Advertising content generation device, advertising content generation method, advertising content generation program

Abstract

Generate more effective advertising content tailored to the current situation. [Solution] The advertising content generation device includes a receiving unit that receives information to be generated as advertising content, a prompt generation unit that generates prompts based on the information to be generated as advertising content, and an advertising content generation control unit that inputs the prompts into a machine learning model that refers to a database containing at least media content data to generate advertising content.

Description

Technical Field

[0001] The present invention relates to an advertisement content generation device, an advertisement content generation method, and an advertisement content generation program.

Background Art

[0002] Patent Document 1 describes a system that generates a plurality of advertisement texts based on a basic advertisement text and keywords corresponding to the advertisement, estimates the advertisement effect of the generated plurality of advertisement texts, and regenerates a new advertisement text from the plurality of advertisement texts based on the estimated advertisement effect.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of Invention

Problems to be Solved by the Invention

[0004] Patent Document 1 does not disclose generating advertisement texts adapted to the current situation. One aspect of the present invention has been made in view of the above problems, and its object is to generate more effective advertisement content adapted to the current situation.

Means for Solving the Problems

[0005] One aspect of the advertisement content generation device includes a reception unit that receives advertisement content generation target information, a prompt generation unit that generates a prompt based on the advertisement content generation target information, and an advertisement content generation control unit that inputs the prompt into a machine learning model that refers to a database including at least data related to media content to generate advertisement content.

[0006] One embodiment of an advertising content generation method involves at least one processor receiving information to be generated as advertising content, generating a prompt based on the information to be generated as advertising content, and inputting the prompt into a machine learning model that refers to a database containing at least media content data to generate advertising content.

[0007] One embodiment of an advertising content generation program causes a computer to function as a receiving means for receiving information to be used for generating advertising content, a prompt generating means for generating prompts based on the information to be used for generating advertising content, and an advertising content generation control means for inputting the prompts into a machine learning model that refers to a database containing at least data related to media content to generate advertising content. [Effects of the Invention]

[0008] According to one aspect of the present invention, advertising content can be generated based on accurate information by referring to media content. [Brief explanation of the drawing]

[0009] [Figure 1] This block diagram shows the configuration of the advertising content generation device related to this disclosure. [Figure 2] This flowchart illustrates the flow of generating advertising content related to this disclosure. [Figure 3] This block diagram shows the configuration of the advertising content generation device related to this disclosure. [Figure 4] An example of a screen related to this disclosure is shown. [Figure 5] An example of a screen related to this disclosure is shown. [Figure 6] An example of a screen related to this disclosure is shown. [Figure 7] This is a flowchart showing the flow of the advertising content generation method related to this disclosure. [Figure 8] This block diagram shows the configuration of a computer that functions as an advertising content generation device related to this disclosure. [Modes for carrying out the invention]

[0010] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining some or all of the technologies (things or methods) employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. In addition, the effects mentioned in each of the exemplary embodiments shown below are examples of effects that can be expected in that exemplary embodiment and do not define the scope of the present invention. That is, embodiments that do not produce the effects mentioned in each of the exemplary embodiments shown below may also be included in the scope of the present invention.

[0011] <First Embodiment> (Overall structure) In the first embodiment, an advertising content generation device is described that generates advertising content based on accurate information by referring to media content.

[0012] (Functional Configuration) Figure 1 is a block diagram showing the configuration of the advertising content generation device 1. The advertising content generation device 1 comprises a reception unit 110, a prompt generation unit 120, and an advertising content generation control unit 130.

[0013] The reception unit 110 receives information to be used for generating advertising content. The reception unit 110 may receive information to be used for generating advertising content from a recording device. Alternatively, it may receive information to be used for generating advertising content entered via a device used by the user.

[0014] The advertisement content generation target information is information including at least one of basic information (products, services, companies, etc. that are the advertisement targets) that is a target of advertisement content generation, and other peripheral information (features of the advertisement target product, target information, etc.).

[0015] The basic information is fundamental data related to products, services, companies, etc. that are the targets of advertisements. For example, the basic information is information such as the overview of the advertisement target product, target customers, provision area, and product lineup.

[0016] The peripheral information is auxiliary information related to the target of advertisement content generation. For example, it is the features of the advertisement target product provided by the advertisement orderer, desired advertisement expressions, expressions to be avoided, images and videos to be used, details of target customers, past advertisement performance (such as click rate and conversion rate), brand guidelines, access history of advertisement placement sites, trend information, and the like.

[0017] The prompt generation unit 120 generates a prompt based on the advertisement content generation target information received by the reception unit 110. Specifically, for example, the prompt generation unit 120 generates the prompt by incorporating the advertisement content generation target information into a predetermined template. The prompt is an instruction statement to be input to a generation model described later. For example, the prompt is a natural language sentence including the advertisement content generation target information. The prompt generation unit 120 outputs the prompt based on the advertisement content generation target information to the advertisement content generation control unit 130.

[0018] The advertisement content generation control unit 130 receives the prompt generated by the prompt generation unit 120 as an input, and generates advertisement content using a machine learning model (generation model) that references a database containing data related to media content. The database includes data related to media content, and for example, includes media content such as newspaper articles, economic and financial data, industry reports, academic papers, social media data, government announcement data, patent information, and market research reports. The database may also include specific features of products targeted for advertisement content, industry trend information, and the like. Retrieval-augmented generation technology such as RAG (Retrieval-Augmented Generation) may be used for referencing the database. This makes it possible to reflect media content not included in the learning data of the generation model and detailed information related to a specific domain in the response.

[0019] Advertising content is content generated for the purpose of promoting a specific product, service, brand, or company. The content can take the form of text, images, videos, audio, or other media, and may be a combination of multiple media forms. The machine learning model can be any machine learning model, such as a large-scale language model, a time series forecasting model, or a multimodal model. For example, if both the input prompt and the output response are natural language text data, then a language model trained on natural language can be applied as the generative model. Here, training on natural language means, more specifically, training on the arrangement of its constituent elements (words, etc.) in natural language sentences, or the arrangement of sentences in texts. Examples of such language models include BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), and ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately). Furthermore, the generative model may be a fine-tuned general-purpose generative model that accurately generates the information necessary to generate advertising content. For fine tuning, the training data can consist of pairs of prompts and the responses that should be generated for those prompts.

[0020] The above machine learning model may be stored in the advertising content generation device 1 or in another device. In the latter case, the advertising content generation control unit 130 can send a prompt to the other device to generate a response and retrieve the generated response from the other device. The database may be included in the advertising content generation device 1 or connected externally to the advertising content generation device 1.

[0021] As described above, the advertising content generation apparatus 1 according to this exemplary embodiment employs a configuration comprising: a reception unit 110 that receives information to be generated as advertising content; a prompt generation unit 120 that generates prompts based on the information to be generated as advertising content; and an advertising content generation control unit 130 that inputs the prompts into a machine learning model that refers to a database containing at least media content data to generate advertising content.

[0022] According to the above configuration, the advertising content generation device 1 generates advertising content based on media content that reflects the current situation, such as newspaper articles and reliable reports stored in the database, thus producing more effective advertising content that is tailored to the current situation.

[0023] (Advertising content generation program) The functions of the advertising content generation device 1 described above can also be implemented by a program. The advertising content generation program according to this exemplary embodiment enables a computer to function as a receiving means for receiving advertising content generation target information, a prompt generation means for generating prompts based on the advertising content generation target information, and an advertising content generation control means for inputting the prompts into a machine learning model that refers to a database containing at least media content data to generate advertising content. This advertising content generation program has the effect of generating more effective advertising content tailored to the current situation.

[0024] (Flowchart for generating advertising content) The flow of advertising content generation according to this exemplary embodiment will be explained with reference to Figure 2. Figure 2 is a flowchart showing the flow of the advertising content generation method. Note that the entity executing each step in this advertising content generation method may be a processor provided in the advertising content generation device 1, a processor provided in another device, or the entity executing each step may be a processor provided in a different device.

[0025] In S1 (reception processing), at least one processor receives information for which advertising content will be generated.

[0026] In S2 (prompt generation process), at least one processor generates a prompt based on the advertising content generation target information received in S1.

[0027] In S3 (Advertising Content Generation Control Processing), at least one processor inputs the prompt generated in S2 into a machine learning model that references a database containing at least media content data, generating a response that generates advertising content.

[0028] As described above, the advertising content generation method according to this exemplary embodiment employs a configuration that includes a reception process for receiving information to be generated as advertising content, a prompt generation process for generating prompts based on the information to be generated as advertising content, and an advertising content generation control process for inputting the prompts into a machine learning model that refers to a database containing at least media content data to generate advertising content. Therefore, with the above configuration, the advertising content generation method has the effect of generating more effective advertising content that is tailored to the current situation.

[0029] The entities executing each process described in the exemplary embodiments above are arbitrary and not limited to the examples given. For example, a system having the same functions as the advertising content generation device 1 can be constructed using multiple devices that can communicate with each other. Furthermore, the entities executing each process shown in the flowchart in Figure 2 may be a single device (which can also be called a processor) or multiple devices (which can also be called processors).

[0030] [Second Embodiment] A second embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same function as those described in the exemplary embodiments described above are denoted by the same reference numerals, and their descriptions are omitted as appropriate. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise. Furthermore, each technology shown in the drawings referenced to describe this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise.

[0031] (Configuration of advertising content generation device 1A) The configuration of the advertising content generation device 1A according to the second embodiment will be described with reference to Figure 3. Figure 3 is a block diagram showing the configuration of the advertising content generation device 1A. The advertising content generation device 1A is a device equipped with an advertising content generation function that generates advertising content. The advertising content generation device 1A may be a local device used by individual users, or it may be a server that provides advertising content generation services to multiple users.

[0032] As shown in Figure 3, the advertising content generation device 1A includes a control unit 10A that comprehensively controls each part of the advertising content generation device 1A, and a storage unit 11A that stores various data used by the advertising content generation device 1A. The advertising content generation device 1A also includes a communication unit 12A for the advertising content generation device 1A to communicate with other devices, an input unit 13A that receives input to the advertising content generation device 1A, and an output unit 14A for the advertising content generation device 1A to output data. The control unit 10A includes a reception unit 110A, a prompt generation unit 120A, an advertising content generation control unit 130A, a verification unit 140A, and a presentation control unit 150A.

[0033] The reception unit 110A, the prompt generation unit 120A, and the advertising content generation control unit 130A have the same configuration as the reception unit 110, the prompt generation unit 120, and the advertising content generation control unit 130 of the first embodiment, respectively, and their description will be omitted.

[0034] The verification unit 140A verifies whether the content of the advertising content generated by the advertising content generation control unit meets predetermined criteria and outputs the verification result to the presentation control unit 150A. Specifically, for example, the verification unit 140A verifies whether the content of the advertising content meets predetermined criteria and rules set in advance. The pre-set rules indicate, for example, whether the advertising content contains predetermined keywords or expressions that evoke those keywords (discriminatory expressions, potentially misleading words, legally problematic expressions, etc.).

[0035] Furthermore, the verification unit 140A may verify whether the advertising content meets predetermined criteria based on media content stored in the database. Specifically, for example, the verification unit 140A calculates an index indicating the degree to which the advertising content is based on media content, and verifies whether the calculated index meets predetermined criteria. The index is calculated using RAG (Retrieval Augmented Generation). Specifically, the verification unit 140A uses the advertising content as a query and extracts a portion of the media content using the query. Next, the verification unit 140A calculates the similarity between the extracted media content and the query (advertising content). Finally, the verification unit 140A verifies whether the calculated similarity index meets predetermined criteria. The rules, keyword list, and machine learning model used by the verification unit 140A may be stored in the advertising content generation device 1A or in another device.

[0036] The presentation control unit 150A controls the presentation of advertising content generated by the advertising content generation control unit 130A based on the verification results input from the verification unit 140A. "Presentation" means making the content recognizable to the user (for example, the person who specified the target for advertising content generation). Specifically, for example, if the verification results indicate that the advertising content meets predetermined criteria, the presentation control unit 150A displays the advertising content on the display device. This allows the user to recognize the advertising content displayed on the display device. Alternatively, for example, the presentation control unit 150A may control the uploading of the advertising content to a server accessible to the user. This allows the user to access the server and recognize the advertising content uploaded by the presentation control unit 150A.

[0037] As described above, the advertising content generation device 1A according to the second embodiment employs a configuration comprising: a reception unit 110A that receives information to be generated as advertising content; a prompt generation unit 120A that generates prompts based on the information to be generated as advertising content; and an advertising content generation control unit 130A that inputs the prompts into a machine learning model that refers to a database containing at least media content data to generate advertising content. Therefore, similar to the advertising content generation device 1, the advertising content generation device 1A has the effect of generating more effective advertising content tailored to the current situation.

[0038] Furthermore, as described above, the advertising content generation device 1A includes a verification unit 140A that verifies whether the content of the advertising content generated by the advertising content generation control unit 130A meets predetermined criteria. It also includes a presentation control unit 150A that, if the verification unit 140A verifies that the predetermined criteria are met, controls the device to present the advertising content. This provides, in addition to the effects of the advertising content generation device 1 described in the first embodiment, the added benefit of preventing the presentation of advertising content that does not meet the predetermined criteria.

[0039] (Modified version of Embodiment 2) The following describes embodiments of each component that reflect user feedback (e.g., requests for corrections or additional information) in the advertising content presented by the presentation control unit 150A, as a modification of the second embodiment. Specifically, for example, the reception unit 110A receives natural language feedback input via the device used by the user and outputs it to the prompt generation unit 120A. The prompt generation unit 120A uses a language model that has learned natural language to generate prompts that reflect the requests for corrections or additional information indicated by the feedback input from the reception unit 110A. For example, the prompt generation unit 120A generates a prompt indicating instructions regarding the correction of the content of the advertising content. The advertising content generation control unit 130A uses the newly generated prompts from the prompt generation unit 120A to generate advertising content that reflects the feedback.

[0040] The feedback may not only involve partial textual revisions, but also instructions that involve restructuring the overall concept and design of the advertisement. Specifically, for example, a user might provide feedback requesting a change to the overall concept of the advertisement (e.g., "emphasize a specific selling point more"). In this case, the prompt generation unit 120A and the advertisement content generation control unit 130A will generate advertisement content with the overall structure modified according to the instructions through the aforementioned processing.

[0041] This feedback function enables interactive use of the advertising content generation device 1A by the user, resulting in the generation of advertisements that are more tailored to the user's needs and intentions.

[0042] (Example of reception screen) Figure 4 illustrates a reception screen for the reception unit 110A to receive information for generating advertising content. The reception unit 110A may also receive information from the user via the reception screen A11 shown in Figure 4. As shown in Figure 4, the reception screen A11 consists of input forms A12, A13, and A14.

[0043] For example, input form A12 contains the user's answer to the question, "Please enter the product for which you want to create an advertisement." Input form A13 contains the user's answer to the question, "Please tell us the features of the product you want to highlight in the advertisement." Input form A14 is a checkbox for selecting information to use as reference. The user uses the checkbox to select information to use as reference from the information shown in input form A14. The reception unit 110A accepts the information entered or selected in input forms A12, A13, and A14 as information to be used for generating advertising content.

[0044] (Example of a screen displayed by the display control unit) Figure 5 shows an example screen presented by the presentation control unit 150A. The screen shown in Figure 5 displays advertisement content A21, A22, and A23 as advertisement proposal 1, and advertisement content A24, A25, and A26 as advertisement proposal 2, with edit buttons A27 and A28 displayed for each advertisement proposal. Advertisement content A21 and A24 show the advertisement title. Advertisement content A22 and A25 are advertisement content shown in text. Advertisement content A23 and A26 are advertisement content shown in images. Edit buttons A27 and A28 are buttons that transition to the feedback input screen for each corresponding content (described later using Figure 6).

[0045] (Example of feedback screen) Figure 6 illustrates a feedback screen that appears when a user clicks either of the edit buttons A27 or A28 shown in Figure 5.

[0046] As shown in Figure 6, the feedback screen consists of, for example, the ad content A31, A32, and A33 to be provided feedback on, the correction instruction input form A34, and the confirmation button A35. For example, if the edit button A27 shown in Figure 5 is clicked, the ad content A21, A22, and A23 will be displayed in the ad content A31, A32, and A33 in Figure 6.

[0047] The revision instruction input form A34 is a form for users to input feedback on advertising content. For example, users can input revision or addition instructions in free-form text on the revision instruction input form A34, such as "I'd like the tone to be a little softer" or "I'd like the word 'Sakura' to be emphasized." After inputting into the revision instruction input form A34, when the user clicks the confirmation button A35, the presentation control unit 150A outputs the feedback content to the reception unit 110A. The prompt generation unit 120A generates a prompt based on the feedback received by the reception unit 110A and outputs it to the advertising content generation control unit 130A. The advertising content generation control unit 130 generates advertising content that reflects the feedback based on the prompt generated by the prompt generation unit 120A. As a result, the advertising content generation device 1A can generate advertisements that better reflect the user's wishes.

[0048] (Process flow) The flow of the advertising content generation method according to the second embodiment will be explained with reference to Figure 7. Figure 7 is a flowchart showing the flow of the advertising content generation method. Note that the entity executing each step in this advertising content generation method may be a processor provided in the advertising content generation device 1, a processor provided in another device, or the entity executing each step may be a processor provided in a different device.

[0049] In S11 (reception processing), at least one processor receives information for which advertising content will be generated.

[0050] In S12 (prompt generation process), at least one processor generates a prompt based on the advertising content generation target information received in S11.

[0051] In S13 (advertising content generation control processing), at least one processor inputs the prompt generated in S12 into a machine learning model that references a database containing at least media content data, causing it to generate advertising content.

[0052] In S14 (verification process), at least one processor verifies whether the content of the advertising content generated in S13 meets predetermined criteria.

[0053] In S15 (presentation control processing), at least one processor presents the advertising content generated in S13.

[0054] As described above, the advertising content generation method according to the second embodiment employs a configuration that includes: a reception process for receiving information to be generated for advertising content; a prompt generation process for generating a prompt based on the information to be generated for advertising content; an advertising content generation control process for inputting the prompt into a machine learning model that refers to a database containing at least media content data to generate advertising content; a verification process for verifying whether the content of the advertising content is appropriate; and a presentation control process for presenting the advertising content. This provides the effect of reducing the possibility of presenting advertising content that does not meet predetermined criteria, in addition to the effects achieved by the exemplary embodiment 1.

[0055] The entities executing each process described in the second embodiment above are arbitrary and not limited to the examples given. For example, a system having the same functions as the advertising content generation device 1A can be constructed using multiple devices that can communicate with each other. Also, the entities executing each process shown in the flowchart in Figure 7 may be a single device (which can also be called a processor) or multiple devices (which can also be called processors).

[0056] (Example of implementation using software) Some or all of the functions of the advertising content generation devices 1 and 1A (hereinafter also referred to as "each of the above devices") may be implemented by hardware such as integrated circuits (IC chips) or by software.

[0057] (Hardware configuration) In the latter case, each of the above devices is implemented, for example, by a computer C that executes instructions for a program, which is software that realizes each function. Figure 8 is a block diagram showing the hardware configuration of the advertising content generation device 1. As shown in the figure, the advertising content generation device 1 includes a processor 2, an input / output interface 3, a ROM (Read Only Memory) 4, a RAM (Random Access Memory) 5, and a storage device 6. Each component is connected to the others, for example, via a bus 7.

[0058] Processor 2 is a computer such as a CPU (Central Processing Unit) that controls the entire advertising content generation device 1 by executing a pre-prepared program. Specifically, as processor 2, a CPU, GPU (Graphics Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof can be used.

[0059] Furthermore, processor 2 loads the program stored in ROM 4, storage device 6, etc. Then processor 2 executes each process coded in the program. Also, processor 2 functions as part or all of advertising content generation device 1. And processor 2 may execute processes or instructions in the flowchart based on the program.

[0060] Input / output interface 3 is an interface for connecting input / output devices such as keyboards, mice, displays, and printers.

[0061] ROM4 stores various programs executed by processor 2. RAM5 is used as working memory while processor 2 is executing various processes.

[0062] The storage device 6 is a non-volatile, non-temporary storage device. For example, the storage device 6 may be a disk-shaped recording medium, a semiconductor memory, or the like. The storage device 6 may be configured to be detachable from the advertising content generation device 1. The storage device 6 stores various programs executed by the processor 2.

[0063] Furthermore, each of the above functions of each of the above devices may be implemented by a single processor in a single computer, by multiple processors in a single computer working together, or by multiple processors in each of multiple computers working together. In addition, the programs for implementing each of the above functions in each of the above devices may be stored in a single memory in a single computer, distributed and stored in multiple memories in a single computer, or distributed and stored in multiple memories in each of multiple computers.

[0064] (Note 1) A reception department that receives information to be used for generating advertising content, A prompt generation unit that generates a prompt based on the aforementioned advertising content generation target information, An advertising content generation control unit inputs the aforementioned prompt to a machine learning model that references a database containing at least data related to media content to generate advertising content, An advertising content generation device equipped with the following features.

[0065] (Note 2) The advertising content generating apparatus according to Appendix 1, characterized in that the advertising content consists of at least one of text and an image.

[0066] (Note 3) A verification unit that verifies whether the content of the aforementioned advertising content meets predetermined standards, If the verification unit verifies that the advertising content meets predetermined criteria, the presentation control unit controls the display of the advertising content, An advertising content generation device as described in Appendix 1, comprising the features described in Appendix 1.

[0067] (Note 4) The reception unit receives feedback on the advertising content output by the presentation control unit, The prompt generation unit generates a prompt based on the feedback, The advertising content generation control unit generates advertising content based on prompts generated based on the feedback, as described in Appendix 3.

[0068] (Note 5) The advertising content generation device described in Appendix 1, wherein the information to be used for generating advertising content includes at least one of the information on the advertised product, target information, and trend information.

[0069] (Note 6) At least one processor, We accept information to be used for generating advertising content. Based on the aforementioned information for generating advertising content, a prompt is generated. The aforementioned prompt is input to a machine learning model that references a database containing at least data related to media content to generate advertising content. Methods for generating advertising content.

[0070] (Note 7) Computers, A means for receiving information to be used for generating advertising content, Prompt generation means for generating a prompt based on the advertising content generation target information, and An advertising content generation control means that inputs the aforementioned prompt into a machine learning model that references a database containing at least data related to media content to generate advertising content. An advertising content generation program that functions as such.

[0071] Furthermore, some or all of the configurations described in Appendices 2 to 5, which are dependent on Appendice 1 above, may also be dependent on Appendices 6 and 7, respectively, through the same dependency relationships as those described in Appendices 2 to 5. Moreover, not limited to Appendices 1, 6, and 7, some or all of the configurations described as appendices may also be dependent on various hardware, software, various recording means for recording software, or systems, without departing from the embodiments described above. [Explanation of Symbols]

[0072] 1. 1A Advertising Content Generation Device 110 Reception area (reception method) 120 Prompt generation unit (prompt generation means) 130 Advertising content generation control unit (advertising content generation control means) 110A Reception area (reception method) 120A Prompt generation unit (prompt generation means) 130A Advertising content generation control unit (advertising content generation control means) 140A Verification Unit (Verification Means) 150A Presentation Control Unit (Presentation Control Means)

Claims

1. A reception department that receives information to be used for generating advertising content, A prompt generation unit that generates a prompt based on the aforementioned advertising content generation target information, An advertising content generation control unit inputs the aforementioned prompt to a machine learning model that references a database containing at least data related to media content to generate advertising content, An advertising content generation device equipped with the following features.

2. The advertising content generating apparatus according to claim 1, characterized in that the advertising content consists of at least one of text and an image.

3. A verification unit that verifies whether the content of the aforementioned advertising content meets predetermined standards, If the verification unit verifies that the advertising content meets predetermined criteria, the presentation control unit controls the display of the advertising content. The advertising content generation apparatus according to claim 1, comprising:

4. The reception unit receives feedback on the advertising content output by the presentation control unit, The prompt generation unit generates a prompt based on the feedback, The advertising content generation device according to claim 3, wherein the advertising content generation control unit generates advertising content based on prompts generated based on the feedback.

5. The advertising content generation apparatus according to claim 1, wherein the information to be used for generating advertising content includes at least one of the information of the product to be advertised, target information, and trend information.

6. At least one processor, We accept information to be used for generating advertising content. Based on the aforementioned information for generating advertising content, a prompt is generated. The aforementioned prompt is input to a machine learning model that references a database containing at least data related to media content to generate advertising content. Methods for generating advertising content.

7. Computers, A means for receiving information to be used for generating advertising content, Prompt generation means for generating a prompt based on the advertising content generation target information, and An advertising content generation control means that inputs the aforementioned prompt into a machine learning model that references a database containing at least data related to media content to generate advertising content. An advertising content generation program that functions as such.

Images