Information processing device, information processing method, and information processing program

Abstract

To propose improvements for improving an advertising effect.SOLUTION: An information processing device according to the present application comprises: a content generation unit that generates a changed content by changing a feature of content; an estimation unit that estimates an advertising effect of the changed content generated by the content generation unit; and a proposing unit that proposes improvements to the content on the basis of the advertising effect estimated by the estimation unit.SELECTED DRAWING: Figure 1

Description

[[Technical Field]]

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program. [[Background Art]]

[0002] In recent years, techniques for distributing content such as news and advertisements via the Internet have been known. As an example of a technique for distributing such content, there is a technique for estimating CTR (Click Through Rate) in advance by using a CTR prediction model that predicts the click probability, which is one of the indicators of advertising effectiveness. (see, for example, Patent Document 1). [[Prior Art Documents]] [[Patent Documents]]

[0003] [[Patent Document 1]] Japanese Unexamined Patent Publication No. 2018-84992 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] However, in the prior art, for example, consideration has not been given to proposing improvements for improving advertising effectiveness.

[0005] The present invention has been made in view of the above, and an object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program that can propose improvements for improving advertising effectiveness. [[Means for Solving the Problem]]

[0006] To solve the above-mentioned problems and achieve the objective, the information processing device according to the present invention is characterized by comprising: a content generation unit that generates modified content with altered characteristics; an estimation unit that estimates the advertising effect of the modified content generated by the content generation unit; and a proposal unit that proposes improvements to the content based on the advertising effect estimated by the estimation unit. [Effects of the Invention]

[0007] According to the present invention, improvements can be proposed to enhance the effectiveness of advertising. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 is a block diagram showing an example configuration of an information processing device according to the embodiment. [Figure 3] Figure 3 shows an example of a delivery history database according to an embodiment. [Figure 4] Figure 4 shows an example of a CTR estimation model database according to the embodiment. [Figure 5] Figure 5 shows an example of an amendment advertisement according to the present invention. [Figure 6] Figure 6 is a diagram (part 1) showing an example of the improvements according to the embodiment. [Figure 7] Figure 7 is a diagram (part 2) showing an example of the improvements according to the embodiment. [Figure 8] Figure 8 is a flowchart showing an example of the proposed process according to the embodiment. [Figure 9] Figure 9 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program relating to this application (hereinafter referred to as "embodiments"). However, these embodiments do not limit the information processing device, information processing method, and information processing program relating to this application.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment.

[0011] The information processing device 100 according to the embodiment shown in Figure 1 is, for example, an information processing device that proposes improvements to advertisements created by an advertisement creator. For example, the information processing device 100 according to the embodiment is an information processing device that works in conjunction with each user's terminal device (not shown) and provides each user's terminal device with API (Application Programming Interface) services for various applications (hereinafter referred to as apps), etc., and various data, and is realized by a server device or a cloud system, etc.

[0012] Furthermore, the information processing device 100 may be an information processing device that provides Web services to each user's terminal device. For example, the information processing device 100 may provide services such as internet access, search services, SNS (Social Networking Service), e-commerce, electronic payment, online games, online banking, online trading, accommodation / ticket reservations, and video / music distribution as Web services. In practice, the information processing device 100 may cooperate with various servers that provide the above-mentioned Web services and act as an intermediary for Web services.

[0013] The information processing device 100 distributes advertisements to users through various web services, and stores data related to the distribution history in a distribution history database. For example, the distribution history includes data such as when, to whom, and through what medium an advertisement was distributed, whether the advertisement was clicked, and whether a conversion was achieved through the advertisement.

[0014] Furthermore, the creator terminal 50 shown in FIG. 1 is a terminal operated by an advertisement creator. For example, the creator terminal 50 transmits information related to an advertisement to the information processing device 100 via a predetermined network, and receives information related to advertisement improvement content from the information processing device 100.

[0015] Conventionally, indicators such as CTR (Click Through Rate) and vCTR (Visible Click Through Rate) of advertisements have been used as indicators related to advertising effectiveness. In general, advertisers create advertisements with the goal of increasing these advertising indicators.

[0016] On the other hand, with regard to improvements for increasing advertising effectiveness, there has been no other option but to manually revise advertisements and repeat A / B tests. That is, conventionally, a large amount of time and effort was required to improve advertising effectiveness.

[0017] Therefore, in the information processing according to the embodiment, advertisement improvement content is proposed to advertisement creators based on data registered in the distribution history database. Specifically, first, the information processing device 100 generates a CTR estimation model based on the data registered in the distribution history database (step S1). As will be described later, the information processing device 100 may also be trained in combination with Explainable AI (XAI: Explainable Artificial Intelligence).

[0018] For example, the CTR estimation model is a model that has learned the relationship between the characteristics of a delivered advertisement and the CTR of the advertisement. Note that the CTR estimation model may be a model that outputs the advertising effect according to the user attributes and industry type when the user attributes targeted by the advertisement and the industry type of the advertisement are input in addition to the advertisement.

[0019] In addition, the CTR estimation model may be a model that outputs an advertising effect according to the advertising objective when the advertising objective of the advertisement is input in addition to the above. The advertising objective herein is, for example, the presence or absence of retargeting aimed at delivering advertisements to users who have an access history to the advertiser's website. Note that the advertising objective is not limited to this, and may be arbitrarily set, for example, to obtain awareness.

[0020] Subsequently, the information processing apparatus 100 according to the embodiment receives advertisement information related to a target advertisement from the creator terminal 50 (step S2).

[0021] The information processing apparatus 100 generates a plurality of modified advertisements each obtained by modifying features of an original advertisement based on the advertisement information received from the creator terminal 50 (step S3). For example, the information processing apparatus 100 obtains feature quantities of the original advertisement by performing OCR and various types of image analysis on an image related to the original advertisement, and generates modified advertisements in which the feature points are respectively modified (step S3).

[0022] For example, a modified advertisement is content obtained by changing text or an image displayed in an original advertisement, and is content in which at least one of the size, position, and content of a plurality of texts or a plurality of images displayed in the original advertisement is changed.

[0023] For example, the information processing apparatus 100 generates a modified advertisement by changing at least one of the content, the number of characters, the ratio of a character area to the entire advertisement, the position, and the color of text from the original advertisement, or at least one of the content, size, position, and color of an image displayed in the original advertisement.

[0024] Next, the information processing device 100 estimates the advertising effect for the original advertisement and each modified advertisement (step S4).

[0025] The information processing device 100 inputs the original advertisement and each modified advertisement into the CTR estimation model and estimates the output value as the respective advertisement effectiveness (CTR). Then, for example, the information processing device 100 proposes the difference between the modified advertisement, which is estimated to have a higher advertising effectiveness than the original advertisement, and the original advertisement as an improvement to the producer terminal 50 (step S5).

[0026] Furthermore, the information processing device 100 may input information regarding the target user group of the content and the advertiser's industry into a CTR estimation model to estimate advertising effectiveness based on the user group or the advertiser's industry. Alternatively, for example, the information processing device 100 may input information regarding the advertising objective into a CTR estimation model to estimate advertising effectiveness.

[0027] As described above, the information processing device 100 according to this embodiment generates a CTR estimation model based on the data registered in the delivery history database. The information processing device 100 then estimates the advertising effectiveness for multiple modified advertisements and proposes improvements.

[0028] In other words, according to the information processing device 100 of this embodiment, it is possible to propose improvements to enhance the effectiveness of advertising.

[0029] [1. Example of an information processing device configuration] Next, an example of the configuration of the information processing device 100 according to the embodiment will be described using Figure 2. Figure 2 is a block diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 2, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0030] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is also connected to the network via a wired or wireless connection.

[0031] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. As shown in Figure 2, the storage unit 120 includes an extraction model database 121, a distribution history database 122, a CTR estimation model database 123, and an explainable AI database 124.

[0032] (Extraction Model Database 121) The extraction model database 121 is a database that stores extraction models. For example, an extraction model is a model that extracts features from an advertisement. For example, an extraction model extracts the features of an input advertisement as an N-dimensional vector.

[0033] (Distribution history database 122) The delivery history database 122 is a database that stores data related to the past delivery history of advertisements. Figure 3 shows an example of the delivery history database 122 according to an embodiment.

[0034] As shown in Figure 3, the delivery history database 122 according to this embodiment has items such as "Ad ID", "Image Information", "Delivery History", "Click History", "CTR", and "vCTR".

[0035] The "Ad ID" is an identifier that identifies each advertisement. "Image Information" is information about the image displayed as the advertisement. "Delivery History" is the delivery history of the corresponding advertisement. For example, the delivery history includes data such as when, to whom, and on what medium the advertisement was delivered.

[0036] "Click history" refers to the click history of the corresponding advertisement. Click history includes data on whether or not the delivered advertisement was clicked. "CTR" and "vCTR" are metrics related to the advertising effectiveness of the corresponding advertisement. In addition, for example, the delivery history database 122 may also store information about the target user group of each advertisement, the advertiser's industry, and information about each item related to the advertising objective.

[0037] (CTR Estimation Model Database 123) The CTR estimation model database 123 stores CTR estimation models. As described above, a CTR estimation model is a model that estimates the click-through rate (CTR) of an advertisement. Figure 4 shows an example of the CTR estimation model database 123 according to the embodiment.

[0038] As shown in Figure 4, the CTR estimation model database 123 according to this embodiment has items such as "Model ID," "Model Body," and "Target Attributes." "Model ID" is an identifier for identifying each CTR estimation model. "Model Body" is the body of the corresponding CTR estimation model.

[0039] The "target attribute" indicates the target attribute of the corresponding CTR estimation model. Specifically, the target attribute is each demographic attribute or psychographic attribute, and the CTR estimation model database 123 according to this embodiment stores a CTR estimation model for each of these target attributes. This is expected to improve the accuracy of CTR estimation for each target attribute.

[0040] Furthermore, the information processing device 100 may, for example, store CTR estimation models not only for target attributes but also for each advertising distribution platform. Here, "distribution platform" refers to the media on which the advertisement is displayed, such as news sites, auction sites, and video sites. Alternatively, the information processing device 100 may also store CTR estimation models for each type of terminal that displays the advertisement.

[0041] (Explainable AI Database 124) The explainable AI database 124 stores explainable AI. For example, an explainable AI is an AI that explains the rationale behind improvements.

[0042] (Control unit 130) The control unit 130 is a controller, and is realized by executing various programs (corresponding to an example of an information processing program) stored in the internal memory of the information processing device 100 using a memory area such as RAM as a working area, for example, by a CPU (Central Processing Unit), MPU (Micro Processing Unit), ASIC (Application Specific Integrated Circuit), or FPGA (Field Programmable Gate Array). In the example shown in Figure 2, the control unit 130 has an acquisition unit 131, a model generation unit 132, a content generation unit 133, an estimation unit 134, and a proposal unit 135.

[0043] (Acquisition part 131) The acquisition unit 131 acquires advertising information related to advertisements from the producer terminal 50 via the communication unit 110. For example, the acquisition unit 131 passes the acquired advertising information to the content generation unit 133. The acquisition unit 131 may also acquire existing advertising information related to advertisements from various web services, for example.

[0044] Furthermore, the acquisition unit 131 acquires information regarding the delivery history of each advertisement. For example, the acquisition unit 131 acquires information regarding the delivery history from each web service and registers it in the delivery history database 122.

[0045] (Model generation unit 132) The model generation unit 132 generates a CTR estimation model. For example, the model generation unit 132 generates a CTR estimation model that learns the relationship between the characteristics of an advertisement and CTR based on the information registered in the delivery history database 122. For example, the model generation unit 132 generates a CTR estimation model for each attribute of the user who views the advertisement, each delivery platform, or a combination of these. Alternatively, the model generation unit 132 may generate a CTR estimation model using, for example, the target user group for each advertisement, the industry of the advertiser (or the advertised product), and the advertising objective as training data.

[0046] Furthermore, any type of model can be used for the CTR estimation model. For example, the model generation unit 132 may use an SVM (Support Vector Machine) or a DNN (Deep Neural Network) as the model. Here, the DNN may be a CNN (Convolutional Neural Network) or an RNN (Recurrent Neural Network). Also, the RNN may be an LSTM (Long Short-Term Memory), etc. In other words, any type of model can be used. Moreover, the model may be a model realized by combining multiple models, such as a model that combines a CNN and an RNN.

[0047] The learning process may involve deep learning using, for example, a deep neural network (DNN). Alternatively, data mining or other machine learning algorithms may be used. The model generation unit 132 learns the CTR estimation model using the various learning methods described above.

[0048] Furthermore, the model generation unit 132 generates explainable AI. Here, explainable AI refers to an AI that calculates a score (confidence level) for each feature (or product thereof) with respect to the target variable. Examples of explainable AI include frequent pattern mining and logistic regression.

[0049] For example, the model generation unit 132 generates an explainable AI based on the CTR estimation model.

[0050] (Content generation unit 133) The content generation unit 133 generates modified advertisements with altered characteristics. For example, the content generation unit 133 extracts the features of the original advertisement by inputting images related to the original advertisement into the extraction model registered in the extraction model database 121.

[0051] Next, the content generation unit 133 generates multiple modified advertisements, each with a different extracted feature. Figure 5 shows an example of a modified advertisement according to the embodiment. As shown in Figure 5, for example, the content generation unit 133 generates multiple modified advertisements Co based on the original advertisement, the original advertisement Or, each with a different feature.

[0052] The content generation unit 133 generates a modified advertisement Co in which the font, font size, font color, text position, text content, product image position, size, background image, etc., are arbitrarily changed.

[0053] In this case, for example, the content generation unit 133 sets the content to be maintained and not changed from the original ad Or based on predetermined rules, and then generates a modified ad with the features other than the maintained content changed.

[0054] For example, in the example shown in the figure, the content to be maintained is "Max 80% OFF," which includes the product name, company name, price, and discount rate. For example, the content generation unit 133 refers to the rules regarding the content to be maintained and generates the modified advertisement. The rules here correspond to an example of the predetermined conditions when changing the text content.

[0055] Furthermore, when the content generation unit 133 generates a modified advertisement Co with altered text content, for example, it may generate the modified advertisement Co within the bounds of the rules so as not to violate the Pharmaceutical Affairs Law or other similar laws.

[0056] (Estimation part 134) The estimation unit 134 estimates the advertising effectiveness of the modified advertisements generated by the content generation unit 133. Specifically, the estimation unit 134 inputs the original advertisement Or and the modified advertisement Co generated by the content generation unit 133 into the CTR estimation model registered in the CTR estimation model database 123, thereby estimating the advertising effectiveness (CTR) of the original advertisement Or and the modified advertisement Co, respectively.

[0057] In this case, the estimation unit 134 inputs the modified advertisement into the CTR estimation model generated for each target attribute, as shown in Figure 4, and estimates the advertising effect for each target attribute. Alternatively, the estimation unit 134 may use the CTR estimation model generated for each distribution platform to estimate the advertising effect for each target attribute.

[0058] Furthermore, the estimation unit 134 may also estimate the advertising effectiveness by using the target user group of the original ad Or or modified ad Co, the industry of the advertiser (or the product being advertised), and the advertising objective as input data to the CTR estimation model.

[0059] (Proposal Department 135) The proposal unit 135 proposes improvements to the original ad Or based on the advertising effect estimated by the estimation unit 134. For example, the proposal unit 135 proposes changes from the original ad Or to a modified ad Co that is estimated to have a higher advertising effect than the original ad Or as an improvement. The proposal unit 135 may also propose improvements for each user attribute or for each distribution platform.

[0060] In this case, the proposal unit 135 may, for example, make suggestions for improvement based on an overall evaluation for each user attribute or each distribution platform, or it may make suggestions for improvement so as to maximize the advertising effectiveness for the persona set by the advertiser.

[0061] Furthermore, the proposal unit 135 uses explainable AI registered in the explainable AI database 124 to propose reasons for the improvements. Figures 6 and 7 show examples of improvements according to the embodiment.

[0062] As shown in Figure 6, for example, the improvement proposed by the proposal unit 135 includes items such as "target image," "predicted CTR," and "changes." The target image is the image to be used for estimating the advertising effect (i.e., the original advertisement or each modified advertisement), and the "predicted CTR" is the CTR value estimated by the estimation unit 134. "Changes" indicates the changes from the original advertisement.

[0063] The example shown in the figure demonstrates that the predicted CTR of modified ad Co1, with a reduced text area, is higher than that of the original ad Or, while the predicted CTR of modified ad Co2, with a shortened text length, is lower than that of the original ad Or.

[0064] In other words, in this case, proposal unit 135 will propose information regarding the changes to the revised advertisement Co1 as the improvement.

[0065] Furthermore, in the example shown in Figure 7, the reason for the prediction is shown instead of the changes in Figure 6. For example, the reason for the prediction is the reason for predicting the predicted CTR, and is created by the explainable AI described above. In this case, by including the reason for the prediction in the improvement content, the proposal unit 135 enables the ad creator to improve the ad more efficiently.

[0066] [3. Processing Flow] Next, the processing flow executed by the information processing device 100 according to the embodiment will be described using Figure 8. Figure 8 is a flowchart of an example of the proposed processing according to the embodiment.

[0067] As shown in Figure 8, the information processing device 100 obtains the original advertisement from, for example, the manufacturer's terminal 50 (step S101). Subsequently, the information processing device 100 generates multiple modified advertisements, each with different characteristics, based on the original advertisement (step S102).

[0068] Next, the information processing device 100 estimates the advertising effectiveness of the original advertisement and the multiple modified advertisements (step S103). Then, the information processing device 100 proposes improvements based on the effectiveness of each advertisement (step S104). Finally, the information processing device 100 terminates the process.

[0069] [4. Variations] The embodiments described above describe a case where the content is image content related to an advertisement, but the invention is not limited to this. For example, the content may be video content, audio content, VR, or 3D digital content such as VR.

[0070] Furthermore, for example, the information processing device 100 may generate modified content, such as altering the makeup, clothing, and hairstyle of the advertising talent appearing in the advertisement, and suggest improvements.

[0071] Furthermore, while the above-described embodiment described the case where the advertising effect is measured by CTR, it is not limited to this. The advertising effect may also be measured by other indicators such as sales, profit margins, or buzz on social media.

[0072] [5. Effects] As described above, the information processing device 100 according to the present invention comprises a content generation unit 133 that generates modified content with altered content characteristics, an estimation unit 134 that estimates the advertising effect of the modified content generated by the content generation unit 133, and a proposal unit 135 that proposes content improvements based on the advertising effect estimated by the estimation unit 134.

[0073] Furthermore, the content generation unit 133 generates multiple modified content pieces, each with altered characteristics, and the proposal unit 135 proposes improvements based on the modifications to the modified content that are estimated to have a higher advertising effect than the original content.

[0074] Furthermore, the content generation unit 133 generates modified content by changing at least one of the text or images within the content. Additionally, the content generation unit 133 generates modified content by changing at least one of the size, position, or content of multiple texts or multiple images within the content.

[0075] Furthermore, the content generation unit 133 generates modified content by changing at least one of the following: the content of the text within the content, the number of characters, the proportion of the text area within the content, its position, its color, or the content, size, position, or color of an image. Also, when generating modified content by changing the content of the text within the content, the content generation unit 133 changes the content of the text that satisfies predetermined conditions, and leaves the content of the text that does not satisfy the predetermined conditions unchanged.

[0076] Furthermore, the estimation unit 134 estimates the advertising effect based on the target user group of the content and the industry of the advertiser. The estimation unit 134 also estimates the advertising effect based on the advertising purpose of the content. In addition, the information processing device 100 includes a model generation unit 132 that generates a model that has learned the relationship between the characteristics of the content and the advertising effect, and the estimation unit 134 uses the model generated by the model generation unit 132 to estimate the advertising effect.

[0077] Furthermore, the model generation unit 132 generates a model for each user attribute of the content viewer, the estimation unit 134 estimates the advertising effect using the model generated for each user attribute, and the proposal unit 135 proposes content improvements for each user attribute.

[0078] Furthermore, the model generation unit 132 generates a model for each distribution platform where the content is delivered to users, the estimation unit 134 estimates the advertising effect using the model generated for each distribution platform, and the proposal unit 135 proposes content improvements for each distribution platform. The estimation unit 134 estimates the click probability of the content being clicked as part of the advertising effect.

[0079] Through any or a combination of the above-described processes, the information processing device according to the present invention can propose improvements to enhance advertising effectiveness.

[0080] [6. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 9. Figure 9 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0081] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The arithmetic unit 1030 can be implemented using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array).

[0082] The primary storage device 1040 is a memory device, such as RAM (Random Access Memory), that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and can be implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. The secondary storage device 1050 may also be a removable storage medium such as a USB memory stick or an SD (Secure Digital) memory card. Furthermore, the secondary storage device 1050 may be cloud storage (online storage), NAS (Network Attached Storage), a file server, etc.

[0083] The output I / F 1060 is an interface for transmitting information to be output to output devices 1010, such as displays, projectors, and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input I / F 1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, keypads, buttons, and scanners, and is implemented using, for example, USB.

[0084] Furthermore, the output interface 1060 and input interface 1070 may be wirelessly connected to the output device 1010 and input device 1020, respectively. In other words, the output device 1010 and input device 1020 may be wireless devices.

[0085] Furthermore, the output device 1010 and the input device 1020 may be integrated as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as an input / output I / F.

[0086] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0087] The network interface 1080 receives data from other devices via network N and sends it to the computing unit 1030, and also transmits data generated by the computing unit 1030 to other devices via network N.

[0088] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output interface 1060 and the input interface 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0089] For example, when computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the primary storage device 1040. Alternatively, the arithmetic unit 1030 of computer 1000 may load a program obtained from another device via the network interface 1080 onto the primary storage device 1040 and execute the loaded program. Furthermore, the arithmetic unit 1030 of computer 1000 may cooperate with other devices via the network interface 1080 and call and use program functions, data, etc., from other programs on other devices.

[0090] [6. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0091] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0092] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0093] For example, the information processing device 100 described above may be implemented using multiple server computers, and depending on the function, it may be implemented by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, allowing for flexible configuration changes.

[0094] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0095] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of symbols]

[0096] 50 Maker terminal 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Extraction Model Database 122 Distribution History Database 123 CTR Estimation Model Database 124 Explainable AI Database 130 Control Unit 131 Acquisition Department 132 Model Generation Unit 133 Content Generation Department 134 Estimation Department 135 Proposal Department

Claims

1. A content generation unit that generates modified content with altered ad features, A model generation unit that generates a model that learns the relationship between the characteristics of the advertisement and the advertising effect, An estimation unit that estimates the advertising effect of the modified content generated by the content generation unit using the model generated by the model generation unit, Based on the advertising effect estimated by the estimation unit, the proposal unit proposes, for each modified content, the reasons for the estimation of the advertising effect by the model based on the changes from the original advertisement, as improvements to the advertisement. An information processing device characterized by comprising:

2. The content generation unit, Multiple modified content pieces are generated, each with a different characteristic of the aforementioned advertisement. The aforementioned proposal section is, To propose as improvements changes to the modified content that are estimated to have a higher advertising effect than the aforementioned advertisement. The information processing apparatus according to claim 1, characterized by the following:

3. The content generation unit, To generate modified content by changing at least one of the text or images within the advertisement. The information processing apparatus according to claim 1, characterized by the following:

4. The content generation unit, To generate modified content in which at least one of the size, position, or content of multiple texts or multiple images within the advertisement has been changed. The information processing apparatus according to claim 3, characterized by the following:

5. The content generation unit, To generate modified content by changing at least one of the following: the content of the text in the advertisement, the number of characters, the proportion of the text area in the advertisement, its position, its color, or the content, size, position, or color of the image. The information processing apparatus according to claim 3 or 4, characterized by the above.

6. The content generation unit, When generating the modified content by changing the text content within the advertisement, the text content that satisfies the predetermined conditions is changed, and the text content that does not satisfy the predetermined conditions is not changed. The information processing apparatus according to claim 3 or 4, characterized by the above.

7. The estimation unit, To estimate the effectiveness of the advertisement based on either the target user group of the advertisement or the industry of the advertiser. The information processing apparatus according to claim 1, characterized by the following:

8. The estimation unit, To estimate the advertising effect based on the advertising objective of the aforementioned advertisement. The information processing apparatus according to claim 1, characterized by the following:

9. The aforementioned model generation unit, The aforementioned model is generated for each attribute of the user who views the aforementioned advertisement. The estimation unit, Using the model generated for each user attribute, the advertising effect is estimated. The aforementioned proposal section is, To propose improvements to the advertisement for each of the user's attributes. The information processing apparatus according to claim 1, characterized by the following:

10. The aforementioned model generation unit, The aforementioned model is generated for each distribution platform where the aforementioned advertisement is delivered to the user. The estimation unit, Using the model generated for each distribution platform, the advertising effect of the modified content is estimated. The aforementioned proposal section is, To propose improvements to the aforementioned advertisement for each of the aforementioned distribution channels. The information processing apparatus according to claim 8 or 9, characterized by the above.

11. The estimation unit, As part of the advertising effect, the click-through rate of the advertisement is estimated. The information processing apparatus according to claim 1, characterized by the following:

12. A method of information processing performed by a computer, A content generation process that generates modified content with altered ad features, A model generation process that generates a model that learns the relationship between the characteristics of the advertisement and the advertising effect, An estimation step in which the advertising effect of the modified content generated by the content generation step is estimated using the model generated by the model generation step, Based on the advertising effect estimated by the estimation step, the proposal step proposes, for each modified content, the reasons for the estimation of the advertising effect by the model based on the changes from the original advertisement, as improvements to the advertisement. An information processing method characterized by including

13. Content generation procedure for generating modified content with altered ad features, A model generation procedure for generating a model that learns the relationship between the characteristics of the aforementioned advertisement and the advertising effect, An estimation procedure for estimating the advertising effect of the modified content generated by the content generation procedure using the model generated by the model generation procedure, Based on the advertising effect estimated by the estimation procedure described above, a proposal procedure is provided to suggest, for each modified content, the reasons for the estimation of the advertising effect by the model based on the changes from the original advertisement, as improvements to the advertisement. An information processing program characterized by causing a computer to execute it.

Images