Information providing device, information providing method, and information providing program

Abstract

To enable an advertiser to grasp advertisements provided to users in a system for generating advertisements using a terminal device.SOLUTION: An information provision device disclosed herein comprises an acquisition unit for acquiring feature information on advertisement of a specified target generated by a terminal device configured to generate and provide the advertisement of the specified target using an advertisement generation model trained to generated an advertisement of a specified target using user information on a user, a generation unit configured to generate a report showing a result of providing the advertisement of the target based on the feature information acquired by the acquisition unit, and a provision unit for providing the report generated by the generation unit.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information providing device, an information providing method, and an information providing program. [Background technology]

[0002] Conventionally, advertisement distribution via the Internet has been popular. As a technology related to advertisement distribution, a technology for distributing advertisements tailored to users based on log information of users accumulated on a server has been disclosed (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-051391 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional technologies, there is a problem that it is difficult to deliver appropriate advertisements to users because the user information that can be acquired by the server is being limited in order to protect personal information. For example, one possible solution is to generate advertisements on the user terminal side using user information stored in the user terminal. However, when advertisements are generated on the user terminal, it is difficult for advertisers to understand what kind of advertisements will be generated.

[0005] The present invention has been made in consideration of the above, and aims to provide an information providing device, an information providing method, and an information providing program that can allow advertisers to understand advertisements provided to users in a system that generates advertisements on a terminal device. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the information providing device of the present invention generates an advertisement for a specified target using an advertisement generation model that has been trained to generate an advertisement for the specified target using user information about a user, and includes: an acquisition unit that acquires characteristic information of the advertisement generated on a terminal device that provides the generated advertisement; a generation unit that generates a report indicating the results of providing the advertisement for the target based on the characteristic information acquired by the acquisition unit; and a provision unit that provides the report generated by the generation unit. [Effects of the Invention]

[0007] According to the present invention, in a system that generates advertisements on a terminal device, it is possible to allow an advertiser to understand the advertisements provided to users. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an overview of the information providing process according to the embodiment. [Figure 3] FIG. 3 is a block diagram illustrating an example of the configuration of the information providing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of an advertisement information database according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a statistical information database according to the embodiment. [Figure 6] FIG. 6 is a block diagram illustrating an example of the configuration of a user terminal according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a log information storage unit according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a camera image storage unit according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of an advertisement information storage unit according to the embodiment. [Figure 10]FIG. 10 is a flowchart illustrating an example of a processing procedure executed by the information providing device according to the embodiment. [Figure 11] FIG. 11 is a flowchart illustrating an example of a processing procedure executed by the user terminal according to the embodiment. [Figure 12] FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information providing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, the information providing device, the information providing method, and the information providing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information providing device, the information providing method, and the information providing program according to the present application are not limited to these embodiments. Furthermore, the embodiments can be appropriately combined as long as the processing contents are not contradictory. Furthermore, the same components in the following embodiments are denoted by the same reference numerals, and redundant explanations will be omitted.

[0010] [1. Overview of Information Processing] FIG. 1 is a diagram showing an example of information processing according to the embodiment, and the information providing processing according to the embodiment is executed by an information providing device 1 shown in FIG.

[0011] 1 includes an information providing device 1, a user terminal 10, and a plurality of advertiser terminals 100. The information providing device 1 provides advertising information related to the requested advertisement to each user terminal 10 based on advertisement distribution requests received from the plurality of advertiser terminals 100. For example, the information providing device 1 is realized by a cloud, a server, or the like.

[0012] Furthermore, the user terminal 10 shown in FIG. 1 is a terminal device owned by a user U, such as a smartphone. As shown in FIG. 1, the user terminal 10 has an advertisement generation model and an advertisement evaluation model. The advertisement generation model is a model trained to generate advertisements for specified targets, such as an image generation AI. For example, the advertisement generation model generates an AI image according to input text information (e.g., context). Furthermore, the advertisement evaluation model is a model trained to estimate an advertisement evaluation by a user U.

[0013] The user terminal 10 repeatedly executes both processes related to advertisement generation and advertisement evaluation within the user terminal 10. As a result, the user terminal 10 can optimize the advertisements provided to the user U.

[0014] For example, the advertisement generation model and the advertisement evaluation model are configured by generative adversarial networks (GANs). For example, the advertisement generation model is corrected based on the evaluation results of the advertisement evaluation model, and the advertisement evaluation model is corrected based on the generation results of the advertisement generation model.

[0015] For example, the advertisement generation model is modified to improve the evaluation results of the advertisement evaluation model, and the advertisement evaluation model is modified to evaluate the content generated by the advertisement generation model more strictly. For example, in this case, the advertisement evaluation model is modified so that an advertisement that the user U has rated as good is given a lower score than the previous time, resulting in an evaluation that more strongly reflects the preferences of the user U. In this way, the user terminal 10 can provide advertisements that are optimized for the user U by performing on-device learning.

[0016] For example, the advertisement evaluation model may also learn the timing of advertisement presentation. For example, the same advertisement may be presented at multiple times, and the timing at which the user U rated it as good and the timing at which the user U rated it as bad may be learned. Furthermore, the advertisement evaluation model may, for example, calculate the score of each advertisement generated by the advertisement generation model as needed, and present the corresponding advertisement to the user when the calculated score exceeds a threshold, or may set presentation conditions for each advertisement in advance, and present the corresponding advertisement when the presentation conditions are met.

[0017] The advertiser terminal 100 is a terminal device of each advertiser. For example, the advertiser operates the advertiser terminal 100 and requests the information providing device 1 to distribute an advertisement (step S1).

[0018] Here, the delivery request includes information about the advertising target, material information that will be used as material for the advertisement, trend information about advertising trends, etc. The material information includes the company name, product name, logo image, product image, etc., and the trend information includes information about the image and atmosphere of the advertisement, etc. As will be described later, the user terminal 10 can also generate advertisements using camera images, etc., and in this case the delivery request includes trend information that indicates the trend of the image to be combined with the advertising target.

[0019] The information providing device 1 provides advertising information to the user terminal 10 based on the distribution requests received from each advertiser (step S2). The advertising information includes, for example, information on material information, advertising trend information, etc. The user terminal 10 generates an advertisement using an advertisement generation model based on the advertising information received from the information providing device 1 and the user information held by the user terminal 10 (step S3).

[0020] Next, the user terminal 10 evaluates the generated advertisement using an advertisement evaluation model (step S4). For example, the advertisement evaluation model is a model that learns a person model of the user U, such as the tendencies, type, advertising preferences, and effectiveness tendencies of the user U, using various user information stored in the user terminal 10, and is a model that is trained so that an advertisement that is estimated to be highly appealing to the user U will have a high score.

[0021] The advertisement evaluation model can also evaluate the advertisement AD provided to the user U, for example, based on the relationship between the user information before and after the advertisement is provided. The advertisement evaluation model can also update the score according to the ambient environment of the user terminal 10. For example, when the ambient temperature is high, the advertisement evaluation model updates the score for the beer advertisement that is the advertised target to a relatively high value.

[0022] Then, the user terminal 10 provides the advertisement AD to the user U, for example, when the score related to the advertisement exceeds a predetermined value (step S5). For example, as shown in FIG. 1, the advertisement AD includes an AI image G and text T generated by the advertisement generation model, and a material image P requested by the advertiser. The advertisement AD may be an image-format advertisement or a video-format advertisement. The advertisement AD may also include music.

[0023] The user terminal 10 can also generate an advertisement AD including a camera image taken by the user terminal 10 and provide it to the user U. In this case, since each user terminal 10 holds a different camera image, each user terminal 10 can provide an advertisement AD using a different camera image.

[0024] In particular, when providing advertising AD using camera images, it is possible to provide advertising AD that incorporates user U's past experiences and memories, etc., making it possible to provide advertising AD that is more familiar to user U.

[0025] Thereafter, the user terminal 10 measures the performance of the advertisement AD using log information such as the behavior history of the user U acquired after the advertisement AD is provided (step S6). The user terminal 10 measures the performance of the advertisement AD according to a change in the behavior of the user U regarding the advertisement target before and after the advertisement AD is provided.

[0026] Thereafter, the user terminal 10 provides the information providing device 1 with statistical information that the information providing device 1 needs to bill the advertiser for expenses, etc. (step S7). For example, the statistical information is minimum information such as information about the feature quantities of the advertisement AD and the results of performance measurement, and does not include sensitive information that could identify the individual user U.

[0027] That is, the user terminal 10 does not provide sensitive information such as log information of the user U to the information providing device 1. This makes it possible to protect the personal information of the user U. Note that the feature amount of the advertisement AD is a feature vector indicating the feature amount of the advertisement AD, but may also be, for example, text indicating the feature of the advertisement AD.

[0028] The information providing device 1 generates a report by aggregating the statistical information acquired from each user terminal 10 (step S8), and provides the generated report to each advertiser terminal 100 (step S9).

[0029] For example, the report includes information on the distribution of the feature amounts of each advertisement AD, its center of gravity, the distribution of scores related to the performance of each advertisement AD, etc. This allows the advertiser to understand the status of the advertisement AD provided to each user terminal 10 and the performance of the advertisement AD.

[0030] Next, an outline of the information provision process according to the embodiment will be further described with reference to Fig. 2. Fig. 2 is a diagram showing an outline of the information provision process according to the embodiment. As described above, in the advertisement delivery system S according to the embodiment, an advertisement AD is generated in each user terminal 10, so the advertiser cannot know what advertisement AD has been provided to the user U.

[0031] Therefore, the information providing device 1 generates a report on the results of providing the advertisement AD provided to each user terminal 10 and provides the report to the advertiser. Specifically, as shown in Fig. 2, the information providing device 1 acquires feature information from each user terminal 10 (step S11).

[0032] The feature information is information about the features of the advertisement AD generated by each user terminal 10, and is, for example, text obtained by verbalizing the advertisement AD using a model that verbalizes an N-dimensional vector or image.

[0033] Then, the information providing device 1 classifies the characteristic information acquired from each user terminal 10 into each advertising target and clusters the characteristic information for each advertising target. At this time, the information providing device 1 may cluster the characteristic information for each group classified according to the attributes of the users, for example.

[0034] Next, the information providing device 1 generates a report based on the clustering result (step S12). For example, the report may include an image (advertisement) corresponding to the center of gravity of the feature amount of the advertisement AD in each group obtained from the clustering result, a scatter plot of the feature amount, the number of times the advertisement AD is provided, etc.

[0035] Then, the information providing device 1 provides the generated report to the corresponding advertiser terminal 100 (step S13). This allows the advertiser to know what advertisements AD have been provided to each user terminal 10.

[0036] In this way, the information providing device 1 according to the embodiment provides a report to the advertiser based on the characteristic information acquired from each user terminal 10. Therefore, the information providing device 1 according to the embodiment allows the advertiser to understand the advertisement provided to the user in a system that generates advertisements in a terminal device. Furthermore, since the information providing device 1 generates a report from information (characteristic information) that abstracts the advertisement AD in this series of processes, it is possible to protect the personal information of the user U.

[0037] [2. Example of information provision device configuration] Next, a configuration example of the information providing device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 2 is a block diagram showing a configuration example of the information providing device 1 according to the embodiment. As shown in Fig. 2, the information providing device 1 according to the embodiment includes a communication unit 2, a storage unit 3, and a control unit 4.

[0038] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0039] The storage unit 3 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 also has an advertisement information database 31, a statistical information database 32, and a model database 33.

[0040] The advertisement information database 31 is a database that stores advertisement information. Fig. 4 is a diagram showing an example of the advertisement information database 31 according to the embodiment. As shown in Fig. 4, the advertisement information database 31 stores information items such as "advertiser ID," "advertising target," "material information," "trend information," and "target information" in association with each other.

[0041] "Advertiser ID" is an identifier used to identify the advertiser. "Advertising target" is the store, brand, event, product, or service that is the subject of the advertisement. "Material information" is information about the materials used in the advertisement. For example, material information includes product images, images of the advertiser's logo or character, images of celebrities featured in the advertisement, and music used in the advertisement.

[0042] "Trend information" is information about advertising trends specified by the advertiser. For example, trend information includes the image the advertiser wants from the advertisement and the advertiser's brand image. "Target information" is information about the user demographic that is the target of the advertisement specified by the advertiser.

[0043] Returning to the explanation of Fig. 3, the statistical information database 32 will be described. The statistical information database 32 is a database that stores statistical information. Fig. 5 is a diagram showing an example of the statistical information database 32 according to the embodiment.

[0044] As shown in FIG. 5, the statistical information database 32 according to the embodiment stores information on items such as "advertising target," "number of times provided," "KPI (Key Performance Indicator)," and "advertising feature amount" in association with each other.

[0045] The "advertising target" is the product or service that is the target of the advertisement, similar to the "advertising target" shown in Fig. 4. The "number of times provided" is the number of times an advertisement related to the corresponding advertising target has been provided to the user terminal 10.

[0046] The "KPI" is an index showing the performance of the corresponding advertising target by the advertising AD, and is, for example, a statistical value of the performance of the advertising AD provided to each user terminal 10. The "advertising feature amount" is a statistical value of the feature amount of the advertising AD provided to each user terminal 10.

[0047] Returning to the explanation of Fig. 3, the model database 33 will be described. The model database 33 is a database that stores each model. For example, the model database 33 stores models required when generating advertisements at each user terminal 10, such as advertisement generation models and advertisement evaluation models.

[0048] The model database 33 also stores an estimation model that estimates KPIs and advertisements generated by each user terminal 10 from the content of a distribution request made by an advertiser. For example, the estimation model is a simulation model that estimates KPIs based on the content of a distribution request using multiple virtually set personas. The estimation model may also be a model that learns the relationship between the request content and the feature quantities of advertisements AD actually provided to the user terminal 10. In this case, the estimation model is a simulation model that estimates advertisements AD provided to each user terminal 10 from the request content.

[0049] Next, we will explain the control unit 4. The control unit 4 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, executing various programs stored in a storage device inside the information providing device 1 using RAM as a working area.

[0050] As shown in FIG. 3, the control unit 4 includes a receiving unit 41, an acquiring unit 42, a learning unit 43, a generating unit 44, and a providing unit 45.

[0051] The reception unit 41 receives a distribution request for an advertisement from the advertiser terminal 100. For example, the reception unit 41 registers information relating to the distribution request for an advertisement from the advertiser terminal 100 in the advertisement information database 31.

[0052] The acquisition unit 42 acquires statistical information related to the advertisement AD from each user terminal 10 and registers it in the statistical information database 32. The statistical information includes information related to the advertising targets of the advertisement AD, information related to the number of times each advertising target is served, information related to the characteristics of each advertisement AD, information related to the effectiveness of each advertisement, etc.

[0053] The learning unit 43 learns each model to be provided to the user terminal 10. For example, the learning unit 43 learns an advertisement generation model and an advertisement evaluation model. The advertisement generation model and the advertisement evaluation model are learned using a known method.

[0054] The generation unit 44 generates advertising AD to be generated in each user terminal 10 in response to advertising requests from each advertiser. For example, the generation unit 44 generates advertising AD by inputting advertising materials and user information specified by the advertising request into an advertising generation model. At this time, the generation unit 44 appropriately changes various parameters related to the user information and then generates advertising AD for each user attribute.

[0055] The advertisement AD generated by the generation unit 44 is provided to the advertiser terminal 100 via the provision unit 45. This allows the advertiser to know in advance what kind of advertisement AD will be provided to each user terminal 10.

[0056] In addition, the generation unit 44 generates a report or the like regarding the results of providing the advertisement AD to the advertiser. For example, the generation unit 44 generates a report for each advertiser based on various statistical information stored in the statistical information database 32.

[0057] For example, the generation unit 44 generates a report including information regarding the number of times the advertisement AD is provided, KPI, advertisement feature amount, etc. More specifically, the generation unit 44 generates, as a report, a centroid image that is the center of gravity of the advertisement feature amount estimated from the feature information, a scatter diagram showing the distribution status of the advertisement feature amount, verbalized information (text) that verbalizes the features of the image used in the advertisement, etc.

[0058] The generation unit 44 can generate the center of gravity image by using, for example, an image generation model that generates an image from feature amounts. At this time, the generation unit 44 generates a report for each group into which each user is classified according to their attributes.

[0059] In addition, the generation unit 44 may, for example, identify an advertisement AD having features similar to the features of an image specified from the advertiser terminal 100, and generate a report regarding the number of times the identified advertisement AD has been provided and the attributes of the users to whom it has been provided.

[0060] The providing unit 45 provides various information to each user terminal 10 and the advertiser terminal 100. For example, the providing unit 45 provides each model to the user terminal 10, and then provides advertising information in response to a request from the advertiser. In this case, the providing unit 45 may provide common advertising information to all user terminals 10, or may provide different advertising information to each user terminal 10. For example, if the advertising target is alcoholic beverages, the providing unit 45 provides corresponding advertising information to the user terminal 10 of user U who is over the age of adulthood. Note that the selection of advertising targets may be performed on the user terminal 10 side.

[0061] Furthermore, the providing unit 45 provides various information generated by the generating unit 44 to the advertiser terminal 100. For example, when an advertiser makes a distribution request, the providing unit 45 provides information about the advertisement AD for each user attribute.

[0062] Furthermore, after the advertisement AD is provided by the user terminal 10, the providing unit 45 provides the report generated by the generating unit 44 to the advertiser terminal 100. This allows the advertiser to grasp the effectiveness of the advertisement AD and the advertisement AD after the fact.

[0063] [3. Example of user terminal configuration] Next, a configuration example of the user terminal 10 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing a configuration example of the user terminal 10 according to the embodiment. As shown in Fig. 6, the user terminal 10 according to the embodiment includes a communication unit 110, a storage unit 120, and a control unit 130. The user terminal 10 also includes a display unit 111, an operation unit 112, a camera 113, a speaker 114, and a group of sensors 115.

[0064] The communication unit 110 is realized by, for example, a network interface card (NIC), etc. The communication unit 110 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0065] The display unit 111 displays images or videos input from the control unit 130. The operation unit 112 accepts various operations from the user U. The display unit 111 and the operation unit 112 are realized by, for example, a touch panel display.

[0066] The camera 113 is a camera mounted on the user terminal 10. The camera 113 includes, for example, an outer camera that takes pictures outside the screen and an inner camera that takes pictures inside the screen.

[0067] The speaker 114 outputs audio input from the control unit 130. The sensor group 115 includes various sensors mounted on the user terminal 10. For example, the sensor group includes an illuminance sensor, a barometric pressure sensor, a temperature sensor, a step count sensor, a G sensor, a sound collection sensor, Lidar, etc. The user terminal 10 may be linked (paired) with sensors mounted on a wearable device worn by the user U, for example, to acquire various information related to the user U's heart rate, body temperature, stress, sleep status, etc.

[0068] The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 also has a log information storage unit 121, a camera image storage unit 122, a material information storage unit 123, an advertisement generation model storage unit 124, an advertisement information storage unit 125, and an advertisement evaluation model storage unit 126.

[0069] The log information storage unit 121 stores various log information related to the behavior history of the user U. Fig. 7 is a diagram showing an example of the log information storage unit 121 according to the embodiment. As shown in Fig. 7, the log information storage unit 121 stores information items such as "date and time," "log information," "location information," and "environment information" in association with each other.

[0070] The "date and time" is the date and time when the user U performed the action corresponding to the log information. The "log information" is the behavior history of the user U. Here, the log information includes, for example, the operation history and browsing history of the user terminal 10 by the user U. The log information may also be, for example, the behavior history of the user U. The user terminal 10 can estimate the behavior history of the user U by acquiring camera images from the camera 113 and analyzing the camera images. The log information may also include the payment history of a payment app, such as cashless payment (for example, QR code (registered trademark) payment) using the user terminal 10.

[0071] "Location information" is information about the location where user U performed the corresponding action. "Environment information" is information about the surrounding environment when user U performed the corresponding action. For example, environmental information includes information such as temperature, humidity, illuminance, and air pressure, surrounding sounds (music and conversations), and information about the operating status of home appliances (e.g., air conditioning equipment such as coolers). Note that information about the operating status of home appliances can be obtained, for example, from a smart speaker that is linked to the home appliance.

[0072] The user terminal 10 may also estimate environmental information by capturing an image of the surroundings with the camera 113. For example, the user terminal 10 may estimate the posture, clothing, belongings, surrounding people, surrounding objects, etc. of the user U and include them in the environmental information.

[0073] Returning to the description of Fig. 6, the camera image storage unit 122 will be described. The camera image storage unit 122 stores camera images captured by the camera 113. Fig. 8 is a diagram showing an example of the camera image storage unit 122 according to the embodiment.

[0074] As shown in FIG. 8, the camera image storage unit 122 stores information items such as "image ID," "photographing date and time," "photographing location," "image information," "subject information," and "photographing environment" in association with one another.

[0075] "Image ID" is an identifier for identifying each camera image. "Photographed date and time" and "Photographed location" are the photographed date and time and the photographed location of the camera image identified by the corresponding camera ID.

[0076] "Image information" is image information of a camera image identified by the corresponding camera ID. "Subject information" is information about a subject captured in a camera image identified by the corresponding camera ID.

[0077] "Shooting environment" is information about the environment when the camera image identified by the corresponding camera ID was taken. For example, "environmental information" is information about the surrounding environment when the camera image was taken, including information such as temperature, humidity, illuminance, and air pressure, as well as information about sounds (music and conversations) playing in the surroundings.

[0078] Returning to the explanation of Fig. 6, the material information storage unit 123 will be described. The material information storage unit 123 stores material information. For example, the material information is information that serves as material when generating an advertisement AD in the user terminal 10, and includes product images for each advertisement target, logo images and character images of advertisers, images of celebrities featured in advertisements, music used in advertisements, and the like.

[0079] The advertisement generation model storage unit 124 stores an advertisement generation model. The advertisement generation model is a model that has been trained to generate advertisements for specified targets based on user information held by the user terminal 10.

[0080] The advertisement information storage unit 125 stores advertisement information. The advertisement information includes information about advertisements generated by the advertisement generation model and information about evaluations of the corresponding advertisements. Fig. 9 is a diagram illustrating an example of the advertisement information storage unit 125 according to the embodiment.

[0081] As shown in FIG. 9, the advertisement information storage unit 125 stores information items such as "advertisement ID," "advertisement target," "advertisement type," "advertisement information," "feature amount," "provision conditions," and "evaluation information" in association with each other.

[0082] The "advertising ID" is an identifier for identifying each advertising AD. The "advertising target" is the advertising target of the advertising AD identified by the corresponding advertising ID. The "advertising type" is the type of advertising AD identified by the corresponding advertising ID. For example, the "advertising type" includes banner ads, text ads, search-related ads, etc.

[0083] "Advertising information" is the advertising information (data body) of the advertising AD identified by the corresponding advertising ID. "Features" are the features of the advertising AD identified by the corresponding advertising ID, such as a vector according to the feature or text indicating the features of the advertising AD.

[0084] The "provision conditions" are conditions for providing the advertisement AD identified by the corresponding advertisement ID to the user U. The "evaluation information" is evaluation information for the advertisement AD identified by the corresponding advertisement ID. For example, various indicators such as KPIs are used as the evaluation information.

[0085] Returning to the explanation of Fig. 6, the advertisement evaluation model storage unit 126 will be explained. The advertisement evaluation model storage unit 126 stores an advertisement evaluation model. The advertisement evaluation model is a model for evaluating an advertisement AD generated by the advertisement generation model.

[0086] Next, we will explain the control unit 130. The control unit 130 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, executing various programs stored in a storage device inside the user terminal 10 using RAM as a working area.

[0087] As shown in FIG. 6, the control unit 130 includes a receiving unit 131, an analyzing unit 132, a processing unit 133, and a providing unit 134.

[0088] The receiving unit 131 acquires information about each model from the information providing device 1 via the communication unit 110. Each model includes an advertisement generation model, an advertisement evaluation model, and the like.

[0089] Furthermore, the reception unit 131 acquires each piece of advertisement information from the information providing device 1 via the communication unit 110. The advertisement information includes, for example, information related to materials used in the advertisement, the image of the advertisement, and the conditions for generating the advertisement.

[0090] The analysis unit 132 analyzes user information (e.g., log information) related to the user obtained by the user terminal 10. For example, the analysis unit 132 analyzes camera images captured by the camera 113. For example, the analysis unit 132 analyzes the subject appearing in the camera image by image analysis of the camera image. For example, the subject includes the person, facial expression, clothing, belongings, surrounding circumstances, etc. appearing in the camera image.

[0091] The analysis unit 132 also analyzes the surrounding environment of the user terminal 10 based on various information input from the sensor group 115. For example, the surrounding environment includes temperature, illuminance, air pressure, humidity, surrounding sounds, and the like.

[0092] Furthermore, the analysis unit 132 analyzes various data stored in the user terminal 10 and generates log information relating to the operation history and behavioral history of the user terminal 10 by the user U. Note that the user terminal 10 may capture images of the surroundings in the background using the camera 113, and the analysis unit 132 may analyze the behavioral history of the user U by analyzing the camera images.

[0093] Furthermore, the analysis unit 132 may, for example, take a picture of the display screen of the display unit 111 in the background and analyze the message sending and receiving history. Furthermore, the analysis unit 132 may analyze the mental state of the user U based on various information input from a wearable device worn by the user U.

[0094] The processing unit 133 executes various processes related to the advertisement generation model and the advertisement evaluation model. As described above, the advertisement generation model and the advertisement evaluation model are configured by generative adversarial networks (GANs).

[0095] At this time, the processing unit 133 generates advertisements using the advertisement generation model and evaluates advertisements using the advertisement evaluation model. The advertisement generation model may generate advertisements related to an arbitrarily selected advertising target, or may generate advertisements related to an advertising target instructed by the advertisement evaluation model, etc. The advertisement generation model can also generate advertisements AD using camera images.

[0096] Furthermore, the processing unit 133 evaluates the performance of the advertisement AD based on the log information after the advertisement AD is provided. For example, the performance of the advertisement AD is evaluated based on various indices such as KPI.

[0097] The providing unit 134 provides the advertisement AD generated by the advertisement generation model to the user U. The statistical information is minimum information such as information on the feature quantities of the advertisement AD provided to the user U and the results of performance measurement, and does not include sensitive information that could identify the individual user U.

[0098] That is, the providing unit 134 can protect the personal information of the user U by providing only the minimum information related to the advertisement AD provided to the user U to the information providing device 1 as statistical information.

[0099] [4. Processing flow] Next, a processing procedure executed by the information providing device 1 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of a processing procedure executed by the information providing device 1 according to the embodiment.

[0100] 10, first, the information providing device 1 receives a distribution request for an advertisement from the advertiser terminal 100 (step S101). Next, the information providing device 1 provides advertisement information to each user terminal 10 (step S102).

[0101] Thereafter, the information providing device 1 collects statistical information on the advertisements AD from the user terminals 10 (step S103), and generates a report for each advertiser based on the collected statistical information (step S104).

[0102] Then, the information providing device 1 provides the report generated for each advertiser to the corresponding advertiser terminal 100 (step S105), and ends the process.

[0103] Next, a processing procedure executed by the user terminal 10 will be described with reference to Fig. 11. Fig. 11 is a flowchart showing an example of a processing procedure executed by the user terminal 10 according to the embodiment.

[0104] As shown in FIG. 11, the user terminal 10 acquires advertisement information from the information providing device 1 (step S201). Next, the user terminal 10 generates an advertisement and evaluates the advertisement (step S202). Next, the user terminal 10 provides the advertisement (step S203) and transmits characteristic information of the provided advertisement to the information providing device 1 (step S204). Then, the user terminal 10 ends the process.

[0105] [5. Modifications] In the above-described embodiment, the user terminal 10 generates the advertisement AD to be provided to the user U, but the present invention is not limited to this. For example, the user terminal 10 may generate various contents such as videos using the method of the present invention.

[0106] [6. Effects] The information providing device 1 according to the embodiment described above generates an advertisement for a specified target using an advertisement generation model trained to generate an advertisement for the specified target using user information about the user, and includes an acquisition unit 42 that acquires characteristic information of the advertisement generated on a user terminal 10 (terminal device) from the terminal device to which the generated advertisement is provided, a generation unit 44 that generates a report indicating the results of providing the advertisement for the target based on the characteristic information acquired by the acquisition unit 42, and a provision unit 45 that provides the report generated by the generation unit 44.

[0107] The generation unit 44 also generates a centroid image, which is the centroid of the feature quantities of the advertisement estimated from the feature information. The generation unit 44 also generates a scatter diagram showing the distribution of the feature quantities of the advertisement based on the feature information. The generation unit 44 also generates a report for each group into which users are classified according to their attributes.

[0108] The generation unit 44 also generates verbalized information that verbalizes the characteristics of the image used in the advertisement as a report. When a predetermined image is input, the generation unit 44 identifies an advertisement that has similar characteristics to the image and generates a report about the advertisement.

[0109] By performing any one or a combination of the above-described processes, the information providing device 1 according to the present invention can allow the advertiser to understand the advertisement provided to the user in the system that generates the advertisement in the terminal device.

[0110] [7. Hardware Configuration] The information providing device 1 and the user terminal 10 according to the above-described embodiment are realized by, for example, a computer 1000 configured as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information providing device 1 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0111] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0112] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0113] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 12, the output devices and input devices are collectively referred to as "input / output devices") via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0114] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0115] For example, when the computer 1000 functions as the user terminal 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0116] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0117] [8. Other] Furthermore, among the processes described in the above embodiments and modifications, 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 using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0118] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0119] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0120] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0121] 1 Information provision device 10 User terminal 31 Advertising Information Database 32 Statistical Information Database 33 Model Database 41 Reception 42 Acquisition Department 43 Learning Department 44 Generation part 45 Providing Department 100 advertiser terminals 121 Log information storage unit 122 Camera image storage unit 123 Material information storage unit 124 Ad generation model memory unit 125 Advertising information storage unit 126 Advertising evaluation model memory unit 130 control section 131 Reception 132 Analysis Department 133 Processing section 134 Provision Department U User

Claims

1. an acquisition unit that generates a specified target advertisement using an advertisement generation model that has been trained to generate a specified target advertisement using user information related to a user, and acquires, from a terminal device that provides the generated advertisement, feature information of the advertisement generated by the terminal device; a generating unit that generates a report indicating a result of providing the advertisement to the target based on the characteristic information acquired by the acquiring unit; a providing unit that provides the report generated by the generating unit to the advertiser that has designated the target; Equipped with The generation unit clustering the feature information for each of the targets, and generating the report indicating the results of providing the advertisement based on the clustering results; An information providing device comprising:

2. The generation unit generating a centroid image, which is a centroid of the feature amount of the advertisement estimated from the feature information, as the report for each of the targets; 2. The information providing device according to claim 1, wherein:

3. The generation unit generating a scatter diagram showing a distribution state of the feature amount of the advertisement as the report for each of the targets based on the feature information; 2. The information providing device according to claim 1, wherein:

4. The generation unit generating the report for each group in which the users are classified according to their attributes, for each of the targets; 2. The information providing device according to claim 1, wherein:

5. The generation unit generating verbalized information that verbalizes the characteristics of the image used in the advertisement as the report; 2. The information providing device according to claim 1, wherein:

6. The generation unit When a predetermined image is input, the advertisements similar to the characteristics of the image are identified, and a report on the advertisements is generated.

2. The information providing device according to claim 1, wherein:

7. 1. A computer-implemented information providing method, comprising: an acquisition step of generating a specified target advertisement using an advertisement generation model trained to generate a specified target advertisement using user information related to the user, and acquiring feature information of the generated advertisement from a terminal device that provides the generated advertisement; a generating step of generating a report showing a result of providing the advertisement to the target based on the characteristic information acquired by the acquiring step; a providing step of providing the report generated by the generating step to the advertiser who has designated the target; Including, The generating step includes: clustering the feature information for each of the targets, and generating the report indicating the results of providing the advertisement based on the clustering results; An information provision method characterized by the above.

8. an acquisition step of generating a specified target advertisement using an advertisement generation model trained to generate a specified target advertisement using user information related to the user, and acquiring feature information of the generated advertisement from a terminal device that provides the generated advertisement; a generating step of generating a report showing a result of providing the advertisement to the target based on the characteristic information acquired by the acquiring step; a providing step of providing the report generated by the generating step to the advertiser who has designated the target; on the computer, The generating procedure includes: clustering the feature information for each of the targets, and generating the report indicating the results of providing the advertisement based on the clustering results; An information program featuring:

Images