effect suppression designation means determines whether a condition different from the designated condition is satisfied based on the relationship between the predetermined conditions. 4. The marketing optimization apparatus of claim 3.

[0102] (Appendix 5) A numerical information generating means is provided for generating numerical information that quantifies each condition of the play indicated by the performance data using one bit or a plurality of bit strings, The input means receives the input of the numerical information. 5. A marketing optimization device according to any one of claims 1 to 4.

[0103] (Appendix 6) The cost function showing the effect of the move is expressed by the first linear model, which uses the quantified conditions as explanatory variables and the effect as the objective variable. The cost function showing the cost of the move is expressed by a second linear model with the quantified conditions as explanatory variables and the cost as the objective variable. The coefficient calculation means calculates a first coefficient, which is a coefficient of the first linear model, and a second coefficient, which is a coefficient of the second linear model, by using the least squares method. 6. A marketing optimization device according to any one of claims 1 to 5.

[0104] (Supplementary Note 7) The coefficient calculation means performs a reduction process to reduce the value indicating the effect by multiplying the value by a positive number less than 1. 7. A marketing optimization device according to any one of claims 1 to 6.

[0105] (Appendix 8) A quantum computer that executes the optimization process of the transmitted objective function; a marketing optimization device connected to the quantum computer; The marketing optimization device includes: an input means for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation means for accepting designation of the player for suppressing the influence of the effect; a coefficient calculation means for performing a reduction process to reduce a value indicating the effect of a designated play from among the numerical information, and calculating a first coefficient, which is a coefficient of a cost function indicating the effect of the play, and a second coefficient, which is a coefficient of a cost function indicating the cost of the play, using both the numerical information that has been reduced and the numerical information that has not been reduced; an objective function definition means for defining, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions, using the first coefficient and the second coefficient; an optimization process execution means for transmitting the defined objective function to the quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and an output means for outputting the results of the optimization process. A marketing optimization system characterized by:

[0106] (Appendix 9) The input means receives input of numerical information in which each condition of the move is quantified as a binary variable, The objective function definition means defines the objective function in QUBO. 8. The marketing optimization system described in Appendix 8.

[0107] (Appendix 10) Accepting input of numerical information that associates the conditions, effects, and costs of a marketing strategy, which is generated based on performance data that associates the conditions, effects, and costs of the strategy; Accepting designation of the player who will suppress the influence of the effect; A reduction process is performed to reduce a value indicating the effect of a designated move among the numerical information, and a first coefficient is a coefficient of a cost function indicating the effect of the move, and a second coefficient is a coefficient of a cost function indicating the cost of the move, using both the numerical information on which the reduction process has been performed and the numerical information on which the reduction process has not been performed; Using the first coefficient and the second coefficient, an energy function is defined as an objective function, which defines a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions; transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process that minimizes the value of the objective function; Output the results of the optimization process A marketing optimization method comprising:

[0108] (Appendix 11) Each condition of the move is quantified as a binary variable and numerical information is input. Defining the objective function in QUBO 10. The marketing optimization method described in Appendix 10.

[0109] (Appendix 12) To the computer, an input process for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation process for accepting designation of the player who will suppress the influence of the effect; a coefficient calculation process for performing a reduction process to reduce a value indicating the effect corresponding to a designated play among the numerical information, and calculating a first coefficient which is a coefficient of a cost function indicating the effect of the play and a second coefficient which is a coefficient of a cost function indicating the cost of the play using both the numerical information on which the reduction process has been performed and the numerical information on which the reduction process has not been performed; an objective function definition process that defines, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, using the first coefficient and the second coefficient, depending on the combination of the conditions; an optimization process execution process for transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and Output process for outputting the results of the optimization process Marketing optimization program to execute.

[0110] (Appendix 13) To the computer, In the input process, each condition of the move is quantified as a binary variable and numerical information is accepted. In the objective function definition process, define the objective function using QUBO. The marketing optimization program described in Appendix 12.

[0111] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0112] This application claims priority based on Japanese Patent Application No. 2022-181737, filed on November 14, 2022, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0113] 10 Marketing Optimization Device 11 Storage section 12 Numerical Information Generation Unit 13 Input section 14 Effect suppression designation section 15 Coefficient calculation section 16 Objective function definition 17 Optimization Processing Execution Unit 18 Output section 20 Quantum Computer 100 Marketing Optimization System

Claims

1. an input means for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation means for accepting designation of the player for suppressing the influence of the effect; a coefficient calculation means for performing a reduction process to reduce a value indicating the effect of a designated play from among the numerical information, and calculating a first coefficient, which is a coefficient of a cost function indicating the effect of the play, and a second coefficient, which is a coefficient of a cost function indicating the cost of the play, using both the numerical information that has been reduced and the numerical information that has not been reduced; an objective function definition means for defining, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions, using the first coefficient and the second coefficient; an optimization process execution means for transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and an output means for outputting the results of the optimization process. A marketing optimization device characterized by:

2. The input means receives input of numerical information in which each condition of the move is quantified using a binary variable; The objective function definition means defines the objective function in QUBO. The marketing optimization device according to claim 1 .

3. The effect suppression designation means receives designation of conditions indicating the target of the play, and determines that a play that includes a condition different from the designated condition is a play that suppresses the influence of the effect.

3. The marketing optimization device according to claim 1 or 2.

4. The effect suppression designation means determines whether a condition different from the designated condition is satisfied based on a relationship between the conditions determined in advance. The marketing optimization device according to claim 3.

5. Numerical information generating means for generating numerical information that quantifies each condition of the move indicated by the performance data using one bit or a string of multiple bits; The input means receives the input of the numerical information.

3. The marketing optimization device according to claim 1 or 2.

6. The cost function showing the effect of the move is expressed by a first linear model with the quantified conditions as explanatory variables and the effect as the objective variable. The cost function showing the cost of the move is expressed by a second linear model with the quantified conditions as explanatory variables and the cost as the objective variable. The coefficient calculation means calculates a first coefficient, which is a coefficient of the first linear model, and a second coefficient, which is a coefficient of the second linear model, by using the least squares method.

3. The marketing optimization device according to claim 1 or 2.

7. The coefficient calculation means performs a reduction process to reduce the value indicating the effect by multiplying the value by a positive number less than 1.

3. The marketing optimization device according to claim 1 or 2.

8. a quantum computer that executes an optimization process for the transmitted objective function; a marketing optimization device connected to the quantum computer; The marketing optimization device includes: an input means for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation means for accepting designation of the player for suppressing the influence of the effect; a coefficient calculation means for performing a reduction process to reduce a value indicating the effect of a designated play from among the numerical information, and calculating a first coefficient, which is a coefficient of a cost function indicating the effect of the play, and a second coefficient, which is a coefficient of a cost function indicating the cost of the play, using both the numerical information that has been reduced and the numerical information that has not been reduced; an objective function definition means for defining, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions, using the first coefficient and the second coefficient; an optimization process execution means for transmitting the defined objective function to the quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and an output means for outputting the results of the optimization process. A marketing optimization system characterized by:

9. Accepting input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; Accepting designation of the player who will suppress the influence of the effect; A reduction process is performed to reduce a value indicating the effect of a designated move among the numerical information, and a first coefficient is a coefficient of a cost function indicating the effect of the move, and a second coefficient is a coefficient of a cost function indicating the cost of the move, using both the numerical information on which the reduction process has been performed and the numerical information on which the reduction process has not been performed; Using the first coefficient and the second coefficient, an energy function is defined as an objective function, which defines a relationship in which the value decreases as the effect increases and the value increases as the cost increases, depending on the combination of the conditions; transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process that minimizes the value of the objective function; Output the results of the optimization process A marketing optimization method comprising:

10. On the computer, an input process for receiving input of numerical information that associates the conditions, effects, and costs of a marketing strategy, the numerical information being generated based on performance data that is data that associates the conditions, effects, and costs of a marketing strategy; an effect suppression designation process for accepting designation of the player who will suppress the influence of the effect; a coefficient calculation process for performing a reduction process to reduce a value indicating the effect corresponding to a designated play among the numerical information, and calculating a first coefficient which is a coefficient of a cost function indicating the effect of the play and a second coefficient which is a coefficient of a cost function indicating the cost of the play using both the numerical information on which the reduction process has been performed and the numerical information on which the reduction process has not been performed; an objective function definition process that defines, as an objective function, an energy function that specifies a relationship in which the value decreases as the effect increases and the value increases as the cost increases, using the first coefficient and the second coefficient, depending on the combination of the conditions; an optimization process execution process for transmitting the defined objective function to a quantum computer and causing the quantum computer to execute an optimization process for minimizing the value of the objective function; and Output process for outputting the results of the optimization process Marketing optimization program to execute.

Images