Information Processing System, Information Processing Method, and Computer Program

Abstract

Provided is a system that enables a user to obtain an advertisement publishing plan with excellent advertising effects through simple operations. 【Solution means】An information processing method according to one aspect of the present disclosure includes predicting an advertising effect obtained by advertising publication for a plurality of advertising media under given simulation conditions. The information processing method further includes realizing a conversation with a user using artificial intelligence by causing the artificial intelligence to generate a response sentence for a user input through a user interface and outputting the response sentence generated by the artificial intelligence through the user interface. The information processing method further includes setting simulation conditions through a conversation with a user using artificial intelligence and creating an advertisement publishing plan for a plurality of advertising media based on the advertising effect predicted under the conditions.

Description

Technical Field

[0001] The present disclosure relates to an information processing system and an information processing method.

Background Art

[0002] Conventionally, a technique for selecting an advertisement publishing destination from among a plurality of advertising media so as to maximize the advertising effect with respect to cost has been known. For example, a technique for selecting an advertisement publishing destination for advertisements published across a plurality of advertising media so as to maximize the reach to a target is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, complicated operations and specialized knowledge were required for setting various parameters necessary for realizing the selection of the publishing destination. Therefore, according to one aspect of the present disclosure, it is desirable to provide a system that allows a user to obtain an advertisement publishing plan with excellent advertising effects through simple operations.

Means for Solving the Problems

[0005] According to one aspect of the present disclosure, an information processing system is provided. The information processing system includes a prediction unit and a conversation unit. The prediction unit is configured to predict an advertising effect obtained by advertising publication for a plurality of advertising media under given simulation conditions.

[0006] The conversation unit is configured to realize a conversation with a user using artificial intelligence by causing the artificial intelligence to generate a response sentence for a user input through a user interface and outputting the response sentence generated by the artificial intelligence through the user interface.

[0007] According to one aspect of the present disclosure, the conversation unit is configured to set simulation conditions through a conversation with a user using artificial intelligence, and create an advertisement posting plan for a plurality of advertising media based on the advertising effect predicted by the prediction unit under the simulation conditions.

[0008] According to one aspect of the present disclosure, the conversation unit is further configured to output the advertisement posting plan through the user interface. According to the information processing system configured in this way, the user can set simulation conditions by directly or indirectly conveying the user's desire regarding advertisement posting to the artificial intelligence through a conversation with the artificial intelligence. Therefore, the user can receive the provision of an advertisement posting plan with excellent advertising effects by a simple operation.

[0009] According to one aspect of the present disclosure, the conversation unit is configured to create an advertisement posting plan including budget allocation for a plurality of advertising media based on the advertising effect predicted by the prediction unit under the simulation conditions.

[0010] According to the information processing system configured in this way, the user can effectively utilize a limited budget and receive the provision of an advertisement posting plan that can effectively advertise through a plurality of advertising media.

[0011] According to one aspect of the present disclosure, the conversation unit may be configured to set the advertising budget and the advertising period as simulation conditions through a conversation with a user using artificial intelligence. According to one aspect of the present disclosure, the conversation unit may be further configured to set the range of the investment budget for each of one or more advertising media among the plurality of advertising media as simulation conditions through a conversation with a user using artificial intelligence.

[0012] According to the information processing system configured as described above, it is possible to provide the user with an advertising publication plan that reflects the user's wishes in detail.

[0013] According to one aspect of the present disclosure, the information processing system may include a designation information acquisition unit that acquires designation information for designating the personality of the virtual planner through the user interface. The conversation unit may configure the artificial intelligence to function as a virtual planner having the personality designated by the user by setting the personality based on the designation information to the artificial intelligence, and may be configured to set simulation conditions through conversation between the virtual planner and the user.

[0014] According to the information processing system configured as described above, the user can receive the provision of various advertising publication plans from various virtual planners by designating the personality of the virtual planner.

[0015] According to one aspect of the present disclosure, the information processing system may further include a performance acquisition unit that acquires past performance information regarding the advertising effect. In this case, the prediction unit may construct a prediction model regarding the advertising effect based on the performance information, and may be configured to predict the advertising effect based on the prediction model.

[0016] According to the information processing system configured as described above, the advertising effect can be predicted with high accuracy from past performance information. Therefore, the user can receive the provision of a more excellent advertising publication plan in terms of the advertising effect.

[0017] According to one aspect of the present disclosure, the information processing system may further include a record acquisition unit that acquires a publication record, which is a record of past advertising publications. The conversation unit provides the publication record to the artificial intelligence and instructs the artificial intelligence to detect a deviation from past advertising publications regarding the simulation conditions designated by the user during the conversation, and may be configured to output an alert regarding the simulation conditions through the user interface when the artificial intelligence detects the deviation.

[0018] According to the information processing system configured as described above, the user can suppress the creation and output of an unwanted advertisement publication plan under unwanted simulation conditions due to misrecognition, input errors, etc., by making corrections based on the alert.

[0019] According to one aspect of the present disclosure, the conversation unit may be configured to convert a part of the conversation content specified by the user among the conversation content with the user into data in a predetermined format and selectively output it according to an instruction from the user input through the user interface.

[0020] According to the information processing system configured as described above, the user can confirm the conversation content with the artificial intelligence at a later date and can use the conversation content to assist in considering the advertisement publication plan.

[0021] According to one aspect of the present disclosure, after the conversation unit outputs the advertisement publication plan through the user interface, when a question about the advertisement publication plan is input as user input, the conversation unit may be configured to obtain an answer to the question from the artificial intelligence as a response sentence and output it through the user interface.

[0022] According to the information processing system configured as described above, the user can deepen their understanding of the provided advertisement publication plan. That is, according to one aspect of the present disclosure, it is possible to provide an information processing system that is highly convenient for the user.

[0023] According to one aspect of the present disclosure, the prediction unit may be configured to predict the advertising effect for each advertising cost obtained by advertising publication for each of a plurality of advertising media.

[0024] According to one aspect of the present disclosure, simulation conditions may include an advertising budget. The prediction unit may be configured to search for the budget to be invested in each of a plurality of advertising media such that the sum of the advertising effects obtained by advertising placements on the plurality of advertising media satisfies a predetermined condition under the constraint conditions including the advertising budget. The conversation unit may be configured to output an advertising placement plan indicating the budget to be invested in each of the searched advertising media.

[0025] According to the information processing system configured as described above, a user can receive the provision of an advertising placement plan that enables advertising placements on a plurality of advertising media with a budget allocation excellent in advertising effects.

[0026] According to one aspect of the present disclosure, at least some of the plurality of advertising media may be advertising media capable of distributing advertisements in a plurality of distribution formats. In this case, the prediction unit may be configured to predict the advertising effect for each investment cost for each of the plurality of distribution formats for at least some of the advertising media. The prediction unit may be configured to search for the budget to be invested for each distribution format as the budget to be invested in the corresponding advertising media for each of at least some of the advertising media.

[0027] According to the information processing system configured as described above, a user can receive the provision of an advertising placement plan that enables advertising placements on a plurality of advertising media and distribution formats with a budget allocation excellent in terms of advertising effects.

[0028] According to one aspect of the present disclosure, the conversation unit may be configured to set, as simulation conditions, the advertising budget and the range of the budget to be invested in each of at least one or more of the plurality of advertising media through a conversation with the user using artificial intelligence.

[0029] The prediction unit may be configured to search for the budget to be invested in each of a plurality of advertising media such that the sum of the advertising effects obtained by advertising placements on the plurality of advertising media satisfies a predetermined condition under the constraint conditions including the advertising budget and the range of the budget to be invested.

[0030] According to the information processing system configured as described above, it is possible to provide an advertisement publication plan that reflects the user's wishes in detail.

[0031] According to one aspect of the present disclosure, a computer program for causing a computer to function as the prediction unit and the conversation unit in the above-described information processing system may be provided. The computer program may be recorded on a non-transitory computer-readable recording medium.

[0032] According to one aspect of the present disclosure, an information processing method may be provided. The information processing method can be executed by a computer. The information processing method may include predicting an advertising effect obtained by advertising publication for a plurality of advertising media under given simulation conditions.

[0033] The information processing method may include realizing a conversation with a user using artificial intelligence by causing the artificial intelligence to generate a response sentence for a user input through a user interface and outputting the response sentence generated by the artificial intelligence through the user interface.

[0034] The information processing method may include setting simulation conditions through a conversation with a user using artificial intelligence, creating an advertisement publication plan for a plurality of advertising media based on the advertising effect predicted under the simulation conditions, and outputting the advertisement publication plan through a user interface. According to one aspect of the present disclosure, the information processing method has the same effect as the above-described information processing system.

Brief Description of the Drawings

[0035]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Embodiments for Carrying Out the Invention

[0036] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. The information processing system 10 of the present embodiment is configured to provide a user with an advertisement publication plan (hereinafter referred to as "media plan") including a proposal regarding a budget for casting to a plurality of advertising media using artificial intelligence (AI) 51. The information processing system 10 is configured to draw out information necessary for providing an appropriate media plan from the user through a natural conversation with the user using artificial intelligence 51.

[0037] As shown in FIG. 1, the information processing system 10 is configured to be communicable with an AI server 50 equipped with artificial intelligence 51. The information processing system 10 is further configured to be communicable with a user's information terminal 70.

[0038] The information terminal 70 is, for example, a personal computer. The information processing system 10 is configured to be communicable with a plurality of information terminals 70 corresponding to a plurality of users. In FIG. 1, for simplicity of representation, only one information terminal 70 is shown.

[0039] The information processing system 10 includes a processor 11, a memory 13, a storage 15, and a communication interface 19. The communication interface 19 is configured to be communicable with the AI server 50 and the information terminal 70 through a communication network.

[0040] The processor 11 is configured to execute processing according to a computer program. The memory 13 functions as a working memory when the processor 11 executes processing. The memory 13 is, for example, a RAM.

[0041] The storage 15 stores various data used for processing executed by the processor 11 in addition to the computer program. The storage 15 is, for example, a solid state drive (SSD).

[0042] Performance data D1 is stored in the storage 15. The performance data D1 includes publication performance data D11 representing the publication performance of the corresponding advertisement and effect performance data D12 explaining the advertisement effect observed for the advertisement publication. The performance data D1 is, for example, available from an advertiser. The performance data D1 can be prepared for each advertiser with respect to a plurality of advertisers.

[0043] The publication performance data D11 includes, for each advertisement publication, as a record of past advertisement publications, for example, information such as a publication ID, an advertisement period, an advertisement budget, an advertisement medium, and / or a distribution menu. The publication ID is an ID for identifying the corresponding advertisement publication. The advertisement period is the period during which the advertisement is distributed.

[0044] The term "distribution" as used in this specification should be interpreted broadly to include distribution through a communication network and broadcasting through a broadcasting station. Hereinafter, the advertising period will also be referred to as the campaign period.

[0045] An advertising medium is a medium for distributing advertisements. Examples of advertising media include digital platforms that provide e-commerce (EC) sites, search sites, news sites, and / or social network services. Examples of advertising media further include broadcasting media such as television broadcasts and / or radio broadcasts. A distribution menu represents the distribution method of advertisements in the corresponding advertising medium. Examples of distribution methods include a distribution method using banners and / or a distribution method using videos.

[0046] Here, an example where an advertising medium can distribute advertisements using a plurality of distribution methods will be described. An advertiser or an operator commissioned by the advertiser can select a desired distribution method from among the plurality of distribution methods prepared by the advertising medium and submit an advertisement, that is, request the advertising medium to perform advertisement distribution. The submission performance data D11 describes the selected distribution method as the distribution menu.

[0047] The effect performance data D12 includes, as past performance information regarding the advertising effect, for each advertisement submission, an effect ID and effect information that describes the advertising effect observed in the advertisement submission identified by the submission ID. The effect information includes, for example, information on cost, conversion number (CV), and / or CPA (Cost Per Action). The cost corresponds to the advertising cost. CPA, also called the customer acquisition unit price, is defined by dividing the cost by the conversion number (CV).

[0048] In addition, the storage 15 stores plan history data D2 for each user. The plan history data D2 describes the media plan created for the corresponding user. The plan history data D2 can be data that describes the most recent predetermined number of media plans.

[0049] By executing processing according to a computer program, the processor 11 functions as a conversation unit 101, a condition setting unit 103, a simulator 105, and a model learning unit 107 as shown in FIG. 2.

[0050] The conversation unit 101 is configured to transfer a user sentence, which is a conversation sentence input from the user through the user interface 71 of the information terminal 70, to the artificial intelligence 51, thereby causing the artificial intelligence 51 to generate a response sentence corresponding to the user sentence, and to obtain the response sentence from the artificial intelligence 51. The user interface 71 includes a display for displaying information to the user and an input device for receiving input from the user.

[0051] The conversation unit 101 is configured to output the response sentence to the user through the user interface 71 by transmitting the response sentence generated by the artificial intelligence 51 to the information terminal 70.

[0052] That is, the conversation unit 101 receives the user sentence from the information terminal 70 and returns the response sentence generated using the artificial intelligence 51 to the information terminal 70, thereby realizing a conversation between the artificial intelligence 51 and the user.

[0053] The artificial intelligence 51 functions as a media planner based on a prior personality setting from the information processing system 10, and functions to elicit information necessary for creating a media plan from the user through conversation.

[0054] The condition setting unit 103 is configured to set simulation conditions for the simulator 105 based on the conversation between the user and the artificial intelligence 51.

[0055] The simulator 105 is configured to search for an optimal investment budget as an investment budget for a plurality of advertising media by predicting the advertising effect expected for the advertisement release under the simulation conditions set by the condition setting unit 103.

[0056] The model learning unit 107 is configured to learn the prediction model 109 provided to the simulator 105 based on the above-described performance data D1. The model learning unit 107 is configured to construct and update the prediction model 109 for each combination of advertising media and distribution menu by machine learning. Hereinafter, each combination of advertising media and distribution menu is expressed as an output destination.

[0057] The prediction model 109 is a mathematical model that calculates a predicted value of the advertising effect with respect to the investment cost for the corresponding output destination. The prediction model 109 may be constructed by a neural network or may be constructed by learning the design parameters of a predetermined function.

[0058] The simulator 105 predicts the advertising effect with respect to the investment cost for each output destination using the pre-learned prediction model 109, and searches for an optimal budget allocation for a plurality of output destinations within a range that satisfies the simulation conditions based on the advertising effect for each output destination.

[0059] In order to obtain a media plan using the information processing system 10 configured as described above, the user can operate the information terminal 70 to access the information processing system 10. When the information terminal 70 accesses the information processing system 10, it can receive the provision of the service usage screen G0 shown in FIG. 3 from the information processing system 10 after user authentication.

[0060] The service usage screen G0 functions as a graphical user interface for receiving various operations for the media planning service provided by the information processing system 10. FIG. 3 shows an exemplary configuration of the service usage screen G0.

[0061] The service usage screen G0 has an item selection area G1 and a main area G2 for displaying information related to the item selected in the item selection area G1. The item selection area G1 has "Home", "Upload", "Plan", "Clip", and "Result" as selectable items.

[0062] In FIG. 3, on the main area G2, a screen related to the item "Home" is displayed. When the item "Home" is selected, on the main area G2, an operation screen is displayed that allows the user to select one of a plurality of AI planners through the user interface 71. The AI planner is a virtual media planner that the artificial intelligence 51 plays through the personality setting for the artificial intelligence 51.

[0063] When the item "Upload" is selected, on the main area G2, an upload screen for the user to upload the performance data D1 to the information processing system 10 is displayed.

[0064] When the item "Plan" is selected, on the main area G2, a chat screen with an input field for the user's sentence is displayed. In the chat screen, the conversation between the user and the artificial intelligence 51 is displayed in speech bubbles (see FIGS. 6, 8, and 12). The chat screen is used when the user desires assistance from the AI planner. According to the present embodiment, through the conversation between the user and the artificial intelligence 51 (AI planner) on the chat screen, the information necessary to provide the user with a media plan is elicited from the user.

[0065] When the item "Clip" is selected, on the main area G2, a part of the conversation extracted by the user's operation from the conversation between the user and the artificial intelligence 51 on the chat screen is displayed as a clip (see FIGS. 14A and 14B).

[0066] When the item "Result" is selected, on the main area G2, a result screen explaining the media plan created by simulation based on the information elicited from the user through the chat screen is displayed (see FIG. 10). The media plan is an advertisement publishing plan that proposes the investment budget for each publishing destination under the publishing conditions based on the information elicited from the user through the chat screen.

[0067] The user can perform an operation of selecting a desired AI planner through an operation screen displayed in the main area G2 by selecting the item "Home" as an operation for obtaining a media plan. Before and after that, the user can select the item "Upload" and provide the performance data D1 to the information processing system 10 through the upload screen displayed in the main area G2.

[0068] When a new talk room is created through the chat screen in a state where an AI planner is selected and the performance data D1 is provided, the processor 11 executes the conversation-related processing shown in FIG. 4.

[0069] When starting the conversation-related processing shown in FIG. 4, a prompt related to the initial settings is input to the artificial intelligence 51, which is the conversation partner with the user (S110). The prompt includes a description regarding the personality settings.

[0070] In S110, the processor 11 obtains the information of the AI planner specified by the user in the item "Home" as the specified information of the AI planner, and includes, in the prompt, the personality information for setting the personality of the specified AI planner to the artificial intelligence 51, and inputs the prompt to the artificial intelligence 51. FIG. 5 shows the information provided to the artificial intelligence 51 for the initial settings of the artificial intelligence 51.

[0071] At this time, as personality information, the artificial intelligence 51 can be given the gender, tone, characteristics related to planning, and knowledge related to advertising media of the AI planner. Further, through the prompt, the artificial intelligence 51 can be instructed to set the parameter values necessary for creating a media plan in the conversation with the user so as to act as a media planner, and further, to notify the execution of the simulator 105 as soon as the preparation for creating the media plan is completed.

[0072] Examples of characteristics related to planning include characteristics such as "planning freely without being bound by past performance", "steadily planning from existing menus according to the publishing trend", and "focusing on making the most effective use of the budget to the limit". For example, when "steadily planning from existing menus according to the publishing trend" is selected, personality information such as "planning so that the CPA falls within the range of 0.8 to 1.2 times the past average publication" is given to the artificial intelligence 51.

[0073] In addition, the processor 11 can include, as knowledge related to the media, information on parameters necessary for creating a media plan and information on the types of optimization modes (described in detail later) that the simulator 105 has in the above prompt.

[0074] Furthermore, the processor 11 provides the actual performance data D1 to the artificial intelligence 51 so that the AI planner can perform planning with reference to past publications. As described above, the actual performance data D1 includes past publication records and records related to the advertising effects obtained therefrom. Furthermore, the processor 11 can provide the artificial intelligence 51 with plan history data D2 for explaining the past media plans created for the user.

[0075] In addition, the processor 11 includes alert instruction information in the prompt and inputs the prompt to the artificial intelligence 51. The alert instruction information is information for detecting a deviation from the past performance of advertising publications regarding the publication conditions specified by the user in the conversation between the user and the artificial intelligence 51 and instructing to notify the information processing system 10 of the detection. For example, the processor 11 can be instructed to detect deviations from past performance regarding the advertising budget, the target number of conversions, and the target CPA.

[0076] In the subsequent S120, the processor 11 transmits an initial message to the information terminal 70 as a signal for starting the conversation and causes the information terminal 70 to display the initial message. The initial message is output to the chat screen displayed by the information terminal 70 through the user interface 71.

[0077] For example, the processor 11 can instruct the artificial intelligence 51 to start a conversation asking the user about the campaign period, obtain an initial message from the artificial intelligence 51, and display this on the information terminal 70 through the chat screen.

[0078] Thereafter, the processor 11 executes a process of receiving a conversation sentence from the user, that is, a user sentence, input through the user interface 71 from the information terminal 70, and inputting the user sentence into the artificial intelligence 51 (S130). Further, the processor 11 executes a process of obtaining a response sentence to the user sentence from the artificial intelligence 51 and outputting the response sentence to the chat screen through the user interface 71 (S140).

[0079] FIG. 6 shows an example of a conversation. According to the example shown in FIG. 6, an initial message such as "Please tell me the setting items required for the media plan. First, please tell me the start date of the campaign." is displayed on the chat screen.

[0080] According to this example, in response to the initial message, information specifying the start date of the campaign period, that is, the start date of the advertisement distribution, is input from the user. The processor 11 can input a user sentence including the information specifying this start date into the artificial intelligence 51 (S130).

[0081] Thereafter, the processor 11 can obtain from the artificial intelligence 51 a message to the effect that "The start date is the xxth day of xx month. Next, please tell me the end date of the campaign.", and transmit the obtained message to the information terminal 70 to display the corresponding message on the chat screen (S140).

[0082] When there is no change operation for the AI planner (No in S150), the processor 11 repeatedly executes the process of inputting the user sentence to the artificial intelligence 51 (S130) and the process of displaying the response sentence from the artificial intelligence 51 through the user interface 71 (S140) until it is determined in S160 that the conversation end operation has been performed.

[0083] The processor 11 further monitors the conversation between the user and the artificial intelligence 51 in S140 and executes sub - processing according to the conversation as shown in FIG. 7.

[0084] For example, when a parameter value related to the creation of the media plan is set (Yes in S210), the processor 11 updates the simulation conditions stored in the memory 13 so as to hold the parameter value as simulation conditions (S220). Alternatively, the processor 11 receives a notification from the artificial intelligence 51 that the parameter value has been set and updates the simulation conditions.

[0085] In this embodiment, it is necessary to set a campaign period for creating the media plan. The parameter values related to the creation of the media plan include values that define the campaign period.

[0086] Details will be described later. When the optimization mode is the CV maximization mode, the parameter values related to the creation of the media plan include, as an optimization index, a value that defines the advertising budget. When the optimization mode is the cost minimization mode, the parameter values related to the creation of the media plan include, as an optimization index, a value that defines the target conversion number. When the optimization mode is the CPA maintenance mode, the parameter values related to the creation of the media plan include, as an optimization index, a value that defines the target CPA.

[0087] Furthermore, in this embodiment, as simulation conditions, for each publication destination, the range of possible investment budgets can be arbitrarily set as a constraint condition. That is, constraint conditions regarding the investment budget can be individually set for each of any one or more publication destinations. When the investment budget is set to zero, the corresponding combination of advertising media and distribution menus is excluded from the publication destination. The range of the investment budget may be set by an explicit designation from the user, or may be set by the user's consent to the proposal of the AI planner.

[0088] When the parameter value regarding the advertising budget, campaign period, or range of the investment budget described above is set, the processor 11 can store the set parameter value as a simulation condition (S220).

[0089] In addition, in this embodiment, when creating a media plan, the user can select one type of optimization mode from among multiple types of optimization modes. Even when the optimization mode is set, when it is determined that the parameter values related to the creation of the media plan are set (Yes in S210), the processor 11 can store the set optimization mode as a simulation condition (S220).

[0090] According to the example shown in FIG. 6, after the information on the start date and end date of the campaign period is obtained, the conversation between the user and the artificial intelligence 51 shifts to the stage where the artificial intelligence 51 inquires about the optimization mode desired by the user. According to this example, the user inquires of the artificial intelligence 51 about the differences between a plurality of modes selectable as the optimization mode through the chat screen, and after receiving an explanation of each mode, selects "CV maximization" as the optimization mode.

[0091] In this embodiment, the following three modes are prepared as optimization modes. · CV maximization mode: This optimization mode is a mode that searches for the investment budget for each publication destination so as to maximize the total number of conversions across all publication destinations within the range that does not exceed the specified advertising budget. · Cost minimization mode: This optimization mode is a mode that searches for the budget to be invested in each publishing destination so as to minimize the advertising budget within the range of achieving the target conversion number. · CPA maintenance mode: This is a mode that searches for the budget to be invested in each publishing destination so as to maximize the advertising budget within the range where the CPA can be maintained below the target value (i.e., the target CPA).

[0092] According to the present embodiment, when the optimization mode is specified by the user, then, a conversation continues to set parameter values necessary for creating a media plan in the corresponding optimization mode according to the user's wishes. According to the example shown in FIG. 8, when the CV maximization mode is specified as the optimization mode, the artificial intelligence 51 continues a conversation to elicit information on the advertising budget.

[0093] In the example shown in FIG. 8, as an answer to an inquiry regarding the advertising budget, the user makes a mistake in entering the number of digits of the advertising budget. At this time, in the present embodiment, the artificial intelligence 51 detects a deviation between the advertising budget transmitted from the user and the past publishing record based on the prior alert instruction information and notifies an alert. Regarding the condition for determining the deviation, it may be specified in advance for the artificial intelligence 51, or it may be left to the judgment of the artificial intelligence 51.

[0094] Upon receiving the alert notification from the artificial intelligence 51, the processor 11 outputs, through the chat screen, a message asking whether there is an input error regarding the publishing conditions received from the artificial intelligence 51, using a balloon dedicated to alerts, thereby calling the user's attention.

[0095] In S140, the processor 11 monitors the conversation between the user and the artificial intelligence 51. When receiving an alert notification from the artificial intelligence 51 as shown in FIG. 7 (Yes in S230), the processor 11 executes a process of outputting, in the form of an alert as described above, a message for inquiring about the presence or absence of an input error regarding the publication conditions from the artificial intelligence 51 to the chat screen (S240). The alert-only speech bubble display is realized, for example, by displaying the outline of the speech bubble in a color different from that in the non-alert state (for example, red).

[0096] In addition, when all the parameter values necessary for creating the media plan are available and the execution conditions for the optimization process are satisfied by the conversation between the user and the artificial intelligence 51 (Yes in S250), the processor 11 executes an optimization process using the simulator 105 according to the notification from the artificial intelligence 51 (S260).

[0097] In the optimization process, the processor 11 searches for an optimal media plan, that is, the budget to be invested in multiple publication destinations, under the set simulation conditions. By executing the optimization process, the processor 11 functions as the simulator 105 and the model learning unit 107 as shown in FIG. 9.

[0098] In the optimization process, the processor 11 obtains the latest performance data D1 by reading it from the storage 15, and based on this performance data D1, learns the prediction model 109 for each publication destination. For a publication destination without publication performance, a standard prediction model not based on the performance data D1 can be prepared as the prediction model 109 for the corresponding publication destination.

[0099] As described above, the prediction model 109 for one publication destination is a mathematical model that calculates the predicted value of the advertising effect with respect to the investment cost for the corresponding publication destination. The advertising effect is, for example, the number of conversions. FIG. 9 shows a change curve of the advertising effect with respect to the investment cost as a conceptual diagram of the prediction model 109.

[0100] In the optimization process, the processor 11 can repeat the operation of inputting the investment cost to these prediction models 109 and obtaining the advertising effect from the prediction models 109 while adjusting the investment cost.

[0101] When the optimization mode is CV maximization, the processor 11 searches for the investment budget for each publishing destination that maximizes the total advertising effect of each publishing destination within the range with the specified advertising budget as the upper limit by repeating such operations. Thereby, the processor 11 searches for an optimal media plan. The total advertising effect is the sum (total) of the predicted values of the advertising effects output by the prediction models 109 for a plurality of publishing destinations, and corresponds to the predicted values of the advertising effects obtained by advertising publications for a plurality of publishing destinations. The processor 11 can predict the overall advertising effect by calculating the sum of the predicted values and search for an optimal media plan.

[0102] Here, when the range of the investment budget for each publishing destination is defined as a constraint condition, the processor 11 can optimize the media plan within the range that satisfies the constraint condition. As described above, the constraint condition may be specified by the user or set by the AI planner.

[0103] For example, a conservative AI planner can set constraint conditions so that the budget is preferentially invested in publishing destinations where the advertiser has publishing experience and not invested in publishing destinations where the advertiser has no publishing experience. An aggressive AI planner can set constraint conditions so that the budget is also invested in publishing destinations where the advertiser has no publishing experience. Furthermore, the AI planner can also add constraint conditions regarding the upper limit and / or lower limit of CPA.

[0104] When the optimization mode is the cost minimization mode, the processor 11 can search for an optimal media plan by searching for the investment budget for each publishing destination that minimizes the advertising budget within the range where the total advertising effect of each publishing destination does not fall below the target conversion number.

[0105] When the optimization mode is the CPA maintenance mode, the processor 11 can search for an optimal media plan by searching for the budget to be invested in each publishing destination that maximizes the advertising budget within a range not exceeding the target CPA.

[0106] By executing the optimization process in this way, the processor 11 can create an optimized media plan under the set publishing conditions according to the optimization mode. The publishing conditions here refer to the conditions related to publishing among the simulation conditions, such as the advertising budget, campaign period, range of the budget to be invested in each publishing destination, target conversion number, and within the target CPA, other than the optimization mode.

[0107] Thereafter, the processor 11 gives the information of the created media plan to the artificial intelligence 51 (S270). At this time, the processor 11 can instruct the artificial intelligence 51 through a prompt to answer questions regarding the media plan based on the given information of the media plan.

[0108] In S270, the processor 11 further outputs the created media plan as an optimization result to the service usage screen G0 of the information terminal 70. Specifically, through the user interface 71, the media plan is output to the result screen corresponding to the item "Result" on the service usage screen G0.

[0109] FIG. 10 shows an example of the display of the media plan on the result screen. According to this example, on the result screen, a bar graph explaining the budget to be invested (cost) for each publishing destination is displayed for a plurality of publishing destinations where the budget to be invested is not zero. In FIG. 10, the plurality of publishing destinations are depicted as publishing destinations M1, M2, M3, M4, M5, M6, and M7.

[0110] The vertical axis of the bar graph represents the budget (cost) invested. Buttons B1, B2, and B3 for switching the vertical axis of the bar graph to "Cost", "CV", and "CPA" are arranged in the upper right corner of the result screen. That is, the result screen is configured to be able to display the invested budget, estimated number of conversions, and estimated CPA for each publishing destination.

[0111] Furthermore, the campaign period, the type of optimization mode, and other constraint conditions are also displayed on the result screen. Examples of other constraint conditions include the advertising budget, the range of the invested budget for each publishing destination, the target number of conversions, and the target CPA. In addition, a download button B4 is arranged on the result screen.

[0112] The user can obtain the simulation results and detailed data regarding the media plan in the form of a data file in a predetermined format by pressing the download button B4 through the user interface 71 of the information terminal 70.

[0113] When the download button B4 is pressed, the processor 11 transmits the detailed data to the information terminal 70, for example, in the form of a spreadsheet. Fig. 11 conceptually shows an example of the detailed data that can be obtained by the user through the download.

[0114] The detailed data includes the simulation name, simulation conditions, simulation results, and information on the details for each publishing destination. As the simulation conditions, the detailed data describes the optimization mode, the lower budget limit, the upper budget limit, the start date of the campaign period, the end date, and information on other constraint conditions.

[0115] As the simulation results, the detailed data describes the estimated budget, estimated number of conversions (estimated CV), and estimated CPA regarding the optimal media plan. The estimated budget, estimated number of conversions, and estimated CPA are the estimated values of the advertising budget, number of conversions, and CPA for the entire publishing destination when advertising is published according to the media plan.

[0116] The detailed data, as the detailed data by destination, describes, for each destination, the proposed investment cost (i.e., the investment budget), as well as the expected number of conversions (CV) and CPA information for the said investment cost.

[0117] After receiving such a media plan, the user can select the item "Plan" on the service usage screen G0 and pose questions about the created media plan to the artificial intelligence 51.

[0118] According to the example shown in FIG. 12, the user is asking "Why has the budget been reduced?" about one of the destinations in the created media plan. The artificial intelligence 51 generates a response sentence to the question based on the information of the given media plan and the knowledge as a media planner. The processor 11 can send the question sentence in S130, and in S140, obtain the response sentence to the question sentence from the artificial intelligence 51 and output it to the chat screen of the information terminal 70.

[0119] In addition, according to the example shown in FIG. 12, the user is asking "Tell me about the recent CPA trend?" The artificial intelligence 51 generates a response sentence to the question based on the information of the given media plan, the performance data D1, and the knowledge as a media planner. The processor 11 can send the question sentence in S130 and output the response sentence to the chat screen of the information terminal 70 in S140.

[0120] Thus, in this embodiment, by giving the artificial intelligence 51 the personality as a media planner and further giving the performance data D1 and the information of the media plan, the artificial intelligence 51 can answer various questions regarding the advertisement placement from the user.

[0121] In addition, in this embodiment, on the chat screen, a clip button B5 is attached to the speech bubble that records the response text of the artificial intelligence 51. When the clip button B5 is pressed (Yes in S310) through the user interface 71, the processor 11 repeatedly executes the clip-related process shown in FIG. 13, and saves the response text of the artificial intelligence 51 associated with the pressed clip button B5, together with the previous user text, as a clip in the storage 15 (S320). The "clip" mentioned here means a cutout of the conversation. Specifically, it corresponds to a part extracted from the conversation between the user and the artificial intelligence 51.

[0122] In S320, the processor 11 not only simply cuts out a part of the conversation on the chat screen, but also organizes the conversation content in a specific format and outputs it as a file. That is, the processor 11 converts a part of the conversation content specified by the user into data in a predetermined format and selectively outputs it as a file. In the storage 15, a data file in a specific file format (for example, a presentation file format) is saved as a clip.

[0123] The user can view and download the saved clip by selecting the item "Clip" on the service usage screen G0. FIG. 14A shows the configuration of the list screen displayed in the main area G2 when the item "Clip" is selected.

[0124] When the item "Clip" is selected, the processor 11 can read out the corresponding multiple clips stored in the storage 15 and display, through the user interface 71, a list screen in which the thumbnails of the multiple saved clips are arranged in the main area G2 of the service usage screen G0.

[0125] After that, when the processor 11 receives an operation on the list screen and a clip is selected, as shown in FIG. 14B, the clip can be displayed through the user interface 71. According to the example shown in FIG. 14B, a clip that describes the user's sentence as a title and summarizes the response sentence from the artificial intelligence 51 and describes it in a list is displayed.

[0126] In addition, during the conversation between the user and the artificial intelligence 51 through the chat screen, when the operation screen of the item "Home" is opened and an AI planner different from the currently set AI planner as the AI planner is selected, the processor 11 executes the conversation handover process.

[0127] That is, when the processor 11 detects that an AI planner change operation has been performed during the conversation (Yes in S150), as shown in FIG. 4, the processor 11 executes a handover process including a process of assigning the personality of the newly selected AI planner to the artificial intelligence 51 (S155). Here, similar to the process in S110, by sending a prompt with personality information to the artificial intelligence 51, the personality of the newly selected AI planner can be assigned to the artificial intelligence 51.

[0128] At this time, the processor 11 inputs the necessary information to the artificial intelligence 51 as a prompt so that the new AI planner can continue the conversation by inheriting information about the previous conversation history, simulation results, and simulation condition settings from the previous AI planner, and sets the new AI planner for the artificial intelligence 51 (S155).

[0129] After setting the new AI planner, the processor 11 adds a notification message indicating the planner change to the chat screen (S155). After that, the processor 11 repeats the processes of S130 to S160 in the same manner as before to realize the conversation between the user and the artificial intelligence 51.

[0130] According to the information processing system 1 of the present embodiment described above, by using the artificial intelligence 51, it is possible to draw out information necessary for creating a media plan from the user during natural conversation, create a media plan, and provide it to the user. Therefore, according to the present embodiment, it is possible to provide a system that allows a user to obtain a media plan with excellent advertising effects through simple operations.

[0131] In particular, in the present embodiment, the user can selectively use AI planners with different personalities and receive a conservative or challenging media plan according to the personality of the AI planner.

[0132] In addition, in the present embodiment, a prediction model 109 for predicting the advertising effect with respect to the investment cost is generated by machine learning using past performance data D1 for each publication destination. The processor 11 uses the prediction model 109 for each publication destination to predict the conversion number and / or CPA as the advertising effect for all of the plurality of publication destinations when allocating the budget to the plurality of publication destinations, and generates an optimal media plan. Therefore, according to the present embodiment, it is possible to perform accurate prediction of the advertising effect, and thereby generate an appropriate media plan.

[0133] According to the present embodiment, the user can specify a desired optimization mode from among a plurality of types of optimization modes including a CV maximization mode, a cost minimization mode, and a CPA maintenance mode, and receive a media plan searched according to the specified optimization mode. Therefore, this information processing system 10 can provide a media plan corresponding to various needs of the user.

[0134] According to the present embodiment, it is also advantageous that an alert can be output to the user when a publication condition that is greatly deviated from the past publication record is set due to a user input error. In addition, the clip function included in the information processing system 10 can improve the convenience of the user regarding the consideration of advertising publication including the provided media plan.

[0135] [Other Embodiments] The present disclosure is not limited to the above embodiments and can take various forms. For example, the illustrated service usage screen G0 is merely an example and can take various forms. In the above embodiments, the advertising effect was predicted and the optimal media plan was searched for in units of combinations of advertising media and distribution menus. However, without considering the distribution menu, the advertising effect may be predicted and the optimal media plan may be searched for in units of advertising media. Only some of the plurality of advertising media may be advertising media capable of advertising distribution by a plurality of distribution methods.

[0136] In addition, in the above embodiments, the conversion number (CV) and CPA were used as indicators of the advertising effect. However, the advertising effect may be quantified using other indicators such as the page view number (PV). The advertising effect can be evaluated using various indicators other than the illustrated indicators.

[0137] The above-described information processing system 10 may have a function of outputting a report that allows a user to compare a plurality of created media plans. For example, the report may be configured such that images explaining the media plans as shown in FIG. 10 are arranged in parallel. Alternatively, the report may be output in the form of a spreadsheet. In this case, the spreadsheet may be configured such that the detailed data shown in FIG. 11 is described for each item for a plurality of media plans.

[0138] The functions of one component in the above embodiments may be distributed and provided to a plurality of components. The functions of a plurality of components may be integrated into one component. A part of the configuration of the above embodiments may be omitted. At least a part of the configuration of the above embodiments may be added to or replaced with the configuration of other above embodiments. All aspects included in the technical idea specified from the language described in the claims are embodiments of the present disclosure.

[0139] [Technical Ideas Disclosed in this Specification] It can be understood that the following technical ideas are disclosed in this specification. [Item 1] A prediction unit configured to predict the advertising effect obtained by advertising placement for a plurality of advertising media under given simulation conditions; A conversation unit configured to cause an artificial intelligence to generate a response sentence for a user input through a user interface, and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with the user using the artificial intelligence; Comprising: The conversation unit sets the simulation conditions through the conversation with the user using the artificial intelligence, creates an advertising placement plan for the plurality of advertising media based on the advertising effect predicted by the prediction unit under the simulation conditions, and outputs the advertising placement plan through the user interface. An information processing system. [Item 2] The information processing system according to Item 1, wherein the conversation unit creates an advertising placement plan including budget allocation for the plurality of advertising media based on the advertising effect predicted by the prediction unit under the simulation conditions. An information processing system. [Item 3] The information processing system according to Item 1 or Item 2, wherein the conversation unit sets, as the simulation conditions, the advertising budget, the advertising period, and the range of the investment budget for each of one or more of the plurality of advertising media through the conversation with the user using the artificial intelligence. An information processing system. [Item 4] The information processing system according to any one of Items 1 to 3, A designated information acquisition unit that acquires designated information for designating the personality of a virtual planner through the user interface Further comprising: The conversation unit functions as the virtual planner having the personality specified by the user by setting the personality to the artificial intelligence based on the specified information, and sets simulation conditions through conversation between the virtual planner and the user. An information processing system. [Item 5] An information processing system according to any one of Items 1 to 4, A performance acquisition unit that acquires past performance information regarding the advertising effect further comprising The prediction unit constructs a prediction model regarding the advertising effect based on the performance information, and is configured to predict the advertising effect based on the prediction model. An information processing system. [Item 6] An information processing system according to any one of Items 1 to 5, A record acquisition unit that acquires a publication record that is a record of past advertisement publications further comprising The conversation unit provides the publication record to the artificial intelligence and instructs it to detect a deviation from past advertisement publications regarding the simulation conditions specified by the user during the conversation, When the artificial intelligence detects a deviation, an alert regarding the simulation conditions is output through the user interface An information processing system configured as such. [Item 7] An information processing system according to any one of Items 1 to 6, The conversation unit is configured to convert a part of the conversation content specified by the user among the conversation content with the user into data in a predetermined format and output it according to an instruction from the user input through the user interface. An information processing system. [Item 8] An information processing system according to any one of Items 1 to 7, The conversation unit is configured to output the advertisement publishing plan through the user interface, and then, when a question about the advertisement publishing plan is input as the user input, obtain an answer to the question from the artificial intelligence as the response sentence and output it through the user interface. [Item 9] The information processing system according to Item 1, wherein the simulation conditions include an advertising budget, the prediction unit, predicts the advertising effect for each advertising cost obtained by advertising publication for each of the plurality of advertising media, and searches for the investment budget for each of the plurality of advertising media such that the sum of the advertising effects obtained by advertising publication for the plurality of advertising media satisfies a predetermined condition under the constraint conditions including the advertising budget. is configured as follows, and the conversation unit outputs an advertisement publishing plan indicating the investment budget for each of the searched advertising media. [Item 10] The information processing system according to Item 9, wherein at least some of the plurality of advertising media are advertising media capable of distributing advertisements in a plurality of distribution formats, the prediction unit, predicts the advertising effect for each advertising cost for each of the plurality of distribution formats for at least some of the advertising media, and searches for the investment budget for each distribution format as the investment budget for the corresponding advertising media for each of at least some of the advertising media. is configured as follows. [Item 11] The information processing system according to Item 9, wherein the conversation unit is configured to set, as the simulation conditions, the advertising budget and the range of the investment budget for at least one or more of the plurality of advertising media through a conversation with the user using the artificial intelligence. The prediction unit is configured to search for the budget to be invested in each of the plurality of advertising media such that the sum of the advertising effects obtained by the advertisement submissions to the plurality of advertising media satisfies a predetermined condition under the constraint conditions including the ranges of the advertising budget and the investment budget. [Item 12] A computer program for causing a computer to function as the prediction unit and the conversation unit in the information processing system according to any one of Items 1 to 11. [Item 13] An information processing method executed by a computer, predicting the advertising effects obtained by the advertisement submissions to the plurality of advertising media under the given simulation conditions; causing an artificial intelligence to generate a response sentence for a user input through a user interface, and outputting the response sentence generated by the artificial intelligence through the user interface to realize a conversation with the user using the artificial intelligence; setting the simulation conditions through the conversation with the user using the artificial intelligence, and creating an advertisement submission plan for the plurality of advertising media based on the advertising effects predicted under the simulation conditions by the predicting; outputting the advertisement submission plan through the user interface; An information processing method including the above.

Description of Signs

[0140] 10…Information processing system, 11…Processor, 13…Memory, 15…Storage, 19…Communication interface, 50…AI server, 51…Artificial intelligence, 70…Information terminal, 71…User interface, 101…Conversation unit, 103…Condition setting unit, 105…Simulator, 107…Model learning unit, 109…Prediction model, G0…Service usage screen, G1…Item selection area, G2…Main area.

Claims

1. A prediction unit configured to predict advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; a conversation unit configured to generate a response sentence in response to a user input through a user interface using an artificial intelligence and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; Equipped with The conversation unit sets simulation conditions including a budget range for each of one or more of the plurality of advertising media as the simulation conditions through a conversation with the user using the artificial intelligence, creates an advertising placement plan for the plurality of advertising media based on the advertising effectiveness predicted by the prediction unit under the simulation conditions, and outputs the advertising placement plan through the user interface.

2. 2. The information processing system according to claim 1, The conversation unit sets simulation conditions further including at least one of an advertising budget and an advertising period as the simulation conditions.

3. A prediction unit configured to predict advertising effects obtained by placing advertisements on a plurality of advertising media under given simulation conditions; a conversation unit configured to generate a response sentence in response to a user input through a user interface using an artificial intelligence and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; A designation information acquisition unit configured to acquire designation information designating a personality of a virtual planner through the user interface; Equipped with The conversation unit sets the personality to the artificial intelligence based on the specified information, thereby causing the artificial intelligence to function as a virtual planner having the personality specified by the user, sets the simulation conditions through a conversation between the virtual planner and the user, creates an advertising placement plan for the multiple advertising media based on the advertising effect predicted by the prediction unit under the simulation conditions, and outputs the advertising placement plan through the user interface.This is an information processing system.

4. A prediction unit configured to predict advertising effects obtained by placing advertisements on a plurality of advertising media under given simulation conditions; a conversation unit configured to generate a response sentence in response to a user input through a user interface using an artificial intelligence and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; A record acquisition unit configured to acquire an advertisement record which is a record regarding past advertisement advertisements; Equipped with The conversation unit includes: The simulation conditions are set through a conversation with the user using the artificial intelligence, and the prediction unit creates an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions, and the advertising placement plan is output through the user interface; and providing the artificial intelligence with the advertisement record and instructing the artificial intelligence to detect a deviation from past advertisement advertisements with respect to the simulation conditions specified by the user during the conversation; When the artificial intelligence detects a deviation, an alert regarding the simulation conditions is output through the user interface. An information processing system configured as follows.

5. A prediction unit configured to predict advertising effects obtained by placing advertisements on a plurality of advertising media under given simulation conditions; a conversation unit configured to generate a response sentence in response to a user input through a user interface using an artificial intelligence and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; Equipped with The conversation unit includes: The simulation conditions are set through a conversation with the user using the artificial intelligence, and the prediction unit creates an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions, and the advertising placement plan is output through the user interface; and An information processing system configured to convert a portion of the conversation content with the user, specified by the user, into data in a predetermined format and selectively output the data in accordance with instructions from the user input through the user interface.

6. A prediction unit configured to predict advertising effects obtained by placing advertisements on a plurality of advertising media under given simulation conditions; a conversation unit configured to generate a response sentence in response to a user input through a user interface using an artificial intelligence and output the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; Equipped with The conversation unit includes: The simulation conditions are set through a conversation with the user using the artificial intelligence, and the prediction unit creates an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions, and the advertising placement plan is output through the user interface; and An information processing system configured to output the advertising plan through the user interface, and then when a question about the advertising plan is input as the user input, obtain an answer to the question as the response sentence from the artificial intelligence and output it through the user interface.

7. A computer program for causing a computer to function as the prediction unit and the conversation unit in the information processing system according to any one of claims 1 to 6.

8. 1. A computer-implemented information processing method, comprising: Predicting advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; generating a response sentence in response to a user input through a user interface using an artificial intelligence, and outputting the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; setting, as the simulation conditions, a simulation condition including a range of an investment budget for each of one or more advertising media among the plurality of advertising media through a conversation with the user using the artificial intelligence, and creating an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions by making the prediction; outputting the advertising placement plan through the user interface; An information processing method comprising:

9. The information processing method according to claim 8, The simulation conditions further include at least one of an advertising budget and an advertising period. Information processing methods.

10. 1. A computer-implemented information processing method, comprising: Predicting advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; generating a response sentence in response to a user input through a user interface using an artificial intelligence, and outputting the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; acquiring, through the user interface, designation information for designating a personality of a virtual planner; By setting the personality to the artificial intelligence based on the designation information, the artificial intelligence functions as the virtual planner having the personality designated by the user; setting the simulation conditions through a conversation between the virtual planner and the user, and creating an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions by making the prediction; outputting the advertising placement plan through the user interface; An information processing method comprising:

11. 1. A computer-implemented information processing method, comprising: Predicting advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; generating a response sentence in response to a user input through a user interface using an artificial intelligence, and outputting the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; setting the simulation conditions through a conversation with the user using the artificial intelligence, and creating an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions by making the prediction; outputting the advertising placement plan through the user interface; Obtaining a record of past advertising placements; providing the artificial intelligence with the advertisement record and instructing the artificial intelligence to detect a deviation from past advertisement advertisements regarding the simulation conditions specified by the user during the conversation; outputting an alert regarding the simulation conditions through the user interface when the artificial intelligence detects a deviation; An information processing method comprising:

12. 1. A computer-implemented information processing method, comprising: Predicting advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; generating a response sentence in response to a user input through a user interface using an artificial intelligence, and outputting the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; setting the simulation conditions through a conversation with the user using the artificial intelligence, and creating an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions by making the prediction; outputting the advertising placement plan through the user interface; converting a part of the conversation content designated by the user out of the conversation content with the user into data in a predetermined format in accordance with an instruction from the user inputted through the user interface, and selectively outputting the data; An information processing method comprising:

13. 1. A computer-implemented information processing method, comprising: Predicting advertising effectiveness obtained by placing advertisements on a plurality of advertising media under given simulation conditions; generating a response sentence in response to a user input through a user interface using an artificial intelligence, and outputting the response sentence generated by the artificial intelligence through the user interface, thereby realizing a conversation with a user using the artificial intelligence; setting the simulation conditions through a conversation with the user using the artificial intelligence, and creating an advertising placement plan for the plurality of advertising media based on the advertising effect predicted under the simulation conditions by making the prediction; outputting the advertising placement plan through the user interface; Including, The information processing method includes, after the advertising plan is output, when a question about the advertising plan is input as the user input, obtaining an answer to the question as the response sentence from the artificial intelligence and outputting it through the user interface, wherein the information processing method includes:

Images