Program, output device, and output method

The program and output device leverage generative AI to generate targeted advertising strategies based on product features and objectives, addressing the lack of clarity in existing promotion methods and optimizing AI efficiency.

WO2026235097A1PCT designated stage Publication Date: 2026-11-12NEC CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2026/017161
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-04-30
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Existing product promotion methods lack clarity in advertising strategies, making it difficult for advertisers to effectively grasp the image of the measures being implemented.

Method used

A program and output device utilizing a generative AI to receive product feature and policy objective information, generating appropriate advertising methods by inputting this data into a pre-trained AI to output clear promotion strategies.

Benefits of technology

Enables effective and clear output of advertising methods tailored to product characteristics and promotional objectives, reducing redundant processing and resource consumption by the AI.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2026017161_12112026_PF_FP_ABST
    Figure JP2026017161_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A program according to the present disclosure causes a computer to execute: a reception step for receiving, from a user, product feature information indicating the features of a product and initiative purpose information indicating the purpose of an initiative for advertising the product; an initiative information acquisition step for inputting the product feature information and the initiative purpose information into a generative artificial intelligence (AI) that has been trained so as to generate initiative information related to an initiative including an advertising method for the product when the product feature information and the initiative purpose information are input, and acquiring the generated initiative information; and an output step for outputting an advertising method on the basis of the initiative information. Thus, there is provided a program with which it is possible to output a method for advertising a product in an initiative in an appropriate manner.
Need to check novelty before this filing date? Find Prior Art

Description

Program, Output Device, and Output Method

[0001] The present disclosure relates to a program, an output device, and an output method.

[0002] Technologies are known that support the planning of measures for effectively promoting products and services. As a related technology, Patent Document 1 discloses a data processing apparatus that accurately predicts a person's product-related behavior while taking into account the influence of factors that motivate a person to take action and measures implemented in relation to the product.

[0003] Japanese Unexamined Patent Application Publication No. 2024-007647

[0004] If the product promotion method in the planned measure is not clear, the advertiser cannot easily grasp the image of the measure.

[0005] In view of the above-described problems, an object of the present disclosure is to provide a program, an output device, and an output method capable of appropriately outputting a product promotion method in a measure.

[0006] The program according to the present disclosure causes a computer to execute: a reception step of receiving, from a user, product feature information indicating features of a product and measure purpose information indicating a purpose of a measure for promoting the product; a measure information acquisition step of inputting the product feature information and the measure purpose information into a generative AI (Artificial Intelligence) trained to generate measure information related to the measure including the promotion method of the product when the product feature information and the measure purpose information are input, and acquiring the generated measure information; and an output step of outputting the promotion method based on the measure information.

[0007] The output device relating to this disclosure comprises: a receiving unit that receives product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition unit that inputs the product feature information and the policy objective information to a generating AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product, and acquires the generated policy information; and an output unit that outputs the promotion method based on the policy information.

[0008] The output method relating to this disclosure includes: a reception step of receiving product feature information indicating the characteristics of a product and policy objective information indicating the purpose of a policy for promoting the product from a user; a policy information acquisition step of inputting the product feature information and the policy objective information into a generating AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product, and acquiring the generated policy information; and an output step of outputting the promotion method based on the policy information.

[0009] The program, output device, and output method relating to this disclosure can appropriately output methods for advertising products in a policy.

[0010] Figure 1 is a block diagram showing the configuration of the output device. Figure 2 is a flowchart showing the processing flow performed by the output device. Figure 3 is a block diagram showing the configuration of the information provision system. Figure 4 is a block diagram showing the configuration of the output device. Figure 5 is a diagram showing an example of an input screen displayed on the display unit of a communication terminal. Figure 6 is a diagram showing an example of a prompt generated based on product feature information and policy objective information. Figure 7 is a diagram showing an example of policy information created by the generating AI. Figure 8 is a block diagram showing the configuration of a communication terminal. Figure 9 is a block diagram showing the configuration of a customer information management device. Figure 10 is a flowchart showing the processing flow performed by the output device. Figure 11 is a block diagram illustrating the hardware configuration of a computer that implements the output device, etc.

[0011] Embodiments of this disclosure will be described in detail below with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals. For clarity of explanation, redundant explanations will be omitted where necessary.

[0012] <Embodiment 1> (Output device 100) Figure 1 is a block diagram showing the configuration of the output device 100 according to the present disclosure. The output device 100 comprises a receiving unit 101, a policy information acquisition unit 102, and an output unit 103.

[0013] The reception unit 101 receives product feature information, which indicates the characteristics of the product, and policy objective information, which indicates the purpose of the measures to promote the product, from the user. The policy information acquisition unit 102 inputs the product feature information and policy objective information into a pre-trained generating AI (Artificial Intelligence) and acquires the generated policy information. The generating AI is trained to generate policy information, including the method of promoting the product, when it receives product feature information and policy objective information as input. The output unit 103 outputs the promotion method based on the policy information.

[0014] The output device 100 includes a processor, memory, and storage device (not shown). The storage device stores a computer program on which the processing described herein is implemented. The processor can load the computer program from the storage device into memory and execute the computer program. In this way, the processor realizes the functions of the reception unit 101, the policy information acquisition unit 102, and the output unit 103.

[0015] Alternatively, the reception unit 101, the policy information acquisition unit 102, and the output unit 103 may each be implemented with dedicated hardware. Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be configured by a single chip or by multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the aforementioned circuits, etc., and programs.

[0016] (Processing of output device 100) The processing performed by output device 100 will be explained with reference to Figure 2. Figure 2 is a flowchart showing the flow of processing performed by output device 100.

[0017] First, the reception unit 101 receives product feature information and policy objective information from the user (S1). Next, the policy information acquisition unit 102 inputs the product feature information and policy objective information into the generating AI (S2). The policy information acquisition unit 102 acquires policy information from the generating AI (S3). Then, the output unit 103 outputs advertising methods based on the policy information (S4).

[0018] As explained above, the output device 100 relating to this disclosure can appropriately output the advertising method for products in the policy.

[0019] <Embodiment 2> Next, Embodiment 2 will be described. Embodiment 2 is a specific example of Embodiment 1 described above. Figure 3 is a block diagram showing the configuration of the information provision system 1 according to this disclosure. The information provision system 1 is a system capable of providing information to a user. The user is a user of the information provision system 1. The user may be, for example, a person who uses the communication terminal 20.

[0020] The information provision system 1 comprises an output device 10, a communication terminal 20, and a customer information management device 30. The output device 10, the communication terminal 20, and the customer information management device 30 can communicate with each other via a network N. The network N includes, for example, an internet connection or a wireless communication network, but the type of communication is not limited to these. The output device 10, the communication terminal 20, and the customer information management device 30 each have a communication unit (not shown in Figure 3) and communicate with each other via the network N.

[0021] (Output device 10) Figure 4 is a block diagram showing the configuration of the output device 10. The output device 10 is a device that generates measures for advertising a product based on conditions specified by the user and can appropriately output the method of advertising the product in said measures. For example, the output device 10 obtains user-desired conditions from the communication terminal 20 and executes predetermined processing. The output device 10 may be composed of a server device or the like.

[0022] A "product" is an item that is the subject of marketing. The genre of the product is arbitrary. Products may include, for example, food, beverages, hygiene products, cosmetics, accessories, books, or home appliances. A product can be any item that is being considered for sales promotion. Furthermore, products are not limited to physical goods but also include services. Products may include services in various fields, such as streaming services or wealth management.

[0023] Output device 10 is an example of the output device 100 described above. Output device 10 comprises a reception unit 11, a policy information acquisition unit 12, an output unit 13, a communication unit 15, and a storage unit 16.

[0024] The reception unit 11 is an example of the reception unit 101 described above. The reception unit 11 receives product feature information indicating the characteristics of the product and policy objective information indicating the purpose of the measures to promote the product from the user. As a result, the reception unit 11 obtains the product feature information and the policy objective information.

[0025] Product feature information is information that describes the characteristics of a product. This information may include, for example, the nature, category, intended use, ingredients, or price range of the product. Product feature information is used to analyze customer interest and to develop appropriate marketing strategies. Product feature information may include not only text information describing the product's characteristics, but also images of the product.

[0026] For example, the reception unit 11 receives product feature information via the display screen of the communication terminal 20. The communication terminal 20 is equipped with a display unit 22 that displays various display screens for receiving information in the information provision system 1.

[0027] The reception unit 11 can receive input on the display screen shown on the display unit 22 of the communication terminal 20 and acquire product feature information. For example, the reception unit 11 may receive text input from a predetermined input field on the screen and acquire product feature information by performing natural language processing on the input text. The reception unit 11 acquires product feature information by using natural language processing to extract product features from the input text.

[0028] Product feature information may include, for example, product feature tags that indicate the characteristics of the product. Product feature tags may include, but are not limited to, information indicating the product's category, brand, function, use, ingredients, or price range. Various types of information indicating the characteristics of a product may be included as product feature tags. Product feature information for a single product may include multiple product feature tags. Product feature information may also be obtained based on whether or not a word in the input text matches a predefined product feature tag. Alternatively, product feature tags similar to a word may be identified based on the feature quantity of that word.

[0029] Furthermore, the reception unit 11 may accept the designation of an information source containing product information and obtain product characteristic information by extracting the product characteristics contained in the designated information source. An information source containing product information is a data source that provides detailed product information. An information source is, for example, a web page or database that describes product details. An information source includes the manufacturer's official website, an e-commerce site's product page, or a product catalog. An information source may be designated by entering a URL, or by specifying a specific database or file. The process for designating an information source may be accepted when the display screen shown on the display unit 22 of the communication terminal accepts input. Alternatively, the information source may be designated before or after the input is accepted on the display screen shown on the display unit 22. Furthermore, the display screen shown on the display unit 22 may perform processing to identify the information source based on the input information.

[0030] Figure 5 shows an example of input screen A displayed on the display unit 22 of the communication terminal 20. Input screen A is a screen for the user to input the necessary information in order to generate a customer cluster from product or service information.

[0031] As shown in Figure 5, input screen A includes a name field a1, a product features input field a2, a URL field a3, and an analysis start button a4. The name field a1 is for entering the name of the product or service. The product features input field a2 is for entering the product's features. The URL field a3 is for entering the URL of the webpage where the product information is posted. The analysis start button a4 is a button for starting the analysis of customer clusters.

[0032] The reception unit 11 may obtain product feature information from the input content in the product feature input field a2. Alternatively, the reception unit 11 may access the page at the URL entered in the URL field a3 and obtain product feature information from the content of that page. In this case, the reception unit 11 obtains product feature information by performing natural language processing on the text data on the page and extracting words related to the product's features. For example, the reception unit 11 analyzes the headings, product descriptions, specification tables, or tag information on the page to identify features such as the product name, brand, category, ingredients, or intended use.

[0033] Policy objective information is information that indicates the objectives that the policy being created should achieve. Policy objective information includes, but is not limited to, increasing product sales, increasing brand awareness, acquiring new customers, or appealing to a specific target group. Furthermore, policy objective information may represent an absolute ideal state to be achieved by the implementation of the policy, or it may represent a relative degree of improvement to be achieved with respect to a certain indicator. If the policy objective information represents a relative degree of improvement to be achieved with respect to a certain indicator, the reception unit 11 may obtain the source data from a predetermined information medium. The predetermined information medium may be, for example, the Web (World Wide Web), internal company data, or user input.

[0034] Policy objective information may be set by the user as appropriate. Although not shown in the diagram, policy objective information may also be entered via the communication terminal 20 using a screen such as input screen A in Figure 5. By providing a policy objective information input field on a screen such as input screen A, the user can input policy objective information using the communication terminal 20. The reception unit 11 acquires the policy objective information via the communication terminal 20.

[0035] The output device 10, in a prompt generation unit (not shown), can generate prompts used to instruct the creation of a policy based on product feature information and policy objective information entered via the input screen A. The prompt generation unit generates prompts with specific and objective-oriented instructions for creating a policy by reflecting the product name and product features included in the product feature information, and the sales target and awareness improvement objectives included in the policy objective information. If the input UI provided on the input screen A indicates that there are items that have not been entered, a pop-up display containing a predetermined message may be displayed to prompt the user to enter the items. Similarly, if the number of characters in a text box is excessive, a pop-up display containing a predetermined message may be displayed to prompt the user to reduce the number of characters. The acceptable number of characters may be changed depending on the model of the generation AI used.

[0036] Figure 5 shows an example where the product is mouthwash, but below, for a more concrete explanation, we will use an example where the product is a beverage.

[0037] Figure 6 shows an example of prompt B generated based on product feature information and policy objective information. The output device 10 can create a policy by inputting prompt B to the trained generation AI. Below, we will explain an example in which the trained generation AI is stored as generation AI 161 in the storage unit 16 of the output device 10. Furthermore, below, we will explain using the case where the product is "Beverage X Sugar-Free" as shown in Figure 6.

[0038] Prompt B includes items b1 to b3, for example. Item b1 includes details such as the role of the user utilizing Information Provision System 1 and the objectives of the measures. Here, it indicates that the person in charge of the marketing department is responsible for considering promotional measures, and that the goal is to achieve annual sales of 3 billion yen per product.

[0039] Item b2 includes content for setting biases in policy formulation. Policy formulation bias is information used to determine the direction and focus of a policy. Policy formulation bias can be expressed, for example, as words or sentences that characterize a product. In addition, information such as media can be provided as a bias in policy formulation as one of the elements for determining the direction of the policy. Note that media includes visual works such as anime and movies, and musical works such as J-POP. Furthermore, policy formulation bias is not limited to these, and may also be a specific person or character. In addition, policy formulation bias may be expressed as a genre. This allows the output device 10 to create policies that are suitable for the characteristics and purpose of the product, taking into account the policy formulation bias. Policy formulation bias may also specify the range of information to be referenced and the viewpoints to be emphasized in the RAG (Retrieval-Augmented Generation) of the generation AI 161. The viewpoints will be described later. Note that in item b2, the user may set biases that they do not want to be applied.

[0040] In the example in Figure 6, the product features are described as follows: "Our 'Beverage X' series is a refreshing and pleasantly tasty chu-hi (Japanese alcoholic beverage)," "The 'Beverage X Sugar-Free' series is not sweet," and "Made without any added sugars or sweeteners." This allows the system to generate strategies that emphasize the refreshing taste and lack of sweetness. Additionally, candidates for animations to collaborate with the product (hereinafter referred to as "animations"), namely animations A1 to A4, and the characteristics of each animation are entered. The characteristics of each animation can be entered by the system searching the web or SNS (Social Networking Service) based on the given animation name. This provides a bias based on the characteristics of each animation, allowing the generating AI 161 to generate more distinctive strategies.

[0041] Item b3 includes the content of domain knowledge shared between departments. Item b3 includes, for example, persona profiles representing the product's target audience and information on past initiatives. A persona profile is a typical customer profile that is expected to use the product targeted by the initiative. The domain knowledge included in item b3 may be based on information on past initiatives or knowledge shared within departments.

[0042] In the example in Figure 6, information is provided about the persona, such as "men and women in their late 20s to early 40s," "people who want to easily relax at home after work or on weekends, or who want to enjoy drinks casually at home parties," and "people who are looking for a 'convenient and refreshing drink,' and who want to enjoy a fruity taste with a moderate alcohol content." In addition, information about past campaigns is provided, including the product, the anime that collaborated with the product, the customer segments that accepted and did not accept the product, and the success or failure of the campaign.

[0043] In this manner, the reception unit 11 can receive product feature information and measure purpose information from the communication terminal 20, and generate Prompt B based thereon. Note that Prompt B shown in FIG. 6 is an example, and the information included in Prompt B may be modified as appropriate. While these pieces of information can be input by the user in any order in text format, the present invention is not limited thereto. In an interface such as an interactive format, an input obtained as a response to a question presented by a chatbot may be reflected in a predetermined text box each time. Alternatively, a desired input may be realized by allowing the user to specify a preset candidate for each item.

[0044] Returning to FIG. 4. The measure information acquisition unit 12 is an example of the measure information acquisition unit 102 described above. When the product feature information and the measure purpose information are input, the measure information acquisition unit 12 inputs the product feature information and the measure purpose information to the generative AI 161 that has been trained to generate measure information related to measures including product promotion methods. Thereby, the generative AI 161 generates the measure information based on the input product feature information and measure purpose information. The measure information acquisition unit 12 acquires the generated measure information.

[0045] The measure information acquisition unit 12 may cause the generative AI 161 to generate a plurality of pieces of measure information. For example, in the example of FIG. 6, the measure information acquisition unit 12 may cause the generative AI 161 to generate respective pieces of measure information for each of the four animations A1 to A4 listed as collaboration animation candidates. This allows the user to compare a plurality of pieces of measure information and examine which measure is preferable. In order to cause such generation, when a plurality of candidates are given as inputs, the generative AI 161 may be instructed in advance to generate measure information for each candidate. Such an instruction may be given in the form of a prompt, and does not necessarily need to be provided in a form visible to the user.

[0046] The viewpoint indicates a perspective taken into account when generating measure information. Examples of the viewpoint include the content of a measure executed by a user and the reason for proposing the relevant measure. Without being limited to these, the viewpoint may be, for example, an issue to be resolved by the measure, an advantage of the measure, an appeal point of the measure, or a story of the measure. The viewpoint only needs to indicate a perspective that can be considered in creating the measure.

[0047] For example, the measure information acquisition unit 12 may cause the generative AI 161 to identify a viewpoint used in generating the measure information based on the product feature information and the measure purpose information, and generate the measure information based on the identified viewpoint. The viewpoint may be configured to be automatically selected by the generative AI 161 based on information extracted from elements related to product features and measure goals. For example, the measure information acquisition unit 12 causes the generative AI 161 to identify an effective viewpoint based on categories and keywords included in the product features, or target contents such as a sales target and awareness improvement indicated in the measure purpose information. Accordingly, the measure information acquisition unit 12 can cause the generative AI 161 to create more accurate measure information using a viewpoint suitable for the purpose of the product and the measure.

[0048] The measure information acquisition unit 12 may cause the generative AI 161 to calculate an evaluation value based on the similarity between the content corresponding to the identified viewpoint and the product feature information, and generate the measure information based on the calculated evaluation value.

[0049] For example, from the viewpoint of "proposal reason", the measure information acquisition unit 12 causes the generative AI 161 to evaluate the affinity between information such as the world view and attributes of content assumed as a collaboration partner (for example, the setting and atmosphere of an animation) and the product feature information, and calculate the relevant evaluation value.

[0050] In addition, the measure information acquisition unit 12 causes the generative AI 161 to select a collaboration partner, an expression method, action content, or the like that has high affinity with the product based on the calculated evaluation value, and combines them to generate the measure information. In this way, the measure information acquisition unit 12 can cause the generative AI 161 to generate effective measure information according to the product features and the purpose of the measure.

[0051] For example, when proposing content to collaborate with a product, the policy information acquisition unit 12 may first have the generating AI 161 extract multiple content candidates to be used in the policy based on product characteristic information and policy objective information. Next, the policy information acquisition unit 12 has the generating AI 161 calculate an evaluation value based on the similarity between each content candidate and the product characteristic information. Then, the policy information acquisition unit 12 has the generating AI 161 select content to be used in the policy from the multiple content candidates based on the calculated evaluation value. For example, the policy information acquisition unit 12 may have the generating AI 161 select the content with the highest evaluation value and propose it to the user.

[0052] Figure 7 shows an example of policy information C created by the generating AI 161. On the left side of Figure 7, the policy details c1 are shown in table format. On the right side of Figure 7, an image c2 of the advertisement used in the policy information C is shown.

[0053] The policy content c1 is structured based on perspectives. The policy content c1 includes items corresponding to, for example, "keywords," "implementation details," "problems to be solved," "reasons for proposal," "benefits," "selling points," and "story." The policy information acquisition unit 12 causes the generation AI 161 to automatically generate policy components suitable for the characteristics of the product according to each perspective. The policy information acquisition unit 12 may also give additional commands to the generation AI 161 to output the policy content in accordance with these perspectives. The additional commands may be given in the form of prompts, and such prompts may be given in a way that the user cannot see. Also, when outputting from multiple perspectives, the policy information acquisition unit 12 may give all prompts at once or give prompts in multiple stages. Naturally, each perspective can also be arbitrarily specified by the user.

[0054] In Figure 7, policy information C shows policy content c1 in a table format as an example. However, in this embodiment, the generation AI 161 generates multiple policy candidates (e.g., Plan A, Plan B, Plan C) all at once, and the user may refer to a screen that displays them for comparison (hereinafter referred to as the policy comparison screen). On this policy comparison screen, parameters such as response rate, cost-effectiveness, expected number of customers, reach rate, and estimated budget may be displayed in a list format as multiple columns, enabling numerical comparison of each policy. Furthermore, by providing a scrollable display at the bottom of the screen or on the side panel, the system may be configured to allow users to refer to design reasons, external data, supporting customer analysis results, and past success stories of similar policies.

[0055] Users can expand and display additional parameters and natural language explanations of each measure by operating the "Details" button or dropdown menu for each measure displayed on the measure comparison screen. For example, in this embodiment, detailed reasons based on customer clusters (targets) and potential needs are generated in natural language by the generation AI 161, allowing advertisers to easily understand the background and objectives of the measures. If multiple measure candidates are generated, users may compare them all at once, or they may use a function to extract only two or three options and compare them with each other.

[0056] In the example in Figure 7, strategies including keywords such as "otherworld experience," "collaboration event," and "SNS campaign" are output. This presents specific promotional strategies that are based on the anime's worldview and feature compelling storylines.

[0057] As shown in the image c2 of Figure 7, the policy information acquisition unit 12 can also cause the generation AI 161 to generate an image of an advertisement to be used in advertising based on product feature information, policy objective information, and policy information. For example, the policy information acquisition unit 12 causes the generation AI 161 to generate image c2 using an image of the product and an image of the collaborating content.

[0058] Furthermore, the policy information acquisition unit 12 can not only generate images by combining multiple images, but can also cause the generation AI 161 to generate images of catchphrases used in advertising based on product feature information, policy objective information, and policy information. By providing at least one of the product feature information, policy objective information, and policy information, the policy information acquisition unit 12 can cause the generation AI 161 to take this information into consideration. This allows the policy information acquisition unit 12 to cause the generation AI 161 to generate, for example, an image of an unexpected catchphrase. In addition, the policy information acquisition unit 12 may also provide the generation AI 161 with customer attribute information of target customers obtained from the customer information management device 30 as input.

[0059] Furthermore, the policy information acquisition unit 12 may instruct the generating AI 161 to generate storyboard images and the like based on product feature information, policy objective information, and policy information. For example, the policy information acquisition unit 12 may instruct the generating AI 161 to generate storyboard images for advertising using video, such as a television commercial.

[0060] Furthermore, the policy information acquisition unit 12 may instruct the generating AI 161 to identify the basis for the advertising method based on the product characteristic information and the policy objective information, and acquire the identified basis in the policy information. For example, as shown in "Proposal Reason" in Figure 7, the policy information acquisition unit 12 instructs the generating AI 161 to generate policy information including the basis for proposing the policy. In this way, users can easily understand the basis for which the policy is proposed.

[0061] Returning to Figure 4, the output unit 13 is an example of the output unit 103 described above. The output unit 13 outputs advertising methods based on policy information. For example, the output unit 13 outputs advertising methods and their rationale in association. Advertising methods include actions taken by advertisers. For example, the output unit 13 transmits policy information to the communication terminal 20 via the communication unit 15. As a result, the policy information, including advertising methods, is displayed on the display unit 22 of the communication terminal 20.

[0062] The output unit 13 outputs multiple policy information in a manner that allows the user to visually review it. For example, in addition to the image described above, the output unit 13 may output policy information in a list format or a table format.

[0063] The communication unit 15 is a communication interface for wired or wireless communication. The storage unit 16 stores various data and programs. At least a portion of the storage unit 16 is made of non-volatile memory so that data is retained even when the power to the output device 10 is turned off. For example, the storage unit 16 may store the generated AI 161 described above.

[0064] (Communication Terminal 20) Figure 8 is a block diagram showing the configuration of the communication terminal 20. The communication terminal 20 is a terminal device used by the user. The communication terminal 20 comprises an input unit 21, a display unit 22, and a communication unit 23. The communication terminal 20 may be, for example, a PC (Personal Computer), a smartphone, a tablet terminal, or a mobile phone.

[0065] The input unit 21 is an input device that receives user input. The input unit 21 may be, for example, a mouse, keyboard, touch panel, smartphone, tablet, or voice input device.

[0066] The display unit 22 is a display device that displays various types of information. The display unit 22 is, for example, a display. The display unit 22 may also be a touch panel that has the functions of the input unit 21. Although not shown in the figures, the communication terminal 20 may also be equipped with an audio output unit such as a speaker and output information by voice.

[0067] The communication unit 23 is a communication interface for communication via wired or wireless means.

[0068] (Customer Information Management Device 30) Figure 9 is a block diagram showing the configuration of the customer information management device 30. The customer information management device 30 is a device for managing customer information. The customer information management device 30 may be managed by, for example, a business that sells goods or services or a business that provides online payment services. The customer information management device 30 may manage customer information provided by multiple businesses. The customer information management device 30 includes a communication unit 31 and a storage unit 32.

[0069] The communication unit 31 is a communication interface for communication by wire or wireless. The storage unit 32 stores various data and programs. At least a portion of the storage unit 32 is made of non-volatile memory so that data is retained even when the power to the customer information management device 30 is turned off. The storage unit 32 may store various data, including the analysis results described above. For example, the storage unit 32 may store purchase history information 321 showing the purchase history of products.

[0070] The configuration of the information provision system 1 has been described above. Note that the configuration of the information provision system 1 described above is merely an example and can be modified as appropriate. For example, if some or all of the components of the information provision system 1 are implemented by multiple information processing devices or circuits, these devices may be centrally located or distributed. For example, the information processing devices or circuits may be implemented in a form where each is connected via a communication network, such as a client-server system or a cloud computing system. Furthermore, the functions of the output device 10 may be provided in SaaS (Software as a Service) format.

[0071] Furthermore, although the above description shows an example in which the generated AI 161 is stored in the storage unit 16 of the output device 10, the generated AI 161 may also be stored in a device other than the output device 10.

[0072] (Processing of Output Device 10) Next, the processing performed by the output device 10 will be explained with reference to Figure 10. Figure 10 is a flowchart showing the flow of processing performed by the output device 10.

[0073] First, the reception unit 11 receives product feature information and policy objective information from the user (S11). Next, the policy information acquisition unit 12 inputs the product feature information and policy objective information into the generation AI 161 (S12). The policy information acquisition unit 12 causes the generation AI 161 to identify the perspectives to be used in generating policy information based on the product feature information and policy objective information (S13).

[0074] Next, the policy information acquisition unit 12 causes the generation AI 161 to generate policy information based on the specified viewpoint (S14). The policy information acquisition unit 12 causes the generation AI 161 to output the generated policy information (S15). The policy information acquisition unit 12 also acquires the policy information output from the generation AI 161 (S16). The policy information may include images of advertisements, etc. The output unit 13 outputs advertising methods based on the policy information (S17). For example, the output unit 13 outputs advertising methods and the basis for those advertising methods in association. The output unit 13 may also transmit the policy information to the communication terminal 20, causing the display unit 22 of the communication terminal 20 to display the policy information.

[0075] As explained above, in the information provision system 1 relating to this disclosure, the output device 10 acquires policy information using a generation AI 161 that has been trained to generate policy information, including methods for advertising products. This allows the output device 10 to appropriately output methods for advertising products in the policy. Furthermore, in one aspect of this disclosure, when the generation AI outputs policy information, it is possible to suppress the generation AI from missing important information in the policy or outputting information that is inconsistent with the purpose. In other words, it is possible to reduce the number of times the generation AI is repeatedly prompted and regenerated in order to obtain a document containing policy information that meets the desired quality. Therefore, since it is possible to suppress the repeated processing of redundant information and the same information due to retries, the processing load and resource consumption of the computer running the generation AI can be reduced in the generation of policy information.

[0076] <Example of Hardware Configuration> Each functional component of the output device 100, output device 10, communication terminal 20, and customer information management device 30 (hereinafter referred to as "output device 100, etc.") may be implemented by hardware that realizes each functional component (e.g., hardwired electronic circuits, etc.), or by a combination of hardware and software (e.g., a combination of electronic circuits and programs that control them, etc.). The case in which each functional component of the output device 100, etc. is implemented by a combination of hardware and software will be further explained below.

[0077] Figure 11 is a block diagram illustrating the hardware configuration of a computer 900 that implements the output device 100, etc. The computer 900 may be a dedicated computer designed to implement the output device 100, etc., or it may be a general-purpose computer. The computer 900 may also be a portable computer such as a smartphone or tablet terminal.

[0078] For example, by installing a predetermined application on the computer 900, the computer 900 can realize various functions such as those of the output device 100. The above application consists of a program for realizing the functional components of the output device 100.

[0079] The computer 900 includes a bus 902, a processor 904, a memory 906, a storage device 908, an input / output interface 910, and a network interface 912. The bus 902 is a data transmission path for the processor 904, memory 906, storage device 908, input / output interface 910, and network interface 912 to send and receive data to and from each other. However, the method of connecting the processor 904 and the other components to each other is not limited to bus connection.

[0080] The processor 904 is a variety of processors such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), or quantum processor (quantum computer control chip). The memory 906 is a main memory device implemented using RAM (Random Access Memory), etc. The storage device 908 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc.

[0081] The input / output interface 910 is an interface for connecting the computer 900 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 910.

[0082] The network interface 912 is an interface for connecting the computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0083] The storage device 908 stores programs that implement each functional component, such as the output device 100 (programs that implement the aforementioned applications). The processor 904 reads these programs into the memory 906 and executes them to implement each functional component, such as the output device 100.

[0084] Each processor executes one or more programs containing a set of instructions for causing the computer to perform an algorithm. These programs, when loaded into the computer, contain a set of instructions (or software code) for causing the computer to perform one or more functions described in the embodiments. The programs may be stored in various types of non-transitory computer-readable medium or tangible storage medium. Examples, but not limited to, include non-transitory computer-readable medium or tangible storage medium, such as RAM, ROM, flash memory, SSD or other memory technologies, CD-ROM, DVD (Digital Versatile Disc), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The programs may also be transmitted over various types of transient computer-readable medium or communication medium. Examples, but not limited to, include transient computer-readable medium or communication medium containing electrically, optically, acoustically, or otherwise propagating signals.

[0085] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0086] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments that are not explicitly illustrated or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0087] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A program that causes a computer to execute: a reception step of receiving product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for advertising the product from a user; a policy information acquisition step of inputting the product feature information and the policy objective information to a generating AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method of advertising the product when the product feature information and the policy objective information are input, and acquiring the generated policy information; and an output step of outputting the advertising method based on the policy information. (Note 2) The program according to Note 1, wherein in the policy information acquisition step, the generating AI identifies the basis for the advertising method based on the product feature information and the policy objective information, and in the output step, the advertising method and the basis for the advertising method are output in association. (Note 3) The program according to Note 1 or 2, wherein in the measure information acquisition step, the generating AI identifies a viewpoint to be used in generating the measure information based on the product characteristic information and the measure objective information, and generates the measure information based on the identified viewpoint. (Note 4) The program according to Note 3, wherein in the measure information acquisition step, the generating AI calculates an evaluation value based on the similarity between the content corresponding to the identified viewpoint and the product characteristic information, and generates the measure information based on the calculated evaluation value. (Note 5) The program according to any one of Notes 1 to 4, wherein the product characteristic information includes an image of the product, and in the measure information acquisition step, the generating AI further generates an image of an advertisement to be used in the advertising based on the product characteristic information, the measure objective information, and the measure information, and in the output step, the image of the advertisement is further output.(Note 6) The program according to any one of Notes 1 to 5, wherein in the measure information acquisition step, the generating AI generates at least one of an image of a catchphrase used in advertising and an image of a storyboard based on the product characteristic information, the measure objective information, and the measure information, and in the output step, the generated image is further output. (Note 7) The program according to any one of Notes 1 to 6, wherein in the measure information acquisition step, the generating AI further generates the measure information for each of the multiple measures, and in the output step, the multiple measure information is output in a manner that allows the user to view it. (Note 8) The program according to any one of Notes 1 to 7, wherein in the measure information acquisition step, the generating AI extracts multiple content candidates to be used in the measure based on the product characteristic information and the measure objective information, calculates an evaluation value based on the similarity between each content candidate and the product characteristic information, and selects content to be used in the measure from the multiple content candidates based on the calculated evaluation value. (Note 9) An output device comprising: a reception unit that receives product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition unit that inputs the product feature information and the policy objective information to a generation AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product when the product feature information and the policy objective information are input, and acquires the generated policy information; and an output unit that outputs the promotion method based on the policy information. (Note 10) An output method comprising: a reception step that receives product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition step that inputs the product feature information and the policy objective information to a generation AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product when the product feature information and the policy objective information are input, and acquires the generated policy information; and an output step that outputs the promotion method based on the policy information.

[0088] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 8 that are subordinate to Appendice 1 may also be subordinate to Appendices 9 and 10 in the same manner as those described in Appendices 2 to 8. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means for recording software, systems, and output methods.

[0089] This application claims priority based on Japanese Patent Application No. 2025-078345, filed on 9 May 2025, and incorporates all of its disclosures herein.

[0090] 1 Information Provision System 10 Output Device 11 Reception Unit 12 Policy Information Acquisition Unit 13 Output Unit 15 Communication Unit 16 Storage Unit 161 Generating AI 20 Communication Terminal 21 Input Unit 22 Display Unit 23 Communication Unit 30 Customer Information Management Device 31 Communication Unit 32 Storage Unit 321 Purchase History Information 100 Output Device 101 Reception Unit 102 Policy Information Acquisition Unit 103 Output Unit 900 Computer 902 Bus 904 Processor 906 Memory 908 Storage Device 910 Input / Output Interface 912 Network Interface A Input Screen a1 Name Field a2 Product Features Input Field a3 URL Field a4 Start Analysis Button B Prompt b1-b3 Items C Policy Information c1 Policy Details c2 Image N Network

Claims

1. A program that causes a computer to execute the following steps: a reception step that receives product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition step that inputs the product feature information and the policy objective information into a generating AI (Artificial Intelligence) that has been trained to generate policy information including a method for promoting the product, and acquires the generated policy information; and an output step that outputs the promotion method based on the policy information.

2. The program according to claim 1, wherein in the step of acquiring policy information, the generating AI identifies the basis for the advertising method based on the product characteristic information and the policy objective information, and in the output step, the advertising method and the basis for the advertising method are output in association.

3. The program according to claim 1 or 2, wherein in the step of acquiring policy information, the generating AI identifies a viewpoint to be used in generating the policy information based on the product characteristic information and the policy objective information, and generates the policy information based on the identified viewpoint.

4. The program according to claim 3, wherein in the step of acquiring policy information, the generating AI calculates an evaluation value based on the similarity between the content corresponding to the identified viewpoint and the product feature information, and generates the policy information based on the calculated evaluation value.

5. The program according to claim 1 or 2, wherein the product characteristic information includes an image of the product, the program in the strategy information acquisition step causes the generating AI to further generate an image of an advertisement to be used in the promotion based on the product characteristic information, the strategy objective information, and the strategy information, and the program in the output step further outputs the image.

6. The program according to claim 1 or 2, wherein in the step of acquiring policy information, the generating AI generates at least one of an image of a catchphrase used in advertising and an image of a storyboard based on the product characteristic information, the policy objective information, and the policy information, and in the output step, the generated image is further output.

7. The program according to claim 1 or 2, wherein in the step of acquiring policy information, the generating AI further generates policy information for each of the multiple policies, and in the output step, the program outputs the multiple policy information in a manner that allows the user to view it.

8. The program according to claim 1 or 2, wherein in the step of acquiring policy information, the generating AI extracts multiple content candidates to be used in the policy based on the product characteristic information and the policy objective information, calculates an evaluation value based on the similarity between each content candidate and the product characteristic information, and selects content to be used in the policy from the multiple content candidates based on the calculated evaluation value.

9. An output device comprising: a reception unit that receives product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition unit that inputs the product feature information and the policy objective information to a generating AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product, and acquires the generated policy information; and an output unit that outputs the promotion method based on the policy information.

10. An output method comprising: a reception step of receiving product feature information indicating the characteristics of a product and policy objective information indicating the objective of a policy for promoting the product from a user; a policy information acquisition step of inputting the product feature information and the policy objective information into a generating AI (Artificial Intelligence) that has been trained to generate policy information relating to a policy including a method for promoting the product, and acquiring the generated policy information; and an output step of outputting the promotion method based on the policy information.