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

Abstract

To easily obtain information about businesses that have government agencies as clients. [Solution] The information providing server 20 has a creation unit 232, an input unit 233, and a provision unit 234. The creation unit 232 creates a prompt that predicts the content of measures corresponding to the government's future budget based on information related to past budgets. The input unit 233 inputs the prompt created by the creation unit 232 into a generative model. The provision unit 234 provides information based on the answer obtained by inputting the prompt created by the creation unit 232 into the generative model.

Description

[Technical Field]

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

[0002] Private businesses may undertake projects with the national government, local governments, etc. as clients. In such cases, in order to plan effective projects, it is desirable to understand information such as the content of policies implemented by the national government and local governments, etc. in the field targeted by the project, as well as budget allocations.

[0003] BACKGROUND ART Conventionally, there is known a technique for predicting the impact of measures implemented by the national government, local governments, etc., based on user surveys (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2022-113369 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional technologies have a problem in that it is not easy to obtain information about businesses that have the government as a client. For example, the technology described in Patent Document 1 requires users to conduct a survey, which requires a lot of time and manpower costs. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objectives, the information provision device is characterized by having a creation unit that creates a prompt by replacing variables in a template, which is text that contains instructions for planning a project related to a budget item indicated by the variables, and a provision unit that provides information based on the answer obtained by inputting the prompt created by the creation unit into a generation model. [Effects of the Invention]

[0007] According to the present invention, information on businesses that have government agencies as clients can be easily obtained. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing the configuration and processing flow of an information providing system. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a terminal. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information providing server. [Figure 4] FIG. 4 is a diagram illustrating an example of a budget table. [Figure 5] FIG. 5 shows examples of prompts and answers created by a person or an information providing system. [Figure 6] FIG. 6 shows examples of prompts and answers created by a person or an information providing system. [Figure 7] FIG. 7 shows examples of prompts and answers created by a person or an information providing system. [Figure 8] FIG. 8 shows examples of prompts and answers created by a person or an information providing system. [Figure 9] FIG. 9 is a diagram showing an example of a diagram of a proposed initial hypothesis. [Figure 10] FIG. 10 shows examples of prompts and answers created by a person or an information providing system. [Figure 11] FIG. 11 shows examples of prompts and answers created by a person or an information providing system. [Figure 12] FIG. 12 is a diagram showing an example of a document showing the contents of a proposal. [Figure 13] FIG. 13 is a flowchart showing the flow of processing by the information processing server. [Figure 14] FIG. 14 is a flowchart showing the flow of the budget evaluation process. [Figure 15] FIG. 15 is a flowchart showing the flow of the process for generating a proposed initial hypothesis. [Figure 16] FIG. 16 is a flowchart showing the flow of the process for generating detailed proposal content. [Figure 17] FIG. 17 is a flowchart showing the flow of processing for creating materials. [Figure 18] FIG. 18 is a flowchart showing the flow of processing for predicting future budget data. [Figure 19] FIG. 19 is a diagram illustrating an example of the configuration of a computer that executes an information provision program. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An information providing apparatus, an information providing method, and an information providing program according to the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention is not limited to the following embodiments.

[0010] [First embodiment] First, the overall configuration of an information providing system including an information providing server will be described with reference to Fig. 1. Fig. 1 is a diagram showing the configuration and processing flow of the information providing system.

[0011] 1, the information providing system 1 includes a terminal 10, an information providing server 20, and a generation server 30. The terminal 10 is a PC, a smartphone, etc. The information providing server 20 and the generation server 30 are virtual or physical servers.

[0012] The information providing server 20 is connected to the terminal 10 and the generation server 30 via a network such as the Internet. Also, the information providing server 20 and the generation server 30 may be virtual servers constructed in a cloud service. Note that the information providing server 20 is an example of an information processing device.

[0013] The generation server 30 is a server that provides services using a large language model (LLM: Large Language Models). The generation server 30 receives a prompt and provides an answer generated using the LLM according to the prompt. The LLM is a so-called generation model, such as ChatGPT (registered trademark) and tsuzumi. The service provided by the generation server 30 may be called a chatbot.

[0014] The information providing server 20 creates a prompt and sends the created prompt to the generation server 30. Then, the information providing server 20 receives an answer to the sent prompt from the generation server 30. The information providing server 20 provides data to the user via the terminal 10 based on the provided answer.

[0015] Note that the generation server 30 outputs an answer using a generation model. Therefore, the target to which the information providing server 20 inputs the prompt and the entity that provides the answer to the information providing server 20 may be rephrased as the generation model instead of the generation server 30.

[0016] In the present embodiment, the information providing server 20 provides information related to government-related projects. For example, the information providing server 20 can provide data indicating plans for government-related projects.

[0017] The government in the present embodiment is the administrative organs of the state and local governments. Here, the government may refer to the entire administrative organs of the state with the Cabinet at the apex, or may refer to individual ministries and agencies.

[0018] Users can obtain information on government-related businesses by using the information providing server 20. The users are businesses (or related parties) that conduct government-related businesses. The users may be businesses in any industry, such as the information and communications industry, construction industry, or finance industry.

[0019] For example, the user can propose to the government a business plan obtained from the information providing server 20. In this way, the information providing server 20 can support the sales activities of the user.

[0020] An example of the processing flow of the information providing system 1 will be described with reference to Fig. 1. The processing flow shown in Fig. 1 is one example. First, as shown in Fig. 1, the terminal 10 requests the government to draft a project related to the project in response to a user operation (step S1).

[0021] Upon receiving the request, the information providing server 20 evaluates each budget included in the budget data (step S2). The budget data is data that indicates the content and budget amount of each government policy. Information that combines the content and budget amount of a policy is called a budget.

[0022] Next, the information providing server 20 creates a prompt for planning a project related to a budget for which the evaluation results satisfy the conditions (step S3).The information providing server 20 then inputs the generated prompt to the generation server 30 (step S4).The input is performed by transmitting the prompt and necessary data to the generation server 30 by means of an API (Application Programming Interface) or the like.

[0023] The generation server 30 generates an answer based on the prompt (step S5). The generation server 30 can generate an answer by inputting the prompt into the LLM. The generation server 30 outputs the generated answer to the information providing server 20 (step S6). The answer may be text, or may be data including diagrams and images. Note that the processes from steps S3 to S6 may be repeated.

[0024] The information providing server 20 constructs data related to the business to be planned based on the answers (step S7). Construction involves creating data in a predetermined format based on the answers. For example, the information providing server 20 creates slides for a presentation related to the business based on the answers.

[0025] The information providing server 20 provides the constructed data to the terminal 10 (step S8), which allows the user to view the business plan generated by the LLM.

[0026] The configuration of the terminal 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the terminal. As shown in Fig. 2, the terminal 10 has a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0027] The communication unit 11 communicates with other devices and is, for example, a network interface card (NIC).

[0028] The input unit 12 is an interface connected to input devices such as a keyboard and a mouse. The output unit 13 is an interface connected to output devices such as a display and a speaker. The input unit 12 and the output unit 13 may be touch panel displays.

[0029] The storage unit 14 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 14 may also be a data-rewritable semiconductor memory such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM).

[0030] The storage unit 14 stores an OS (Operating System) and various programs executed on the terminal 10.

[0031] The control unit 15 controls the entire terminal 10. The control unit 15 is, for example, an electronic circuit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0032] The control unit 15 also has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory. The control unit 15 also functions as various processing units by running various programs.

[0033] For example, the control unit 15 includes an output control unit 151 and a communication control unit 152.

[0034] The output control unit 151 controls the output unit 13 to output data. For example, the output control unit 151 causes the output unit 13 to display a screen on a display.

[0035] The communication control unit 152 performs communication by controlling the communication unit 11. For example, the communication control unit 152 transmits and receives data to and from the information providing server 20.

[0036] The terminal 10 can request the information providing server 20 to perform processing and display data received from the information providing server 20 via a web browser or a dedicated application.

[0037] The configuration of the information providing server 20 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information providing server. As shown in Fig. 3, the information providing server 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0038] The communication unit 21 communicates with other devices and is, for example, a NIC.

[0039] The storage unit 22 is a storage device such as an HDD, an SSD, an optical disk, etc. The storage unit 22 may also be a data-rewritable semiconductor memory such as a RAM, a flash memory, or an NVSRAM.

[0040] The storage unit 22 stores an OS and various programs executed by the information providing server 20. The storage unit 22 stores a budget table 221, a prompt master 222, and a document template DB 223.

[0041] The budget table 221 is a table in which budget data is stored. FIG. 4 is a diagram showing an example of a budget table. The budget data may be created in advance based on data issued by the government. Data called "Summary of Budget Requests" published by each ministry and agency in Japan (for example, "Summary of Budget Requests under the Jurisdiction of the Ministry of Internal Affairs and Communications" published by the Ministry of Internal Affairs and Communications) is an example of data issued by the government.

[0042] 4, the budget table 221 has the following columns: "No.", "Ministry / agency," "Budget item," "Budget amount," and "Details of measures." The "Budget item" includes "Major item," "Medium item," and "Minor item." Each record in the budget table 221 corresponds to a budget.

[0043] "No." is a number that identifies the budget. "Ministry" is the ministry that corresponds to the budget. "Budget item" is an item for classifying budgets. "Budget amount" is the budget amount (unit: 100 million yen) for the current fiscal year requested by the ministry. The number in parentheses next to "Budget amount" is the budget amount for the previous fiscal year. "Content of measures" is a detailed explanation of the contents of the measures.

[0044] For example, the budget table 221 indicates that the organization listed in the "Ministry" column is requesting the amount listed in the "Budget Amount" column to implement the policy listed in the "Policy Content" column.

[0045] For example, Figure 4 shows that the budget for "No." "13" is requested by the Ministry of Internal Affairs and Communications, and its "major item" is "1. Establishment of local administrative and financial foundations to realize vibrant and diverse local communities, promotion of regional digital transformation and regional revitalization," its "medium item" is "4. Enhancement of human resources active in the region and regional revitalization," and its "minor item" is "(4) Promotion of depopulation countermeasures." It also shows that the budget amount for "13" is "8.3 (8.0)" billion yen, and the content of the measure is "(a) Support for efforts toward the sustainable development of depopulated regions 4.3 (4.0)..."

[0046] The prompt master 222 is a template for creating a prompt (hereinafter referred to as a prompt template). For example, the prompt template is text that includes variables. In this case, a prompt is created by substituting the variables in the prompt template.

[0047] For example, in the prompt template "Please plan a project related to {subitem} of {Ministry}," "{Subitem}" are variables. By replacing the variables in this prompt template, the prompt "Please plan a project related to (4) the promotion of depopulation measures of the Ministry of Internal Affairs and Communications" is created.

[0048] The document template DB 223 contains templates for creating materials (hereinafter referred to as document templates). For example, a document template is a diagram in which blank text boxes are arranged. In this case, a material is created by filling in the text boxes of the document template with text.

[0049] 3, the control unit 23 controls the entire information providing server 20. The control unit 23 is, for example, an electronic circuit such as a CPU, an MPU, or a GPU, or an integrated circuit such as an ASIC or an FPGA.

[0050] The control unit 23 also has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory. The control unit 23 also functions as various processing units by running various programs.

[0051] For example, the control unit 23 includes an evaluation unit 231 , a creation unit 232 , an input unit 233 , and a provision unit 234 .

[0052] The evaluation unit 231 evaluates the budget. Information about the budget for which the evaluation result by the evaluation unit 231 satisfies the conditions is provided via the terminal 10.

[0053] The creation unit 232 creates a prompt for obtaining information about a budget for which the evaluation result by the evaluation unit 231 satisfies the condition.

[0054] The input unit 233 inputs the prompt created by the creation unit 232 into the generation server 30 .

[0055] The providing unit 234 provides the terminal 10 with data constructed based on the response obtained from the generating server 30 .

[0056] The information providing server 20 can request the information providing server 20 to perform processing or display data received from the information providing server 20 via a web browser or a dedicated application.

[0057] The processing of the information providing server 20 will be explained in detail below, showing examples of prompts input to the generation server 30 and answers output from the generation server 30. In the following explanation, as an example, we will mainly explain a case where the government is a Japanese government agency (Ministry of Internal Affairs and Communications, Ministry of Agriculture, Forestry and Fisheries, etc.) and the user's industry is the information and communications industry. For example, the user requests the information providing server 20 to plan a project related to the government agency.

[0058] (1. Budget Evaluation) The following describes the evaluation of the budget by the evaluation unit 231. First, the evaluation unit 231 refers to the budget table 221 and selects a budget whose budget amount (for example, 100 million yen) is equal to or greater than a threshold value.

[0059] Furthermore, the evaluation unit 231 selects budgets whose contents of measures correspond to predetermined items from the selected budgets. The items here are determined based on the business or the like that the user is mainly implementing.

[0060] The evaluation unit 231 may determine whether or not a budget corresponds to an item using a machine learning model (including LLM), or may determine whether or not a specific keyword is included in the content of the measure or the budget item.

[0061] For example, if the user is an information and communications business operator, the item in the "Collection of Measures Related to Basic Measures for the Realization of a Digital Society" published by the Digital Agency may be used. The evaluation unit 231 determines that the budget with "No." "14" in Fig. 4 corresponds to the item "Popularization of Telework" in the "Collection of Measures Related to Basic Measures for the Realization of a Digital Society" because the content of the measure includes the keyword "telework."

[0062] The evaluation unit 231 calculates scores for the budgets selected in the processes up to this point. The evaluation unit 231 calculates a score for the degree of match between the policy content and social trends, a score for the attractiveness of the market related to the policy content, and a score for the urgency of the policy content.

[0063] The evaluation unit 231 calculates the score by searching a website or a specific database, etc., using keywords and by considering hypotheses using LLM, etc.

[0064] The evaluation unit 231 calculates a score of 1 to 5 as a score of the degree of agreement between the policy content and social trends. The criteria for calculating each score are as follows: 5 points: More than 10 listed Japanese companies are working to solve this issue. 4 points: At least five listed Japanese companies are working to solve this issue. 3 points: Three or more listed Japanese companies are working to solve this issue. 2 points: At least one listed Japanese company is working to solve this issue. 1 point: No listed Japanese companies are addressing this issue.

[0065] The evaluation unit 231 calculates a score of 1 to 5 as the attractiveness of the market related to the policy content. The criteria for calculating each score are as follows. 5 points: Public information + estimated market size of over 100 billion yen. 4 points: Public information + estimated market size of over 50 billion yen. 3 points: Public information + estimated market size of over 30 billion yen. 2 points: Public information + estimated market size of over 10 billion yen. 1 point: Public information + estimated market size of less than 10 billion yen.

[0066] The evaluation unit 231 calculates a score of 1 to 5 as the urgency score of the measure content. The criteria for calculating each score are as follows. 5 points: If the issue is not resolved within one year, the business will not survive. 4 points: If this issue is not resolved within three years, the business will not survive. 3 points: If this issue is not resolved within three years, there is a risk that new competitors will take away revenue. 2 points: There will be no impact on existing business even if this issue is not resolved. 1 point:-

[0067] The evaluation unit 231 may further evaluate each budget measure based on whether it is a measure that has been continued from the previous fiscal year, a measure that has been newly added in the current fiscal year, or whether it falls into either category.

[0068] Subsequent processing is performed on budgets for which the evaluation by the evaluation unit 231 satisfies the conditions (for example, the total score is equal to or greater than a threshold).

[0069] (2. Generation of initial hypotheses) The information providing server 20 generates an initial proposal hypothesis for a budget-related project. The initial proposal hypothesis is information that serves as the basis for generating detailed proposal content.

[0070] The information providing server 20 submits a plurality of prompts to the generation server 30 according to a procedure. The prompts submitted by the information providing server 20 may change based on the response from the generation server 30. By submitting the prompts in stages, the information providing server 20 can make the response from the generation server 30 closer to what the user intended.

[0071] For example, if a simple prompt such as "Please plan a business by an information and communications company" is entered alone, the generation server 30 may ignore the current issues and output as an answer a business based on the first idea generated.

[0072] On the other hand, for example, a user may want to be proposed a business that has sustainability and profitability above a certain level based on multiple business candidates that can solve current issues.

[0073] Therefore, the input unit 233 of the information providing server 20 gradually inputs prompts to help the user understand the problem itself, prompts to list current measures (businesses) that are expected to address the problem, and prompts to output the reasons why the problem has not been resolved by the measures.

[0074] The answers to the prompts at each stage are fed back to the generation server 30. That is, the generation server 30 generates an answer by referring to the prompts entered up to that point and the answers that have already been output, either according to the instructions in the prompt or of its own accord. The information providing server 20 may explicitly instruct in the prompt to refer to the answer at the previous stage.

[0075] Examples of prompts that allow the user to understand the task itself and answers to the prompts are shown in Fig. 5. Fig. 5 is a diagram showing examples of prompts and answers created by a person or an information providing system.

[0076] 5, the input unit 233 inputs a prompt 501. In response, the generation server 30 outputs a response 502. In this way, the information providing server 20 can have the generation server 30 organize the assignments and store the contents of the assignments together with a label such as "Assignment A."

[0077] Furthermore, the input unit 233 may input a prompt that further expands the current move, as shown in Fig. 6. Fig. 6 is a diagram showing examples of prompts and answers created by a person or an information providing system.

[0078] As shown in Fig. 6, the input unit 233 inputs a prompt 511. In response, the generating server 30 outputs a response 512. In this way, the information providing server 20 can add information to and expand the response output by the generating server 30. In the example of Fig. 6, information indicating the people involved has been added to the information on the action "1. Automation and remote control of forestry machinery" that has already been output.

[0079] Furthermore, the input unit 233 gradually inputs prompts to output multiple ideas for solving the problem, prompts to prioritize each of the multiple ideas, prompts to output an idea that integrates the multiple ideas, and prompts to create a text-based diagram for each of the multiple ideas.

[0080] Figure 7 shows examples of prompts that prompt a user to output multiple ideas for solving a problem and create a text-based diagram for each of the multiple ideas, as well as examples of responses to the prompts. Figure 7 shows examples of prompts and responses created by a person or an information providing system.

[0081] 7, the input unit 233 inputs a prompt 521. In response, the generation server 30 outputs a response 522. In this way, the information providing server 20 can generate a response with a condition such as "to generate a positive feedback loop regarding data acquisition and sales."

[0082] An example of a prompt that outputs an idea that integrates a plurality of ideas is shown in Fig. 8. Fig. 8 is a diagram showing an example of a prompt and an answer created by a person or an information providing system.

[0083] 8, the input unit 233 inputs a prompt 531. In response, the generation server 30 outputs an answer 532. In this way, the information providing server 20 can cause the generation server 30 to generate not only a single idea but also an answer including elements of multiple ideas.

[0084] Fig. 9 shows an example of a text-based diagram generated by the generation server 30. Fig. 9 is a diagram showing an example of a diagram of a proposed initial hypothesis. To obtain a diagram such as that shown in Fig. 9, the input unit 233 may input templates included in the document template DB 223 into the generation server 30 along with a prompt to create a text-based diagram for each of a plurality of ideas.

[0085] (3. Refine the initial hypothesis) After the proposed initial hypothesis is obtained, the information providing server 20 generates detailed proposal content based on the proposed initial hypothesis.

[0086] The information providing server 20 generates detailed proposal content by stepwise inputting prompts to the generation server 30 based on the proposed initial hypothesis. The information providing server 20 can also finally output the detailed proposal content as a material (document).

[0087] The input unit 233 of the information providing server 20 inputs prompts in stages, such as prompts for examining the details of the proposal, prompts for creating a product development story, prompts for formulating a sales policy, and prompts for examining the company's internal structure.

[0088] As with the generation of the proposed initial hypothesis, in the refinement of the proposed initial hypothesis, answers to prompts at each stage are fed back to the generation server 30 .

[0089] For example, a prompt to consider the details of the proposal will output the core story of the initial hypothesis of the proposal, market size, profit and loss, necessity of use, and required functions.

[0090] Furthermore, for example, a prompt for creating a product development story outputs information about the development of a product based on the initial hypothesis of the proposal. A product is a good or service provided by a business. For example, the product of a company in the information and communications industry may be rephrased as a solution, information processing service, information processing system, software, application, program, etc.

[0091] Specifically, in the process of creating a product development story, the information providing server 20 outputs to the generation server 30 the essential questions that the product answers, why the product is needed, the customer journey, press release images, virtual user feedback, product market fit (PMF), actions to cross the chasm, government outcomes from the business, the customer journey, etc.

[0092] An example of a hypothetical user's voice is shown in Figure 10. Figure 10 is a diagram showing examples of prompts and answers created by a person or an information provision system. Note that "Child Policy DX Hub" is an example of the name of a product generated as an initial hypothesis for the proposal.

[0093] 10, the input unit 233 inputs a prompt 541. In response, the generation server 30 outputs a response 542. In this way, the information providing server 20 can output the voice of a virtual user with conditions such as advantages and disadvantages, a specified number of personas, etc.

[0094] An example of why a product is desired (reason for the product being desired) is shown in FIG. 11. FIG. 11 is a diagram showing an example of a prompt and answer created by a person or an information providing system. As shown in FIG. 11, the input unit 233 inputs a prompt 551. In response, the generation server 30 outputs an answer 552. In this way, the information providing server 20 can output the reason for the product being desired after specifying multiple positions and output formats (items on the vertical and horizontal axes).

[0095] Furthermore, for example, the prompt for formulating a sales policy outputs a sales policy for a product based on the initial hypothesis of the proposal. Specifically, in the process of formulating the sales policy, the information providing server 20 causes the generation server 30 to output information such as known related businesses, companies that have received orders in the past, information that organizes the scope of proposals in the entire ecosystem related to the business from the "public, cooperative, and competitive service perspective," a project acquisition roadmap, and methods for approaching key people.

[0096] Furthermore, for example, a prompt to consider the internal structure causes the output of information regarding the internal structure related to the development of a product based on the initial hypothesis of the proposal. Specifically, the information providing server 20 causes the generation server 30 to output the product development status related to the business in related departments within the company, the method of hearing about the deployment roadmap, the possibility of collaboration with the service manager, etc.

[0097] The information providing server 20 creates materials for the proposed content. Fig. 12 is a diagram showing an example of materials showing the proposed content. For example, the materials may be created by the generating server 30. As shown in Fig. 12, in the step of refining the proposed initial hypothesis, detailed materials incorporating images and the like are output, compared to the materials for the proposed initial hypothesis in Fig. 9.

[0098] (4. Predicting future budget data) The input unit 233 of the information providing server 20 can cause the generating server 30 to predict future budget data.

[0099] At this time, the input unit 233 of the information providing server 20 inputs a prompt that instructs the user to think from a specific perspective, such as that of a "government official in charge of official statistics" at the "Ministry of Internal Affairs and Communications." The information providing server 20 then inputs a prompt that specifies a thinking method. The thinking method may be a combination of known methods such as "logical thinking," "systems thinking," and "design thinking."

[0100] The information providing server 20 predicts future budget data from a specified perspective and with a specified way of thinking based on documents related to past budgets and documents related to measures on a specific theme. For example, the information providing server 20 predicts the content and amount of measures for a budget following a specific theme for the fiscal year following the current fiscal year.

[0101] [Processing flow of the embodiment] The flow of processing by the information providing server 20 will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the flow of processing by the information processing server.

[0102] As shown in Fig. 13, first, the information providing server 20 evaluates budgets (step S10), and then the information providing server 20 narrows down the budgets to those whose evaluation results satisfy the conditions (step S20).

[0103] If there is an unselected budget in the narrowed-down budget data (Yes in step S30), the information providing server 20 proceeds to step S40. If there is no unselected budget (No in step S30), the information providing server 20 proceeds to step S80.

[0104] In step S40, the information providing server 20 selects one unselected budget (step S40), and generates a proposed initial hypothesis for the selected budget (step S50).

[0105] Then, the information providing server 20 generates detailed proposal content based on the proposed initial hypothesis (step S60). Furthermore, the information providing server 20 creates materials showing the proposal content (step S70).

[0106] In step S80, the information providing server 20 predicts future budget data (step S80). Note that the information providing server 20 does not necessarily have to execute step S80. Also, the information providing server 20 may execute step S80 independently.

[0107] The creation unit 232 creates a plurality of prompts related to government-related projects in steps S50, S60, etc. Specifically, the creation unit 232 creates a prompt that causes the generation server 30 to output a project proposal corresponding to the policy content corresponding to the government budget. The provision unit 234 provides information based on the answers obtained by sequentially inputting the plurality of prompts created by the creation unit 232 to the generation server 30.

[0108] In this way, by creating prompts to obtain useful information from the generative model, it becomes possible to easily obtain information about businesses that target governments as clients.

[0109] The flow of the process of evaluating the budget (step S10 in FIG. 13) will be described with reference to FIG. 14. FIG. 14 is a flowchart showing the flow of the process of evaluating the budget.

[0110] If there is an unselected budget in the budget data (step S101, Yes), the information providing server 20 proceeds to step S102. If there is no unselected budget (step S101, No), the information providing server 20 ends the process.

[0111] In step S102, the information providing server 20 selects one unselected budget (step S102). If the budget amount of the selected budget is 100 million yen or more (step S103, Yes), the information providing server 20 proceeds to step S104. If the budget amount of the selected budget is not 100 million yen or more (step S103, No), the information providing server 20 returns to step S101.

[0112] In step S104, if the policy content corresponds to any of the predetermined items (step S104, Yes), the information providing server 20 proceeds to step S105. If the policy content does not correspond to any of the predetermined items (step S104, No), the information providing server 20 returns to step S101.

[0113] In step S105, the information providing server 20 calculates a score of the degree of match between the policy content and social trends (step S105). The information providing server 20 also calculates a score of the market attractiveness related to the policy content (step S106). The information providing server 20 also calculates a score of the urgency of the policy content (step S107).

[0114] Then, the information providing server 20 stores the selected budget together with the priority based on the total score (step S108).

[0115] Here, the creation unit 232 creates a prompt to cause the generation server 30 to output a business plan for a budget for which the evaluation result by the evaluation unit 231 satisfies the conditions, i.e., a budget for which the budget amount corresponding to the budget is equal to or greater than a threshold and the policy content falls under a predetermined item.

[0116] This makes it possible to exclude in advance budgets with small amounts or budgets whose policy content does not match the operator's business, making it possible to plan projects efficiently.

[0117] The flow of the process for generating a proposed initial hypothesis (step S50 in FIG. 13) will be described with reference to FIG. 15. FIG. 15 is a flowchart showing the flow of the process for generating a proposed initial hypothesis.

[0118] The information providing server causes the generating server 30 to execute three main processes: observation (steps S501, S502, S503), observation (steps S501, S502, S503), idea creation (steps S504, S505, S506, S507), and summary (step S508).

[0119] First, the information providing server 20 allows the user to understand the problem (step S501). The information providing server 20 also allows the user to present a possible current move (step S502). The information providing server 20 also allows the user to output the reason why the move has not solved the problem (step S503).

[0120] Next, the information providing server 20 outputs a plurality of ideas for solving the problem based on the output of the observation (step S504). The information providing server 20 also assigns a priority to each of the plurality of ideas (step S505). The information providing server 20 also outputs an idea that integrates the plurality of ideas (step S506). The information providing server 20 also creates a text-based diagram for each of the plurality of ideas (step S507).

[0121] Then, the information providing server 20 creates slides for the presentation (step S508).

[0122] In the observation step, the creation unit 232 creates a prompt that causes the generation server 30 to output the issues and current situation of the policy content. In the idea creation step, the creation unit 232 creates a prompt that causes the generation server 30 to output a business proposal, taking into account the issues and current situation of the policy content that the generation server 30 has output.

[0123] Furthermore, the creation unit 232 creates a prompt that causes the generation server 30 to output multiple business proposals, and a prompt that causes the generation server 30 to output a proposal that integrates the multiple proposals that have been output by the generation server 30.

[0124] In this way, the information providing server 20 can make the answer from the generating server 30 closer to what the user intended by issuing prompts in stages.

[0125] The flow of the process for generating detailed proposal content (step S60 in FIG. 13) will be described with reference to Fig. 16. Fig. 16 is a flowchart showing the flow of the process for generating detailed proposal content.

[0126] First, the information providing server 20 outputs the core story, market size, profit and loss, necessity of use, and required functions of the proposed initial hypothesis (step S601). Next, the information providing server 20 outputs information related to the development of a product based on the proposed initial hypothesis (step S602).

[0127] Next, the information providing server 20 outputs a sales policy for the product based on the proposed initial hypothesis (step S603), and then outputs information about the in-house organization for developing the product based on the proposed initial hypothesis (step S604).

[0128] The creation unit 232 creates a plurality of prompts that cause detailed information of the business plan output by the generation server 30 to be output.

[0129] In this way, the information providing server 20 can refine the proposed initial hypothesis in stages, thereby brushing up the answer from the generating server 30 to make it more useful.

[0130] The flow of the process for creating a material (step S70 in FIG. 13) will be described with reference to Fig. 17. Fig. 17 is a flowchart showing the flow of the process for creating a material.

[0131] First, the information providing server 20 reads a template of a material (step S701). Next, the information providing server 20 creates a material based on the template and the contents of the detailed proposed initial hypothesis (step S702).

[0132] The flow of processing for predicting future budget data will be described with reference to Fig. 18. Fig. 18 is a flowchart showing the flow of processing for predicting future budget data.

[0133] First, the information providing server 20 inputs documents related to past budgets and documents related to measures on a specific theme (step S801). Next, the information providing server 20 predicts the content of future measures and the budget amount related to the budget using the documents as the input theme (step S802).

[0134] The theme may represent the business of the business operator. For example, if the business operator's industry is the information and communications industry, the theme may be cybersecurity, local government digital transformation, etc.

[0135] Here, the creation unit 232 creates a prompt that predicts the content of measures corresponding to the government's future budget based on information about past budgets. The providing unit 234 inputs the prompt created by the creation unit 232 into the generation server 30 and provides information (for example, predicted future policy content and budget amount) based on the response obtained.

[0136] This will make it easier to obtain information about projects targeting governments as clients, and by using the prediction results, more effective project planning will become possible.

[0137] The creation unit 232 can also create a prompt that specifies a way of thinking when predicting the content of measures corresponding to future budgets. The creation unit 232 creates a prompt that allows the user to predict the content of measures corresponding to future budgets from the perspective of a specific government official (for example, a government official in charge of official statistics). This makes it possible to obtain prediction results that meet the user's requirements.

[0138] The user may create the prompts themselves. For example, the user may create multiple prompts related to government-related projects and sequentially input the created multiple prompts into the generative model to obtain an answer. Alternatively, the user may create a prompt that predicts the content of measures corresponding to the government's future budget based on information about past budgets and input the created prompt into the generative model to obtain an answer. Alternatively, the information providing server 20 may receive a prompt created by the user and input the received prompt into the generation server 30 instead of performing processing by the creation unit 232.

[0139] [System configuration, etc.] Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in part by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0140] Furthermore, among the processes described in the embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0141] [program] In one embodiment, the information providing server 20 can be implemented by installing an information providing program that executes the above-described information processing as package software or online software on a desired computer. For example, by executing the above-described information providing program on an information processing device, the information processing device can function as the information providing server 20. The information processing device referred to here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as tablet terminals, smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as slate terminals such as PDAs (Personal Digital Assistants).

[0142] 19 is a diagram showing an example of the configuration of a computer that executes an information provision program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0143] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM (Random Access Memory) 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0144] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, the program that defines each process of the information providing server 20 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing processes similar to those of the functional configuration of the information providing server 20 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0145] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0146] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or a wide area network (WAN)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]

[0147] 10 devices 11, 21 Communications Department 12 Input section 13 Output section 14, 22 Storage section 15, 23 Control section 20 Information Server 30 Generation Server 151 Output control section 152 Communication control section 221 Budget Table 222 Prompt Master 223 Document Template DB 231 Evaluation Department 232 Creation Department 233 Insertion section 234 Provision Department 501, 511, 521, 531, 541, 551 prompts 502, 512, 522, 532, 542, 552 answers

Claims

1. a creation unit that creates a prompt by replacing the variables in a template, which is a text containing instructions for planning a project related to the budget item indicated by the variables; a providing unit that provides information based on an answer obtained by inputting the prompt created by the creating unit into a generative model; An information providing device comprising:

2. The creation unit creates a prompt that specifies a way of thinking when planning the business.

2. The information providing device according to claim 1.

3. The creation unit creates prompts that allow the project to be planned from the perspective of a specific government official.

2. The information providing device according to claim 1.

4. An information providing method executed by an information providing device, comprising: a creation step of creating a prompt by substituting the variables in a template, the template being a text containing instructions for planning a project related to the budget item represented by the variables; a providing step of providing information based on an answer obtained by inputting the prompt created in the creating step into a generative model; An information providing method comprising:

5. An information providing method executed by an information providing device, comprising: An information provision method characterized by providing information based on the answer obtained by inputting a prompt created by replacing variables in a template, which is text containing instructions for planning a project related to a budget item indicated by the variables, into a generative model.

6. creating a prompt by substituting the variables in a template, the template being text that contains instructions for planning a project related to the budget item represented by the variables; Input the prompt into the generative model An information providing method characterized in that the processing is executed by an information providing device.

7. a creation step of creating a prompt by substituting the variables in a template, the template being a text containing instructions for planning a project related to the budget item indicated by the variables; a providing step of providing information based on an answer obtained by inputting the prompt created by the creating step into a generative model; An information providing program that causes a computer to execute the above.

Images