Scenario planning device, scenario planning method, scenario planning program

Abstract

Generate content related to the scenario plan. [Solution] The scenario planning device includes a reception unit that receives information to be planned for scenario planning, a scenario plan generation control unit that generates a scenario plan based on the information to be planned for scenario planning and a first generation model, and a scenario content generation control unit that generates scenario content to visualize the scenario plan based on the scenario plan and a second generation model.

Description

Technical Field

[0001] The present invention relates to a scenario planning device, a scenario planning method, and a scenario planning program.

Background Art

[0002] Patent Document 1 describes an apparatus that extracts themes from related information such as news and statistical reports based on a selected field, analysis framework, etc., and generates time-series information in which events for each theme are arranged in chronological order.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Patent Document 1 only generates time-series information, and does not generate content related to related information (scenario plan). One aspect of the present invention has been made in view of the above problems, and an object thereof is to enable generation of content related to a scenario plan.

Means for Solving the Problems

[0005] One aspect of the scenario planning device includes: a reception unit that receives scenario planning target information; a scenario plan generation control unit that causes a scenario plan to be generated based on the scenario planning target information and a first generation model; and a scenario content generation control unit that causes scenario content for visualizing the scenario plan to be generated based on the scenario plan and a second generation model.

[0006] One embodiment of the scenario planning method involves at least one processor receiving information to be planned for scenario planning, generating a scenario plan based on the information to be planned for scenario planning and a first generative model, and generating scenario content that visualizes the scenario plan based on the scenario plan and a second generative model.

[0007] One embodiment of a scenario planning program causes a computer to function as: a reception process for receiving information to be planned for scenario planning; a scenario plan generation control process for generating a scenario plan based on the information to be planned for scenario planning and a first generation model; and a scenario content generation control process for generating scenario content that visualizes the scenario plan based on the scenario plan and a second generation model. [Effects of the Invention]

[0008] According to one aspect of the present invention, content related to a scenario plan can be generated. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of scenario planning related to this disclosure. [Figure 2] This is a block diagram showing the configuration of the scenario planning device related to this disclosure. [Figure 3] This is a flowchart illustrating the flow of the scenario planning method related to this disclosure. [Figure 4] Examples of prompts and outputs related to this disclosure are shown below. [Figure 5] Examples of prompts and outputs related to this disclosure are shown below. [Figure 6] Examples of prompts and outputs related to this disclosure are shown below. [Figure 7] Examples of prompts and outputs related to this disclosure are shown below. [Figure 8] Examples of prompts and outputs related to this disclosure are shown below. [Figure 9]This is a block diagram showing the configuration of the scenario planning device related to this disclosure. [Figure 10] This is a flowchart illustrating the flow of the scenario planning method related to this disclosure. [Figure 11] This is a block diagram showing the configuration of a computer that functions as an information processing 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 techniques (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 techniques 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, a scenario planning device that generates content related to a scenario plan will be described.

[0012] Scenario planning is a method of considering multiple uncertain situations (scenarios) that may occur in the future, and examining effective strategies and measures for each scenario. For example, scenario planning aims to prepare for potential risks and opportunities by considering multiple scenarios based on factors such as technological innovation and changes in market trends.

[0013] Figure 1 is a diagram showing an example of scenario planning. In one example, as shown in Figure 1, scenario planning is performed by combining a scenario plan X10 and scenario content X20.

[0014] The scenario plan X10 is configured such that four scenarios can be assumed by combining a vertical axis (analysis axis X1) representing the market growth rate and a horizontal axis (analysis axis X2) representing the progress of technological innovation. The four scenarios store Analysis Y1 to Analysis Y4 related to assumed future outlooks under the circumstances of each scenario. The analysis is performed, for example, on indices serving as analysis items such as assumed future outlooks and major risks, as well as target organizations and the like. Further, the scenario plan is not limited to the graph form as shown in Figure 1, and may be in the form of text or a table.

[0015] Similar to the scenario plan, the scenario content X20 is configured such that four scenarios can be assumed by combining a vertical axis (analysis axis X1) representing the market growth rate and a horizontal axis (analysis axis X2) representing the progress of technological innovation. The four scenarios store content corresponding to the analysis. For example, content Y1 is content recalled from Analysis Y1, and may be an image, a moving image, or the like.

[0016] (Functional Configuration) Figure 2 is a block diagram showing the configuration of a scenario planning device 100. The scenario planning device 100 includes a reception unit 110, a prompt generation unit 120, a scenario plan generation control unit 130, and a scenario content generation control unit 140.

[0017] The reception unit 110 receives scenario planning target information. The reception unit 110 may receive the scenario planning target information from a storage device. Alternatively, the reception unit 110 may receive scenario planning target information input via a device used by a user.

[0018] The information subject to scenario planning includes at least one of the following: basic information (organization, analysis items, etc.), analysis axes, or other peripheral information (market trends, financial indicators, etc.).

[0019] Basic information refers to fundamental data about the organization or company that is the subject of scenario planning. For example, basic information includes the company profile, the target region, and the target product.

[0020] The analytical axes are the criteria used to evaluate a scenario. For example, analytical axes may include the progress of technological innovation, market growth rate, changes in regulations and laws, competitive landscape, macroeconomic factors, changes in consumer needs and values, geopolitical risks, environmental and climate factors, socio-cultural factors, and supply chain stability.

[0021] Peripheral information is information related to the subject of scenario planning. For example, it includes organizational structure (departmental structure, job titles, organizational chart), financial statements (income statement, balance sheet, cash flow statement), past performance (sales, profit, growth rate), budget (budget plan, comparison with actual results), market share (share within the industry, position relative to competitors), target customers (customer segments, customer needs), customer satisfaction surveys (customer feedback, NPS), product portfolio (lineup of main products and services), new product plans (progress of product development, plans for new services), product lifecycle (stages of each product), number of employees (total number, number of employees per department), skill map (specialized skills and qualifications of each employee), talent development programs (training, education system), technological infrastructure (currently used technologies and systems), research and development status (R&D projects, progress of technology development), intellectual property (patents, trademarks), etc.).

[0022] The prompt generation unit 120 generates prompts based on the scenario plan target information received by the reception unit 110. Specifically, for example, the prompt generation unit 120 generates prompts by incorporating the scenario plan target information into a predetermined template. A prompt is an instruction statement to be input to the generation model described later. For example, a prompt is a natural language sentence containing the scenario plan target information. The prompt generation unit 120 outputs a prompt based on the scenario plan target information to the scenario plan generation control unit 130.

[0023] The scenario plan generation control unit 130 receives the prompt (first prompt) generated by the prompt generation unit 120 as input and generates a scenario plan using a machine learning model (first generative model). The machine learning model (first generative model) is any machine learning model, and may be, for example, a large-scale language model, a time series forecasting model, a multimodal model, etc. 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 a document. 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 first generative model may be a fine-tuned general-purpose generative model that accurately generates the information necessary to generate a scenario plan. For fine-tuning, the training data can consist of pairs of prompts and the responses that should be generated for those prompts.

[0024] Furthermore, the scenario plan generation control unit 130 may be connected to an external database 132. The first generation model may generate scenario planning information by referencing media content from the external database 132, such as newspaper articles, economic and financial data, industry reports, academic papers, social media data, government announcements, patent information, and market research reports. Search augmentation generation techniques such as RAG (Retrieval Augmented Generation) may be used to reference the database. This makes it possible to reflect media content not included in the generation model's training data, as well as detailed information on specific domains, in the response.

[0025] The first generation model described above may be stored in the scenario planning device 100 or in another device. In the latter case, the scenario plan 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.

[0026] The scenario content generation control unit 140 generates scenario content that visualizes the scenario based on the generated scenario plan. For example, the scenario content consists of images, videos, or a combination thereof. The scenario content generation control unit 140 may also input the scenario plan into a machine learning model (second generative model) to generate the scenario content. The machine learning model may be a generative adversarial network (GAN), variational autoencoder (VAE), diffusion model, or transformer model, which has been trained to generate images. The scenario content generation control unit 140 may also input prompts into the second generative model to generate the scenario content. In this case, the prompt generation unit 120 generates prompts (second prompts) based on the scenario plan generated by the scenario plan generation control unit 130 and outputs them to the scenario content generation control unit 140.

[0027] The second generation model described above may be stored in the scenario planning device 100 or in another device. In the latter case, the scenario plan 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.

[0028] As described above, the scenario planning device 100 according to the first embodiment employs a configuration comprising: a reception unit 110 that receives scenario planning target information; a prompt generation unit 120 that generates prompts based on the scenario planning target information; a scenario plan generation control unit 130 that inputs the prompts into a first generation model that refers to a database containing at least media content data to generate a scenario plan; and a scenario content generation control unit 140 that inputs the scenario planning information into a second generation model to generate scenario content.

[0029] The above configuration has the effect of being able to generate content related to scenario plans.

[0030] (Scenario Planning Program) The functions of the scenario planning device 100 described above can also be implemented by a program. The scenario planning program according to the first embodiment causes a computer to function as follows: receiving means for receiving information to be planned for scenario planning; prompt generation means for generating prompts based on the information to be planned for scenario planning; scenario plan generation control means for inputting the prompts into a first generation model that refers to a database containing at least media content data to generate a scenario plan; and scenario content generation control means for inputting the scenario planning information into a second generation model to generate scenario content. This scenario planning program has the effect of being able to generate content related to the scenario plan.

[0031] (Scenario planning process) The flow of the scenario planning method according to the first embodiment will be explained with reference to Figure 3. Figure 3 is a flowchart showing the flow of the scenario planning method.

[0032] In S1 (reception processing), at least one processor receives the information to be used for scenario planning.

[0033] In S2 (prompt generation process), at least one processor generates a prompt based on the scenario planning target information received in S1.

[0034] In S3 (Scenario Plan Generation Control Process), at least one processor inputs the prompt generated in S2 into the first generation model to generate a response.

[0035] In S4 (Scenario Content Generation Control Processing), at least one processor inputs the scenario planning information generated in S3 into a second generation model to generate scenario content.

[0036] As described above, the scenario planning method according to the first embodiment employs a configuration that includes: a reception process for receiving information to be planned for scenario planning; a prompt generation process for generating prompts based on the information to be planned for scenario planning; a scenario plan generation control process for inputting the prompts into a first generation model that refers to a database containing at least media content data to generate a scenario plan; and a scenario content generation control process for inputting the scenario planning information into a second generation model to generate scenario content. Therefore, the above configuration provides the effect of being able to generate content related to the scenario plan.

[0037] The execution entities for each process described in the first embodiment above are arbitrary and are not limited to the examples given. For example, a system having the same functions as the scenario planning device 100 can be constructed using multiple devices that can communicate with each other. Also, the execution entities for each process shown in the flowchart in Figure 3 may be a single device (which can also be called a processor) or multiple devices (which can also be called processors).

[0038] (Specific examples of scenario plan generation) Here, using Figure 4, we will explain an example of a prompt, which is the input to the first model used by the scenario plan generation control unit 130, and a scenario plan, which is the output of the first model. Figure 4 is a diagram illustrating the prompt 11, which is the input to the first model used by the scenario plan generation control unit 130, and the output 21, which is the output of the first generated model.

[0039] As shown in Figure 4, the prompt 11 consists of the following sections: "Instructions," "Analysis Axes," "Scenario," and "Analysis Target." The "Instructions" section contains instructions written in natural language for generating a scenario plan. The "Analysis Axes" section describes the analysis axes included in the scenario planning target information received by the reception unit 110. In the example shown in Figure 4, "Temperature increase range (1.5°C, 4°C)" and "Lifestyle change pattern (voluntary, forced)" are described. The "Scenario" section describes the scenario conditions that combine the analysis axes included in the scenario planning target information. In the example shown in Figure 4, "1.5°C x voluntary, 1.5°C x forced, 4°C x voluntary, 4°C x forced" are described. The "Analysis Target" section describes the indicators to be analyzed included in the scenario planning target information. In the example shown in Figure 4, "Risk" is described. The output 21 shown in Figure 4 is a scenario plan that shows the results of the risk analysis for each scenario described in the prompt 11.

[0040] (Specific examples of scenario content generation) Next, using Figure 5, we will explain examples of prompts, which are inputs to the second model used by the scenario content generation control unit 140, and scenario content, which is the output of the second model. Figure 5 is a diagram illustrating prompt 12, which is an input to the second model used by the scenario content generation control unit 140, and output 22, which is the output of the second generation model.

[0041] As shown in Figure 5, prompt 12 consists of the sections of prompt 11 described using Figure 4, plus a section indicating the content of output 21. The "Instructions" section contains instructions in natural language for generating scenario content. In the example shown in Figure 5, the instructions in natural language are for generating scenario content that divides an illustration explaining the scenario plan (output 21) generated by the scenario plan generation control unit 130 into four quadrants. The "Analysis Axis," "Scenario," and "Analysis Target" are the same as the content of prompt 11 shown in Figure 4. Also, output 22 shown in Figure 5 is the scenario content generated according to the instructions of prompt 12.

[0042] (Variation 1) In the first embodiment, the scenario plan generation control unit 130 generates a scenario plan using one prompt generated by the prompt generation unit 120, but the configuration is not limited to this. Hereinafter, as a modified example, an embodiment in which the scenario plan generation control unit 130 generates a final scenario plan from prompts including a scenario plan generated using multiple prompts will be described with reference to Figures 6, 7, and 8.

[0043] Figures 6 and 7 illustrate prompts 13 and 14, each with a single "analysis axis," and the outputs 23 and 24 of the first generative model using each prompt. The "analysis axis" for prompt 13 in Figure 6 is "temperature rise," and the "analysis axis" for prompt 14 in Figure 7 is "pattern of lifestyle changes during temperature rise."

[0044] Figure 8 illustrates prompt 15, which includes outputs 23 and 24 shown in Figures 6 and 7, and output 25 of the first generation model using prompt 15. The "analysis axes" of prompt 15 shown in Figure 8 are "temperature rise range" and "pattern of lifestyle changes during temperature rise," which are the "analysis axes" of prompt 13 in Figure 6 and prompt 14 in Figure 7, respectively. The "reference information" of prompt 15 describes the contents of output 23 in Figure 6 and output 24 in Figure 7. In other words, the prompt generation unit 120 generates each prompt shown in Figures 6 and 7, and further generates the prompt shown in Figure 8, which includes the output generated by the first generation model using each prompt. The scenario plan generation control unit 130 uses the prompt shown in Figure 8, generated by the prompt generation unit 120, to generate a scenario plan that will ultimately be output to the scenario content generation control unit 140.

[0045] As explained above, in this modified example 1, the scenario plan is created step by step using multiple prompts, which has the effect of generating a more accurate scenario plan compared to the case where the scenario plan is created using a single prompt. The prompt generation unit 120 may similarly generate prompts to output to the scenario content generation control unit 140. Furthermore, this modified example is also applicable to Embodiment 2, which will be described later.

[0046] <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 first embodiment 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 each drawing 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.

[0047] (Configuration of Scenario Planning Device 100A) The configuration of the scenario planning device 100A according to the second embodiment will be described with reference to Figure 9. Figure 9 is a block diagram showing the configuration of the scenario planning device 100A. The scenario planning device 100A is a device equipped with a scenario planning function that generates scenario plans. The scenario planning device 100A may be a local device used by individual users, or it may be a server that provides scenario planning services to multiple users.

[0048] As shown in Figure 9, the scenario planning device 100A includes a control unit 10A that controls all parts of the scenario planning device 100A, and a storage unit 11A that stores various data used by the scenario planning device 100A. The scenario planning device 100A also includes a communication unit 12A for the scenario planning device 100A to communicate with other devices, an input unit 13A that receives input to the information processing device 1A, and an output unit 14A for the scenario planning device 100A to output data. The control unit 10A includes a reception unit 110A, a prompt generation unit 120A, a scenario plan generation control unit 130A, a scenario content generation control unit 140A, a verification unit 150A, and a presentation control unit 160A.

[0049] The reception unit 110A, prompt generation unit 120A, scenario plan generation control unit 130A, and scenario content generation control unit 140A have the same configuration as the reception unit 110, prompt generation unit 120, scenario plan generation control unit 130, and scenario content generation control unit 140 of Embodiment 1, respectively, and their description is omitted.

[0050] The verification unit 150A verifies whether the content of the scenario plan generated by the scenario plan generation control unit 130A meets predetermined criteria and outputs the verification result to the presentation control unit 160A. Specifically, for example, the verification unit 150A verifies whether the content of the scenario plan meets predetermined criteria and rules set in advance. The pre-set rules indicate, for example, whether the scenario plan contains a list of predetermined keywords (such as discriminatory expressions, potentially misleading words, legally problematic expressions, etc.).

[0051] Furthermore, for example, the verification unit 150A may use a machine learning model to verify whether the content of the scenario plan meets predetermined criteria. The machine learning model may be a model that has been trained to take the content of the scenario plan as input and output a judgment result on whether or not it meets predetermined criteria. The machine learning model may be any LLM, and the LLM may refer to an external database containing media content, laws, and regulations whose accuracy is guaranteed. The verification unit 150A may verify whether or not the content of the scenario plan is appropriate by comparing the media content stored in the external database with the scenario plan, calculating an index indicating whether the scenario plan is based on the media content, and determining whether or not the calculated index meets predetermined criteria. The verification unit 150A may extract some of the external data referenced in the judgment. The rules, keyword list, and machine learning model used by the verification unit 150A may be stored in the scenario planning device 100A or in another device.

[0052] The presentation control unit 160A controls the presentation of the scenario plan generated by the scenario plan generation control unit 130A based on the verification results input from the verification unit 150A. "Presentation" means making the content of the presentation recognizable to the user (for example, the person who specified the analysis target). Specifically, for example, if the verification results indicate that the scenario plan meets predetermined criteria, the presentation control unit 160A displays the scenario plan on the display device. This allows the user to recognize the scenario plan displayed on the display device. Alternatively, for example, the presentation control unit 160A may control the uploading of the scenario plan to a server accessible to the user. This allows the user to access the server and recognize the scenario plan uploaded by the presentation control unit 160A.

[0053] Furthermore, the presentation control unit 160A may control the presentation of the scenario content generated by the scenario content generation control unit 140A if the verification result indicates that the scenario plan meets predetermined criteria. The presentation method of the scenario content is the same as the presentation method of the scenario plan. Also, when the verification unit 150A verifies the content of the scenario content, the presentation control unit 160A may control the presentation of the scenario content based on the verification result input from the verification unit 150A.

[0054] As described above, the scenario planning device 100A according to the second embodiment employs a configuration comprising: a reception unit 110A that receives scenario planning target information; a prompt generation unit 120A that generates prompts based on the scenario planning target information; a scenario plan generation control unit 130A that inputs the prompts into a first generation model that refers to a database containing at least media content data to generate a scenario plan; and a scenario content generation control unit 140A that inputs the scenario planning information into a second generation model to generate scenario content. Therefore, similar to the scenario planning device 100A, the effect of being able to generate content related to the scenario plan can be obtained.

[0055] Furthermore, the scenario planning device 100A includes a verification unit 150A that verifies whether the content of the scenario plan generated by the scenario plan generation control unit 130A is appropriate. It also includes a presentation control unit 160A that presents one or more of the scenario plans verified by the verification unit 150A to meet predetermined criteria, and the scenario content generated based on the scenario plan. This provides, in addition to the effects of the scenario planning device 100 described in the first embodiment, the effect of being able to present only scenario plans and scenario content that meet predetermined criteria.

[0056] (Process flow) The flow of the scenario planning method according to the second embodiment will be explained with reference to Figure 10. Figure 10 is a flowchart showing the flow of the scenario planning method. Note that the entity executing each step in this scenario planning method may be a processor provided in the scenario planning device 100A, a processor provided in another device, or the entity executing each step may be a processor provided in a different device.

[0057] In S11 (reception processing), at least one processor receives the information to be used for scenario planning.

[0058] In S12 (prompt generation process), at least one processor generates a prompt based on the scenario planning target information received in S11.

[0059] In S13 (scenario plan generation control processing), at least one processor inputs the prompt generated in S12 into a first generation model that references a database containing at least media content data, causing it to generate a response.

[0060] In S14 (Scenario Content Generation Control Processing), at least one processor inputs the scenario planning information generated in S13 into a second generation model to generate scenario content.

[0061] In S15 (verification process), at least one processor verifies whether the contents of the scenario plan generated in S14 meet predetermined conditions.

[0062] In S16 (presentation control processing), at least one processor controls the presentation of the scenario plan generated in S13 based on the verification results of S15.

[0063] As described above, the scenario planning method according to the second embodiment employs a configuration that includes: an acceptance process for receiving information to be planned for scenario planning; a prompt generation process for generating prompts based on the information to be planned for scenario planning; a scenario plan generation control process for inputting the prompts into a first generation model that refers to a database containing at least media content data to generate a scenario plan; a scenario content generation control process for inputting the scenario planning information into a second generation model to generate scenario content; a verification process for verifying whether the content of the scenario plan satisfies predetermined conditions; and a presentation control process for controlling the presentation of the scenario plan generated by the scenario plan generation control process based on the verification results of the verification process. This provides an additional benefit compared to the first embodiment, by reducing the possibility of presenting scenario plans and scenario content that are inaccurate.

[0064] The execution entities for each process described in the second embodiment above are arbitrary and are not limited to the examples given. For example, a system having the same functions as the scenario planning device 100A can be constructed using multiple devices that can communicate with each other. Also, the execution entities for each process shown in the flowchart in Figure 10 may be a single device (which can also be called a processor) or multiple devices (which can also be called processors).

[0065] (Modified version of Embodiment 2) The following describes embodiments of each component that reflect user feedback (e.g., requests for modifications or additional information) to the scenario plan and scenario content presented by the presentation control unit 160A, 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 trained on natural language to generate prompts that reflect the requests for modifications or additional information indicated by the feedback input from the reception unit 110A. For example, the prompt generation unit 120A generates prompts that modify the content of the "scenario conditions" section or add "analysis axes".

[0066] The scenario plan generation control unit 130A generates a scenario plan that reflects the feedback using the prompts newly generated by the prompt generation unit 120A. The scenario content generation control unit 140A generates scenario content that reflects the feedback using the scenario plan newly generated by the scenario plan generation control unit 130A. The prompt generation unit 120A may generate prompts based on the scenario plan that reflects the feedback and output them to the scenario content generation control unit 140A, as described in the first embodiment.

[0067] Furthermore, if the feedback is directed only at the scenario content (for example, "Keep the scenario plan the same, but make the content simpler"), the prompt generation unit 120A will generate a prompt that modifies the content of the "instruction." In this case, the prompt generation unit 120A will output the generated prompt to the scenario content generation control unit 140A. As a result, only the scenario content will be modified to reflect the feedback.

[0068] This feedback function enables interactive use of the system by the user, allowing for deeper insights. Furthermore, it continuously improves the output accuracy of the scenario planning device, resulting in the creation of scenario plans that are better suited to the user's needs.

[0069] (Example of implementation using software) Some or all of the functions of the scenario planning devices 100 and 100A (hereinafter also referred to as "the above devices") may be implemented by hardware such as integrated circuits (IC chips) or by software.

[0070] (Hardware configuration) In the latter case, each of the above devices is implemented by a computer C that executes instructions for a program, which is software that implements each function. Figure 11 is a block diagram showing the hardware configuration of the scenario planning device 100. As shown in the figure, the scenario planning device 100 includes a processor 1, an input / output interface 2, a ROM (Read Only Memory) 3, a RAM (Random Access Memory) 4, and a storage device 5. Each component is connected to the others, for example, via a bus 6.

[0071] Processor 1 is a computing device such as a CPU (Central Processing Unit) that controls the entire scenario planning device 100 by executing a pre-prepared program. Specifically, as processor 1, 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.

[0072] Furthermore, processor 1 loads programs stored in ROM 3, storage device 5, etc. Then processor 1 executes each process coded in the program. Also, processor 1 functions as part or all of the scenario planning device 100. Then processor 1 may execute processes or instructions in the flowchart based on the program.

[0073] Input / Output Interface 2 is an interface for connecting input / output devices such as keyboards, mice, displays, and printers.

[0074] ROM3 stores various programs executed by processor 1. RAM4 is used as working memory while processor 1 is executing various processes.

[0075] The storage device 5 is a non-volatile, non-temporary storage device. For example, the storage device 5 may be a disk-shaped recording medium, a semiconductor memory, or the like. The storage device 5 may be configured to be detachable from the scenario planning device 100. The storage device 5 stores various programs executed by the processor 1. It may also store machine learning models, training data, and the like.

[0076] Furthermore, each function of the above-mentioned device 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 program for implementing each of the above-mentioned functions in each of the above-mentioned 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.

[0077] Some or all of the above embodiments may also be described as follows, but are not limited to the following:

[0078] (Note 1) The reception desk accepts information for scenario planning, A scenario plan generation control unit generates a scenario plan based on the aforementioned scenario planning target information and the first generation model, A scenario content generation control unit generates scenario content that visualizes the scenario plan based on the aforementioned scenario plan and a second generation model, A scenario planning device equipped with the following features.

[0079] (Note 2) Prompt generation unit that generates prompts to be input to the first generation model. A scenario planning device as described in Appendix 1, having the following features.

[0080] (Note 3) The prompt generation unit, Based on the aforementioned scenario planning target information, a first prompt is generated to be input to the first generation model. The scenario plan generation control unit, The first prompt is input to the first generative model to generate a scenario plan. The scenario planning device described in Appendix 2.

[0081] (Note 4) The prompt generation unit, Based on the aforementioned scenario plan, a second prompt is further generated to be input to the second generative model. The scenario content generation control unit, The second prompt is input to the second generative model to generate a scenario plan. A scenario planning device as described in Appendix 2 or 3.

[0082] (Note 5) The generative model in the previous first generation is Refer to a database that contains at least data on media content. The scenario planning device described in Appendix 1.

[0083] (Note 6) The generative model in the previous first generation is It is a generative model trained with machine learning to output a scenario plan for an input prompt. The second generative model described above is: This is a machine learning-trained generative model that outputs scenario content for an input scenario plan. The scenario planning device described in Appendix 1.

[0084] (Note 7) A verification unit that verifies whether the contents of the aforementioned scenario plan meet predetermined criteria, If the verification unit verifies that the scenario plan meets predetermined criteria, the presentation control unit presents the scenario plan. A scenario planning device as described in Appendix 6, comprising the above.

[0085] (Note 8) The system includes a prompt generation unit that generates prompts to be input to the first generation model, The reception unit receives feedback on the scenario plan presented by the presentation control unit. The prompt generation unit generates a new prompt that includes a correction instruction based on the feedback. The scenario planning device described in Appendix 7.

[0086] (Note 9) At least one processor, We accept information for scenario planning. Based on the aforementioned scenario planning target information and the first generation model, a scenario plan is generated. A scenario planning method that generates scenario content to visualize the scenario plan based on the aforementioned scenario plan and a second generation model.

[0087] (Note 10) Computers, A means of receiving information for scenario planning, A scenario plan generation control means for generating a scenario plan based on the aforementioned scenario planning target information and the first generation model, and A scenario planning program that functions as a scenario content generation control means for generating scenario content that visualizes the scenario plan, based on the aforementioned scenario plan and a second generation model.

[0088] Furthermore, some or all of the configurations described in Appendices 2 to 8, which are dependent on Appendice 1 above, may also be dependent on Appendices 9 and 10, respectively, through the same dependency relationships as those described in Appendices 2 to 8. Moreover, not limited to Appendices 1, 9, and 10, 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]

[0089] 100, 100A Scenario Planning Device 110 Reception area (reception method) 120 Prompt generation unit (prompt generation means) 130 Scenario plan generation control unit (scenario plan generation control means) 140 Scenario Content Generation Control Unit (Scenario Content Generation Control Means) 110A Reception area (reception method) 120A Prompt generation unit (prompt generation means) 130A Scenario Plan Generation Control Unit (Scenario Plan Generation Control Means) 140A Scenario Content Generation Control Unit (Scenario Content Generation Control Means) 150A Verification Unit (Verification Means) 160A Presentation Control Unit (Presentation Control Means)

Claims

1. The reception desk accepts information for scenario planning, A scenario plan generation control unit generates a scenario plan based on the aforementioned scenario planning target information and the first generation model, A scenario content generation control unit generates scenario content that visualizes the scenario plan based on the aforementioned scenario plan and a second generation model, A scenario planning device equipped with the following features.

2. Prompt generation unit that generates prompts to be input to the first generation model A scenario planning device according to claim 1, having the following features.

3. The prompt generation unit, Based on the scenario planning target information, a first prompt is generated to be input to the first generation model. The scenario plan generation control unit, The first prompt is input to the first generative model to generate a scenario plan. The scenario planning device according to claim 2.

4. The prompt generation unit, Based on the aforementioned scenario plan, a second prompt is further generated to be input to the second generative model. The scenario content generation control unit, The second prompt is input to the second generative model to generate a scenario plan. The scenario planning device according to claim 2 or 3.

5. The first generative model described above is Refer to a database that contains at least data on media content. The scenario planning device according to claim 1.

6. The first generative model described above is It is a generative model trained with machine learning to output a scenario plan for an input prompt. The second generation model described above is This is a machine learning-trained generative model that outputs scenario content for an input scenario plan. The scenario planning device according to claim 1.

7. A verification unit that verifies whether the contents of the aforementioned scenario plan meet predetermined criteria, If the verification unit verifies that the scenario plan meets predetermined criteria, the presentation control unit presents the scenario plan. The scenario planning device according to claim 6, comprising:

8. The system includes a prompt generation unit that generates prompts to be input to the first generation model, The reception unit receives feedback on the scenario plan presented by the presentation control unit. The prompt generation unit generates a prompt based on the feedback. The scenario planning device according to claim 7.

9. At least one processor, We accept information for scenario planning. Based on the aforementioned scenario planning target information and the first generation model, a scenario plan is generated. A scenario planning method that generates scenario content to visualize the scenario plan based on the aforementioned scenario plan and a second generation model.

10. Computers, A means of receiving information for scenario planning, A scenario plan generation control means for generating a scenario plan based on the aforementioned scenario planning target information and the first generation model, and A scenario planning program that functions as a scenario content generation control means for generating scenario content that visualizes the scenario plan, based on the aforementioned scenario plan and a second generation model.

Images