Advertisement generation assistance device and advertisement generation assistance method

Abstract

This advertisement generation assistance device comprises: an acquisition unit that acquires advertised article information indicating a product or service to be advertised, and target information indicating a target when advertising the product or service; a determination unit that determines, on the basis of the target information, medium information indicating a medium on which advertisement content for advertising the product or service is published; and a processing unit that executes processing on the advertised article information and the medium information for obtaining the advertisement content based on the advertised article information and the medium information by a generative AI model.

Description

Advertisement Generation Support Device and Advertisement Generation Support Method

[0001] The present invention relates to an advertisement generation support device and an advertisement generation support method.

[0002] Patent Document 1 describes a device used for advertising a product that is the target of an advertisement. The device described in Patent Document 1 generates an image related to the product based on information about the user and information about the product that is the target of the advertisement. Then, the device associates the URL of the generated image with the URL of the advertisement page to generate advertisement data (advertisement content).

[0003] Japanese Patent Application Laid-Open No. 2020-154670

[0004] However, with the above-described device, it was not possible to accurately generate advertisement content for advertising a product or service. For example, since the advertisement content is generated based only on information about the user and information about the product or service, there is a possibility that advertisement content with a high advertisement effect when posted on an advertisement medium cannot be generated.

[0005] An embodiment of the present invention has been made in view of the above, and an object thereof is to provide an advertisement generation support device and an advertisement generation support method capable of accurately generating advertisement content with a high advertisement effect.

[0006] In order to achieve the above object, an advertisement generation support device according to an embodiment of the present invention includes an acquisition unit that acquires advertisement target information indicating a product or service that is the target of an advertisement, and target information indicating a target when advertising the product or service, a determination unit that determines medium information indicating a medium on which advertisement content for advertising the product or service is posted based on the target information, and a processing unit that executes processing on the advertisement target information and the medium information to obtain advertisement content based on the advertisement target information and the medium information by a generation AI model.

[0007] In an advertising generation support device according to one embodiment of the present invention, a processing unit performs processing on advertising target information and media information in order to obtain advertising content that advertises a product or service based on advertising target information and media information using an AI generation model. With this configuration, advertising content that advertises a product or service is generated taking into account the advertising media on which the advertising content will be placed. As a result, for example, it becomes possible to generate advertising content that is more suitable for the advertising media, and thus it becomes possible to generate highly effective advertising content with high accuracy.

[0008] Incidentally, one embodiment of the present invention can be described not only as an apparatus invention as described above, but also as a method invention as follows. These are substantially the same invention, differing only in category, and produce similar functions and effects.

[0009] In other words, an advertising generation support method according to one embodiment of the present invention comprises: an acquisition step in which an advertising generation support device acquires advertising target information indicating a product or service that is the subject of the advertisement, and target information indicating the target when advertising the product or service; a determination step in which the advertising generation support device determines media information indicating a medium on which advertising content advertising the product or service will be published, based on the target information; and a processing step in which the advertising generation support device performs processing on the advertising target information and media information in order to obtain advertising content based on the advertising target information and media information using an AI generation model.

[0010] According to one embodiment of the present invention, it becomes possible to accurately generate advertising content with high advertising effectiveness.

[0011] This diagram shows the configuration of an advertising generation support device according to an embodiment of the present invention. This diagram shows an example of a prompt generated by the advertising generation support device. This flowchart shows an advertising generation support method, which is a process executed by the advertising generation support device according to an embodiment of the present invention. This diagram shows the hardware configuration of the advertising generation support device according to an embodiment of the present invention.

[0012] Hereinafter, embodiments of the advertisement generation support apparatus and advertisement generation support method according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant explanations are omitted.

[0013] Figure 1 shows the advertisement generation support device 10 according to this embodiment. The advertisement generation support device 10 is a device used to advertise a product or service that is the subject of the advertisement. The subject of the advertisement is the product or service advertised by the user of the advertisement generation support device 10. For example, the user of the advertisement generation support device 10 is a provider of the product or service that is the subject of the advertisement, such as a seller. The user of the advertisement generation support device 10 advertises the product or service and increases the number of purchasers of the product or service by creating opportunities for the product or service to be seen by consumers.

[0014] Advertising is a means performed by a user of the advertising generation support device 10 to provide consumers with an opportunity to see a product or service. For example, when advertising a product or service, a user of the advertising generation support device 10 prepares advertising content for the product or service and presents the advertising content to consumers through some medium. This allows consumers to see the product or service shown in the advertising content. Advertising content may include, for example, images, videos, text, and audio related to the product or service.

[0015] Advertising content is presented to specific individuals or to a large, unspecified group of people. For example, advertising content may be presented to specific individuals on a Social Networking Service (SNS) used for communication between specific individuals. One example is that advertising content is presented to specific individuals by appearing in chat rooms on SNS such as LINE. Alternatively, advertising content may be presented to a large, unspecified group of people on an SNS used for communication with a large, unspecified group of people. For example, advertising content may be presented to a large, unspecified group of people by appearing on timelines on SNS such as X.

[0016] Specifically, first, a user who wants to advertise a product or service (a user of the ad generation support device 10) inputs advertising target information, indicating the product or service to be advertised, and target information, indicating the target audience for advertising the product or service, into the ad generation support device 10. Next, the ad generation support device 10 acquires the input advertising target information and target information. Based on the acquired target information, the ad generation support device 10 determines media information, indicating the media on which to publish the advertising content for the product or service. Finally, the ad generation support device 10 generates advertising content based on the acquired advertising target information and the determined media information. In this way, the ad generation support device 10 is used to determine a suitable media for a product or service and to generate advertising content suitable for that media. Then, the user of the ad generation support device 10 can advertise their product or service more effectively by publishing the advertising content generated by the ad generation support device 10 on the media determined by the ad generation support device 10.

[0017] The generation of advertising content itself is performed using a generative AI (artificial intelligence) model. The generative AI model is a model generated by machine learning. The generative AI model is a model that can generate content according to any or a combination of the instructions, context, questions, and output formats indicated by a prompt (details of which will be described later) in response to the input of a prompt, and return that content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeting the input information. The generative AI model may consist of, for example, a Large Linguistic Model (LLM) and a user interface (UI) for interacting with the user of the Large Linguistic Model, and may be an interactive AI model that enables text chat or voice chat with the user of the Large Linguistic Model. Examples of such generative AI models include ChatGPT, GPT®-3.5, GPT-4V, PaLM2, etc. Although the above is described using a Large Linguistic Model as an example, other AI models may also be used.

[0018] A prompt is a set of instructions or information input to a generating AI model. A prompt can include initial information, parameters, and questions for the generating AI model to perform a specific task. In an interactive system, such as a command-line interface (CLI), a prompt indicates instructions or questions input by the user of the generating AI model. The prompt expresses, in text, the commands the interactive AI model will execute, the tasks the interactive AI model will perform, the background and context the interactive AI model should consider (e.g., roles, conditions), the questions the interactive AI model should answer, and the output format of the response information from the interactive AI model. Furthermore, the prompt may include input information that will be the target of the commands / tasks executed by the interactive AI model. Such input information includes data files with specific file extensions, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, tabular data, and graph data that can be processed by a default application program.

[0019] In this embodiment, the generated AI model 21 is implemented by an AI server (server device) 20. The generated AI model 21 may be stored within the AI ​​server 20, or it may be stored in another device connected to the AI ​​server 20 via a network and made available to the AI ​​server 20. The generated AI model 21 and the AI ​​server 20 may be the same as those in the conventional system.

[0020] The ad generation support device 10 is comprised of a computer such as a PC (personal computer) or server device, separate from the user's terminal of the ad generation support device 10. The ad generation support device 10 may be comprised of multiple computers. The ad generation support device 10 can send and receive information with other devices, including the AI ​​server 20, via a network in order to acquire information necessary for realizing its functions. The ad generation support device 10 may be a RAG (Retrieval-Augmented Generation) system. In this case, the knowledge database that the RAG system searches may be implemented within the ad generation support device 10, or it may be implemented on another device on the network (for example, the cloud).

[0021] Next, the functions of the advertisement generation support device 10 according to this embodiment will be described. As shown in Figure 1, the advertisement generation support device 10 is configured to include an acquisition unit 11, a determination unit 12, and a processing unit 13.

[0022] The acquisition unit 11 acquires advertising target information. Advertising target information is information that indicates a product or service. For example, advertising target information includes information indicating the type of product or service (e.g., the type of autonomous vehicle), information indicating the name of the product or service, an image of the product or service, or a combination thereof. Also, for example, advertising target information may include information necessary for advertising (promoting) the product or service. For example, advertising target information may include information indicating the characteristics, quality, performance, functions, test results (e.g., results of demonstration tests conducted on the product or service before it is sold), and awards received. Also, for example, advertising target information may include information indicating the period during which the product is sold or the period during which the service is available, and at least one of the uses of the product or service. Advertising target information is generated by a device other than the advertising generation support device 10 or by a user of the advertising generation support device 10 using various known methods. The acquisition unit 11 acquires advertising target information by receiving input from a device other than the advertising generation support device 10 or a user of the advertising generation support device 10. Furthermore, the acquisition unit 11 may acquire advertising target information by other means.

[0023] The acquisition unit 11 acquires target information indicating the target audience when advertising a product or service. Specifically, the acquisition unit 11 may acquire target information based on advertising target information. A target is, for example, a person or group of people to whom an advertising content advertising a product or service is expected to be highly effective when a user of the advertising generation support device 10 advertises the product or service. Alternatively, a target is a person or group of people to whom it is expected that they will be the main consumers of the product or service. Target information is, for example, information related to the target, and one example includes attribute information that specifies the attributes (target group) of the target. Target information is generated by a user of the advertising generation support device 10 or another device using various known methods and is stored in a database or the like provided by the advertising generation support device 10. Note that target information only needs to be information used by the determination unit 12 to determine media information, and may include other information not mentioned above. The acquisition unit 11 may also acquire target information by accepting input from a device other than the advertising generation support device 10 or from a user of the advertising generation support device 10. The acquisition unit 11 may also acquire target information by other means.

[0024] Attribute information includes regional information indicating at least one region where the target lives. For example, the regional information may indicate Tokyo and Kanagawa prefectures. Regional information may also indicate the number of targets living in each of the at least one region, or the percentage of such numbers in each region. For example, the regional information may include information indicating that 70% live in Tokyo and 30% live in Kanagawa prefecture. As an example, the regional information may include information indicating that there are 70 targets living in Tokyo and 30 targets living in Kanagawa prefecture.

[0025] Attribute information includes age information indicating the target age group. In other words, target information includes information indicating the age group of the target people when advertising a product or service. For example, age information may include information indicating the gender and age group of the advertised target. For example, age information may include information indicating men in their 20s and women in their 20s. Furthermore, for example, age information may include information indicating the number of targets corresponding to each combination of age and gender, or the percentage of such numbers for each combination. For example, age information may include information indicating that 70% are men in their 20s and 30% are women in their 20s. For example, age information may include information indicating that there are 70 targets corresponding to the attribute (combination) of men in their 20s and 30 targets corresponding to the attribute (combination) of women in their 20s.

[0026] If the target is a specific person or group of people, attribute information may include information such as the target's purchase history and payment methods, family structure information indicating the target's family structure, the target's engagement information, operation history information indicating the target's history of using the application, and other information not mentioned above. For example, purchase history and payment method information indicates the goods or services the target has purchased, when the goods or services were purchased, and the payment method used at the time of purchase. For example, family structure information indicates people within two degrees of kinship to the target. For example, engagement information indicates the results of a survey about the product or service, and may include information showing responses to the question "How likely are you to recommend the product or service to someone?" on a multi-level scale (e.g., 11 levels), or information showing responses to the question "How likely are you to purchase the product or service?" on a multi-level scale. For example, operation history information indicates how the advertised target has reacted to other people's posts on social media. For example, operation history information may include information indicating that the advertised target shared posts by other users on social media and information indicating the time spent viewing posts from other companies. Attribute information may also include information that represents a combination of the above-mentioned pieces of information. Furthermore, this attribute information may also be used when it can be assumed that the target is a specific person or group of people.

[0027] Specifically, the acquisition unit 11 acquires reaction information that shows human reactions to content related to a product or service, and acquires target information based on the reaction information. For example, the reaction information is impression information that shows to what extent content related to a product or service was displayed or spread on social networking services (SNS) etc. from one point in the past to another. In other words, the impression information includes information that shows up to what point in the past SNS reactions should be checked. As an example, the impression information is information that shows the number of times a post showing a product or service was spread on SNS for each age group of SNS users. The impression information may also include indicators that show the advertising effectiveness of web advertisements, such as the number of sessions per advertising medium (number of accesses to content related to a product or service), bounce rate (percentage of SNS users who accessed content related to a product or service but did not continue to view the page related to that content), and average time on site (average value of the time that SNS users continued to access content related to a product or service). Furthermore, impression information may include information indicating the response of each SNS user to the promotional content (for example, the probability that an SNS user will open a notification displayed on their device during the customer journey). Response information may also include result information showing the results of a survey about the product or service (for example, Q&A). Response information is generated by devices other than the advertising generation support device 10 or by SNS users using various known methods.

[0028] More specifically, the acquisition unit 11 targets SNS users in age groups whose number of shares of posts indicating a product or service exceeds a predetermined threshold when advertising the product or service. For example, impression information indicates that for a post indicating a product or service, SNS users in their 20s shared it 156 times, SNS users in their 30s shared it 241 times, and SNS users in their 40s shared it 23 times. In this case, the acquisition unit 11 targets SNS users in their 20s and SNS users in their 30s, who have a higher number of shares than the predetermined threshold of 100, when advertising the product or service.

[0029] Furthermore, for example, the acquisition unit 11 may target users of all age groups on the SNS when advertising a product or service. In this case, the acquisition unit 11 may use information with weights set for each age group based on impression information (for example, information indicating that the weight for SNS users in their 20s is 156, the weight for SNS users in their 30s is 241, and the weight for SNS users in their 40s is 23) as target information.

[0030] The acquisition unit 11 may also present advertising target information to the user of the advertising generation support device 10, and acquire target information when the user of the advertising generation support device 10 inputs target information. For example, the acquisition unit 11 may present response information to the user of the advertising generation support device 10, and acquire target information when the user of the advertising generation support device 10 inputs target information.

[0031] Furthermore, the acquisition unit 11 may refer to a database (a database provided by the advertising generation support device 10) that stores various target information and acquire target information linked to the acquired advertising target information. At this time, target information indicating the target audience for which advertising content advertising a product or service is expected to be highly effective is linked to the advertising target information indicating a product or service. This linking of advertising target information and target information is performed by the user of the advertising generation support device 10, the advertising generation support device 10, or other devices using various known methods.

[0032] The determination unit 12 determines at least one media information indicating a medium on which advertising content advertising a product or service will be posted, based on the target information. The media information is information indicating a medium on which advertising content advertising a product or service will be posted. For example, the media information includes information indicating an SNS on which the advertising content will be posted (for example, LINE and X as mentioned above), information indicating a web page on which the advertising content will be posted (for example, information indicating a web page on which advertisements to be posted on a homepage and banner advertisements will be posted), information indicating other information on which the advertising content will be posted (for example, information specifying other media and email newsletters, etc.), information indicating the size of the medium on which the advertisement will be posted, and information indicating the configuration of the medium (for example, image placement, text placement, text font and amount of text, etc.). The media information is generated by a user of the advertising generation support device 10, the advertising generation support device 10, or other devices using various known methods.

[0033] Specifically, the determination unit 12 refers to relationship information (e.g., a table) that has been set and stored in advance, which shows the correspondence between target information and media information, and extracts at least one piece of media information corresponding to the target information acquired by the acquisition unit 11. The correspondence between target information and media information is created, for example, by a user of the advertising generation support device 10 based on past knowledge, so that target information corresponds to media information that has a high appeal effect on the target corresponding to the target information. This makes it possible to extract advertising media that have a high appeal effect on the target corresponding to the target information.

[0034] The decision unit 12 may pre-construct a learning model that has learned the relationship between target information and media information through machine learning. In this case, the decision unit 12 may input the target information acquired by the acquisition unit 11 into the learning model to acquire at least one piece of media information output from the learning model. For example, the decision unit 12 may pre-acquire a vector space in which each piece of target information is represented as a first node, each piece of media information is represented as a second node, and the correspondence between target information and media information is represented as an edge between the first node and the second node. The decision unit 12 plots the target information acquired by the acquisition unit 11 as a first node in the vector space and extracts media information corresponding to a second node whose distance from the first node is less than or equal to a predetermined value. Alternatively, the decision unit 12 may create a prompt for determining media information based on the target information and input it into the generating AI model 21 to acquire media information output from the generating AI model 21.

[0035] The processing unit 13 performs processing on the advertising target information and media information in order to obtain advertising content based on the advertising target information and media information using the AI ​​generation model 21. Specifically, the processing unit 13 performs processing on the advertising target information, target information and media information in order to obtain advertising content based on the advertising target information, target information and media information using the AI ​​generation model 21. In this embodiment, the processing unit 13 performs processing on the advertising target information, target information, media information and advertising example information in order to obtain advertising content based on the advertising target information, target information, media information and advertising example information showing examples of advertisements suitable for the media using the AI ​​generation model 21.

[0036] The advertising example information is information that shows examples of advertisements suitable for a medium. For example, if the medium is X, the advertising example information includes an example of an image to be presented to users of X on X's timeline. Also, if the medium is LINE, the advertising example information includes an example of an image to be sent to LINE users in a LINE chat. Furthermore, the advertising example information includes an example of text to be presented to the user, an instruction statement that instructs the generation of text to be included in the advertising content considering the example text, and information indicating whether or not the instruction statement is present. The advertising example information is information that has been stored in advance in a database (a database provided by the advertising generation support device 10) by the user of the advertising generation support device 10, and is information that has been generated by the user of the advertising generation support device 10 using various known methods. The advertising example information is pre-associated with medium information using various known methods.

[0037] First, the processing unit 13 generates a prompt P1 for input to the generated AI model 21 based on the advertising target information and media information. In this embodiment, the processing unit 13 acquires advertising target information and target information from the acquisition unit 11 and media information from the determination unit 12. Based on the acquired media information, the processing unit 13 acquires advertising example information corresponding to the media information from a database or the like provided by the advertising generation support device 10. Based on the advertising target information, target information, media information and advertising example information, the processing unit 13 generates a prompt P1 for input to the generated AI model 21.

[0038] Figure 2 shows an example of prompt P1. In the example shown in Figure 2, the processing unit 13 generates prompt P1 by inputting input strings based on advertising target information, target information, and media information, as well as input information including advertising example information, into the input locations of a pre-stored general-purpose prompt. The input strings based on advertising target information, target information, and media information are strings (sentences) generated to allow the AI ​​model 21 to appropriately refer to the advertising target information, target information, and media information. These input strings are generated using various known methods for generating strings based on information.

[0039] The generic prompt includes information indicating that the user is to generate advertising content to advertise a product or service. In the example shown in Figure 2, this information is as follows: "Role: You are an advertising agency representative. Task: Generate advertising content according to the following conditions. Condition: Generate different advertising content for each medium. Describe in writing the advertising strategy, indicating which media to use and to what target audience the generated advertising content will be advertised."

[0040] The general prompt includes input strings based on the advertising target information, target information, and media information, as well as information indicating where to input example advertising information. This information is the part that reads: "Product or service being advertised Media 1 where the advertisement is placed Main target audience Reference advertising image Media 2 where the advertisement is placed Main target audience Create advertising copy referring to the following examples Reference advertising image." Thus, the general prompt includes the instruction "Create advertising copy referring to the following examples" which instructs the system to generate text to be included in the advertising content, taking the example text into consideration. The content of this instruction and information indicating whether or not this instruction is present are included in the example advertising information and are determined according to the type of media on which the advertisement is placed.

[0041] Prompt P1 includes information in the input field indicating the input string based on the advertised information. This information is the part that reads "[Name and description of the product or service]". Note that "[Name and description of the product or service]" will contain the actual name of the product or service.

[0042] In the prompt P1, information indicating an input string based on the target information is included in the input section. For example, the prompt P1 includes an instruction to target users of all age groups on SNS when advertising a product or service. The instruction is the part "Please generate advertisement content that appeals to all generations (do not ignore any generation)". In this case, in the prompt P1, in the input section, information indicating an input string based on the information included in the target information and based on the information in which weightings are set for each age group based on impression information, and an instruction to generate advertisement content having a higher appeal effect for the generation with a higher weighting are included. The information is the part "Please prioritize the generation with a higher weighting. Weighting for the 20s: 156, Weighting for the 30s: 241, Weighting for the 40s: 23".

[0043] Also, for example, the prompt P1 includes an instruction to target 20-year-old men when advertising a product or service, and an instruction to explain the purchase history of the 20-year-old men and the payment method used at the time of purchase (one of the information included in the attribute information of the target information). The instruction is the part "20-year-old man A with purchase history, user of payment method B".

[0044] In the prompt P1, an input string based on the media information is included in the input section. The information is the part "SNSA" and the part "SNSB".

[0045] In the prompt P1, advertisement example information is included in the input section. For example, the prompt P1 includes an image showing an example of an advertisement. The information is the part "Advertisement image for reference [image file name]". Note that the actual address or URL of the image file, etc. is described in [image file name].

[0046] Also, for example, in the prompt P1, an example of the text (advertising text) to be included in the advertising content and an image showing an example of the advertisement are included as advertisement example information. This information is the part "2% discount with B payment! [image file name]". Note that the [image file name] describes the address or URL of the actual image file, etc.

[0047] By including the advertisement example information in the prompt P1, the processing unit 13 can generate advertising content more suitable for the medium. That is, the processing unit 13 can utilize a method called Few Shot Learning to more accurately generate advertising content with a high advertising effect.

[0048] In such a prompt P1, different instruction texts are determined for each medium information. The instruction texts are pre-generated using various methods known to the user of the advertising generation support device 10 or the like. For example, when the medium is an advertising medium that distributes advertisements to a specific individual (for example, LINE), for at least one or more pieces of attribute information (for example, the payment method (settlement means) such as B payment), a text showing an example of the advertisement may be prepared in advance and the text showing an example of the advertisement may be included in the prompt P1. The text is the part "2% discount with B payment!". As an example, when the medium is an advertising medium that distributes advertisements to a specific individual, an instruction text instructing to generate advertising content in consideration of information about the specific individual (for example, the personality, preferences, past conversation history, etc. of the specific individual) may be included in the prompt P1.

[0049] Also, for example, when the medium is an advertising medium that distributes the same advertisement to an unspecified number of people (for example, X), it is necessary to generate advertising content that has an appealing effect on many users who use the advertising medium. Therefore, the prompt P1 includes an input string based on target information indicating users of multiple generations (users who use the advertising medium), and an instruction text (information explaining the advertising strategy) instructing to generate advertising content that has an appealing effect on users of various generations (users who use the advertising medium). The instruction text is the part "Please generate advertising content that hits all generations (do not ignore any generation)".

[0050] The processing unit 13 inputs a prompt P1 based on the advertising target information and media information to the generation AI model 21 to obtain advertising content. Specifically, the processing unit 13 sends the generated prompt P1 to the AI ​​server 20 for input to the generation AI model 21. The generation AI model 21 receives the input of prompt P1 and generates advertising content according to prompt P1. The generation AI model 21 transmits the generated advertising content to the advertising generation support device 10 as a response to the transmitted prompt P1. The processing unit 13 receives and acquires the advertising content transmitted from the generation AI model 21. The processing unit 13 presents the acquired advertising content to the user of the advertising generation support device 10. Note that the presentation of advertising content to the user of the advertising generation support device 10 does not need to be performed by the advertising generation support device 10. Also, the advertising content may be used for purposes other than presentation to the user of the advertising generation support device 10. The advertising generation support device 10 may output advertising content by methods other than those described above.

[0051] The processing unit 13 generates a prompt P1 for input to the generating AI model 21 based on the advertising target information and media information, but is not limited to this. For example, if the generating AI model 21 accepts input in a format other than a prompt, the processing unit 13 may send input information based on the advertising target information and media information to the AI ​​server 20, and the AI ​​server 20 may receive the input information and input it to the generating AI model 21. The AI ​​server 20 may send the generated advertising content to the advertising generation support device 10. In other words, the processing unit 13 may input the input information based on the advertising target information and media information to the generating AI model 21 in the AI ​​server 20, for example, and obtain the advertising content.

[0052] Next, using the flowchart in Figure 3, we will explain the advertising generation support method, which is the process (operation method performed by the advertising generation support device 10) executed by the advertising generation support device 10 according to this embodiment. When a user of the advertising generation support device 10 who wishes to advertise a product or service inputs advertising target information indicating the product or service to be advertised into the advertising generation support device 10, the following steps S01 to S05 are executed by the advertising generation support device 10.

[0053] In this process, first, the acquisition unit 11 of the advertising generation support device 10 acquires advertising target information and target information (steps S01 and S02, acquisition step). Subsequently, the determination unit 12 of the advertising generation support device 10 determines media information based on the target information (step S03, determination step).

[0054] The processing unit 13 of the advertising generation support device 10 generates a prompt P1 for obtaining advertising content using the AI ​​model 21 based on the advertising target information and media information, and the generated prompt P1 is input to the AI ​​model 21 to obtain advertising content (S04 and S05, processing steps). In other words, the processing unit 13 performs processing on the advertising target information and media information in order to obtain advertising content based on the advertising target information and media information using the AI ​​model 21.

[0055] Subsequently, the user of the advertising generation support device 10 can more effectively advertise their product or service by posting the advertising content generated by the advertising generation support device 10 on the medium determined by the advertising generation support device 10. The above describes the advertising generation support method, which is the process performed by the advertising generation support device 10 according to this embodiment.

[0056] In this embodiment, the processing unit 13 performs processing on the advertising target information and media information in order to obtain advertising content for advertising a product or service using the generation AI model 21, based on the advertising target information and media information. With this configuration, advertising content for advertising a product or service is generated taking into account the advertising media on which the advertising content will be placed. As a result, for example, it is possible to generate advertising content that is more suitable for the advertising media, and thus it is possible to generate highly effective advertising content with high accuracy.

[0057] Furthermore, in this embodiment, advertising content for products or services can be easily and accurately obtained by the generation AI model 21. This allows users who select from various advertising media such as email newsletters and display advertisements (for example, businesses providing small-scale services for the purpose of demonstration testing, and service providers such as venture companies) to quickly and accurately obtain highly effective advertising content within their limited financial and human resources. Moreover, in this embodiment, by utilizing the generation AI model 21, the selection of advertising media and the generation of advertising content suitable for those media are performed, thus lowering the barrier for personnel with low data literacy to interpret metadata and formulate marketing strategies. As a result, even businesses with limited data analysis skills and human resources, such as local businesses (restaurants, hospitals, etc.), can implement effective promotions in a short period of time. In addition, in this embodiment, since advertising content is easily and accurately generated using the generation AI model 21, personalized recommendations can be made to individual users on social media, etc., and the human costs associated with making such recommendations can be reduced.

[0058] As in this embodiment, the processing unit 13 may generate a prompt P1 for input to the generation AI model 21 based on the advertising target information and media information. With this configuration, the generation AI model 21 can generate advertising content. Furthermore, by adjusting the description of prompt P1, it becomes possible to reliably and accurately generate advertising content with high advertising effectiveness. However, the processing unit 13 may obtain the advertising content from the generation AI model 21 by a method other than generating prompt P1. In this case, the process of causing the generation AI model 21 to generate advertising content using the generated prompt P1 may be performed by another device.

[0059] As in this embodiment, the processing unit 13 may input input information based on the advertising target information and media information to the generation AI model 21 to acquire advertising content. With this configuration, the generation AI model 21 can generate advertising content.

[0060] As in this embodiment, the acquisition unit 11 may acquire target information based on the advertising target information. With this configuration, target information indicating the target audience when advertising a product or service is determined by considering the advertising target information indicating the product or service that is the subject of the advertisement. This makes it possible to acquire target information indicating the target audience for which the advertising content advertising the product or service is expected to be highly effective, for example, when advertising a product or service, with greater accuracy. However, the acquisition unit 11 does not necessarily need to acquire target information based on the advertising target information; for example, the user of the advertising generation support device 10 may input target information into the advertising generation support device 10 to acquire target information.

[0061] As in this embodiment, the acquisition unit 11 may acquire reaction information indicating human reactions to content related to a product or service, and acquire target information based on the reaction information. With this configuration, it is possible to determine the target audience for advertising a product or service by considering human reactions to the product or service. For example, people who are likely to purchase a product or service can be targeted for advertising the product or service. However, the acquisition unit 11 does not necessarily need to generate target information based on reaction information; for example, the user of the advertising generation support device 10 may input target information into the advertising generation support device 10 to acquire target information.

[0062] As in this embodiment, the processing unit 13 may perform processing on the advertising target information, target information, and media information in order to obtain advertising content based on the advertising target information, target information, and media information using the AI ​​model 21 for generating advertising content. With this configuration, it becomes possible to generate advertising content while considering the target audience for advertising the product or service. For example, prompt P1 is generated based on the target information. This allows prompt P1 to include instructions that generate advertising content with a high appeal effect to the target audience, thus enabling the accurate generation of such advertising content. However, the processing unit 13 does not necessarily need to perform processing on the target information in order to obtain advertising content based on the target information using the AI ​​model 21 for generating advertising content. The processing unit 13 only needs to perform processing on the advertising target information and media information in order to obtain advertising content based on the advertising target information and media information using the AI ​​model 21 for generating advertising content.

[0063] As in this embodiment, the target information may be information indicating the age group of the target people when advertising a product or service. With this configuration, advertising content that is highly effective in appealing to the target people can be generated with high accuracy, taking into account the age group of the target people when advertising a product or service. However, the target information does not necessarily have to be information indicating the age group of the target people when advertising a product or service; it can be any information relating to the target people when advertising a product or service.

[0064] As in this embodiment, the processing unit 13 may perform processing on the advertising target information, media information, and advertising example information in order to obtain advertising content based on advertising target information, media information, and advertising example information showing examples of advertisements suitable for the media using the AI ​​model 21 for generation. With this configuration, advertising content can be generated while referring to examples of advertisements suitable for the media. This makes it possible to generate advertising content that is more suitable for the media with greater accuracy. However, the processing unit 13 does not necessarily have to perform processing on the advertising example information in order to obtain advertising content based on the advertising example information using the AI ​​model 21 for generation. The processing unit 13 only needs to perform processing on the advertising target information and media information in order to obtain advertising content based on the advertising target information and media information using the AI ​​model 21 for generation.

[0065] In the above embodiment, the ad generation support device 10 was a PC or server device separate from the user's terminal, but is not limited to this. For example, the ad generation support device 10 may be part of the terminal. As an example, the RAG system, which is composed of the functional parts of the ad generation support device 10, may be implemented in the terminal. In this case, the knowledge database that the RAG system searches may be implemented inside the terminal, or it may be implemented in another device on the network (e.g., the cloud).

[0066] Furthermore, the ad generation support device 10 may also have the functionality of an AI server 20. This configuration can be achieved by installing an application that performs the functions of the AI ​​server 20 on the ad generation support device 10. Thus, the generated AI model 21 may be implemented on a network (e.g., the cloud) other than the AI ​​server 20.

[0067] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0068] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0069] For example, the advertising generation support device 10 in one embodiment of the present disclosure may function as a computer that performs information processing according to the present disclosure. Figure 4 is a diagram showing an example of the hardware configuration of the advertising generation support device 10 according to one embodiment of the present disclosure. The above-described advertising generation support device 10 may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0070] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the advertisement generation support device 10 may include one or more of the devices shown in the figure, or it may be configured without some of the devices.

[0071] Each function in the advertisement generation support device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which causes the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

[0072] The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the processing unit 13 of the advertisement generation support device 10 may be implemented by the processor 1001.

[0073] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the processing unit 13 of the advertisement generation support device 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line.

[0074] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out information processing according to one embodiment of the present disclosure.

[0075] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The storage medium provided by the advertising generation support device 10 may be, for example, a database, server, or other suitable medium including at least one of the memory 1002 and the storage 1003.

[0076] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0077] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0078] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0079] Furthermore, the advertisement generation support device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0080] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0081] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0082] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0083] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0084] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0085] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0086] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0087] The terms “system” and “network” as used in this disclosure are interchangeable.

[0088] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0089] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0090] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0091] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0092] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0093] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0094] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0095] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0096] The advertising generation support device and advertising generation support method of this disclosure have the following configurations: [1] An advertising generation support device comprising: an acquisition unit that acquires advertising target information indicating a product or service that is the subject of an advertisement, and target information indicating the target when advertising the product or service; a determination unit that determines media information indicating a media on which advertising content for the product or service is published based on the target information; and a processing unit that performs processing on the advertising target information and the media information in order to obtain the advertising content based on the advertising target information and the media information by a generation AI model. [2] The advertising generation support device according to [1], wherein the processing unit generates prompts for input to the generation AI model based on the advertising target information and the media information. [3] The advertising generation support device according to [1], wherein the processing unit inputs input information based on the advertising target information and the media information to the generation AI model and obtains the advertising content. [4] The advertising generation support device according to any one of [1] to [3], wherein the acquisition unit acquires target information based on the advertising target information. [5] The advertising generation support device according to any one of [1] to [3], wherein the acquisition unit acquires reaction information indicating human reactions to content relating to a product or service, and acquires target information based on the reaction information. [6] The advertising generation support device according to any one of [1] to [4], wherein the processing unit performs processing on the advertising target information, the target information and the media information in order to obtain the advertising content based on the advertising target information, the target information and the media information by a generation AI model. [7] The advertising generation support device according to any one of [1] to [6], wherein the target information is information indicating the age of the target human when advertising the product or service. [8] The advertising generation support device according to any one of [1] to [7], wherein the processing unit performs processing on the advertising target information, the media information and the advertising example information in order to obtain the advertising content based on the advertising target information, the media information and advertising example information indicating examples of advertisements suitable for the media by a generation AI model.[9] An advertising generation support method comprising: an acquisition step in which an advertising generation support device acquires advertising target information indicating a product or service that is the subject of an advertisement, and target information indicating the target when advertising the product or service; a determination step in which the advertising generation support device determines media information indicating a medium on which advertising content for the product or service will be published, based on the target information; and a processing step in which the advertising generation support device performs processing on the advertising target information and the media information in order to obtain the advertising content based on the advertising target information and the media information by an AI generation model.

[0097] 10...Advertisement generation support device, 11...Acquisition unit, 12...Decision unit, 13...Processing unit, 21...Generating AI model, 1001...Processor, 1002...Memory, 1003...Storage, 1004...Communication device, 1005...Input device, 1006...Output device, P1...Prompt.

Claims

1. An advertising generation support device comprising: an acquisition unit that acquires advertising target information indicating a product or service that is the subject of an advertisement, and target information indicating the target audience when advertising the product or service; a determination unit that determines media information indicating the media on which advertising content for the product or service will be published based on the target information; and a processing unit that performs processing on the advertising target information and the media information in order to obtain the advertising content based on the advertising target information and the media information using a generation AI model.

2. The advertising generation support apparatus according to claim 1, wherein the processing unit generates prompts for input to the generating AI model based on the advertising target information and the media information.

3. The advertising generation support device according to claim 1, wherein the processing unit inputs the advertising target information and the media information into the generating AI model and acquires the advertising content.

4. The advertising generation support device according to claim 1, wherein the acquisition unit acquires target information based on the advertising target information.

5. The advertising generation support device according to claim 1, wherein the acquisition unit acquires reaction information indicating human reactions to content relating to the product or service, and acquires target information based on the reaction information.

6. The advertising generation support apparatus according to claim 1, wherein the processing unit performs processing on the advertising target information, the target information and the media information in order to obtain the advertising content based on the advertising target information, the target information and the media information by an AI generation model.

7. The advertising generation support device according to claim 1, wherein the target information is information indicating the age group of the target people when advertising the product or service.

8. The advertising generation support device according to claim 1, wherein the processing unit performs processing on the advertising target information, the media information, and the advertising example information in order to obtain the advertising content based on the advertising target information, the media information, and the advertising example information showing examples of advertisements suitable for the media using an AI generation model.

9. An advertising generation support method comprising: an acquisition step in which an advertising generation support device acquires advertising target information indicating a product or service that is the subject of an advertisement, and target information indicating the target when advertising the product or service; a determination step in which the advertising generation support device determines media information indicating a media on which advertising content for the product or service will be published, based on the target information; and a processing step in which the advertising generation support device performs processing on the advertising target information and the media information in order to obtain the advertising content based on the advertising target information and the media information using an AI generation model.

Images