Creation support device, creation support method, and program

Abstract

The progress of the discussion when creating ideas using generative AI could not be appropriately controlled. 【Solution means】A character setting unit 131 that gives a setting prompt for setting the characters of one or more agents to the generative AI, an idea acquisition unit 135 that gives a phase prompt corresponding to the idea generation phase to each of the one or more agents of the generative AI and acquires ideas, an idea output unit 142 that outputs the ideas, a determination unit 432 that determines whether the discussion change conditions are met, and when the determination unit 432 meets the discussion change conditions, a speech order change process for changing the speech order of two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea re-acquisition process for giving a prompt to each of the one or more agents again and acquiring ideas. With the creation support device 4 having a discussion change unit 433 that performs the above processes, when creating ideas using generative AI, the progress of the discussion can be appropriately controlled.

Description

Technical Field

[0001] The present invention relates to a creation support device and the like that assist in creating ideas using generative AI. Note that the support for idea creation may also be the creation of ideas.

Background Art

[0002] Conventionally, there has been an idea creation support system that is considered to be a platform as an environment in which ideas are easily created by participants (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, when creating ideas using generative AI, it has been difficult to appropriately control the progress of the discussion.

Means for Solving the Problems

[0005] The idea creation support device of the first invention is an idea creation support device that supports idea creation by two or more parties including one or more agents of a generative AI, and includes a setting prompt template for configuring a prompt for character setting of each of one or more agents, and a phase prompt template for configuring a prompt to be given to the generative AI in each of one or more phases including an idea generation phase. A prompt management unit in which is stored, an attribute value storage unit in which one or more idea attribute values are stored, which are attribute values regarding the idea to be created and include a theme of the target for idea generation, a person setting unit that acquires one or more setting prompts using the setting prompt template and gives each of the one or more setting prompts to the generative AI, and a phase corresponding to the idea generation phase. An idea acquisition unit that acquires a prompt using a prompt template and one or more idea attribute values, gives the prompt to each of one or more agents of the generative AI, and acquires an idea, an idea output unit that outputs the idea acquired by the idea acquisition unit, a determination unit that determines whether it meets the discussion change condition, and when the determination unit determines that it meets the discussion change condition, a speech order change process for changing the speech order of two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea re-acquisition process for giving a prompt to each of one or more agents again and acquiring an idea. It is an idea creation support device comprising a discussion change unit that performs

[0006] With such a configuration, when creating an idea using a generative AI, the progress of the discussion can be appropriately controlled.

[0007] Further, the idea creation support device of the second invention further includes an idea reception unit that receives one or more ideas from a person with respect to the first invention, and the idea output unit outputs the idea acquired by the idea acquisition unit or one or more ideas received by the idea reception unit. The determination unit determines whether the idea acquired by the idea acquisition unit, one or more ideas received by the idea reception unit, the time until the idea reception unit receives one or more ideas from a person, or the received instruction meets the discussion change condition. It is an idea creation support device.

[0008] With such a configuration, it is possible to assist in creating appropriate ideas through cooperation between humans and generative AI.

[0009] In addition, the idea creation support device of the third invention further includes, for the second invention, a discussion change unit that performs additional instruction input processing and has an additional instruction reception unit that receives additional instructions, and an additional instruction unit that passes a prompt having the additional instructions to the generative AI.

[0010] With such a configuration, when creating ideas using generative AI, the progress of the discussion can be appropriately controlled.

[0011] In addition, the idea creation support device of the fourth invention, for any one of the first to third inventions, the discussion change unit gives the ideas acquired by the idea acquisition unit or one or more ideas received by the idea reception unit to the generative AI, and also gives them to the generative AI for generating a prompt corresponding to the idea generation phase, and is an idea creation support device that performs an idea re-acquisition process for acquiring ideas.

[0012] With such a configuration, when creating ideas using generative AI, the progress of the discussion can be appropriately controlled.

[0013] In addition, the idea creation support device of the fifth invention further includes, for the second invention, a ranking unit that determines the rank of a person using one or more ideas received by the idea reception unit and accumulates the rank in pairs with a person identifier that identifies the person.

[0014] With such a configuration, the rank of a person who participated in the creation of ideas can be determined.

[0015] Further, in the idea creation support device of the sixth invention, for any one of the first to fifth inventions, the character setting unit acquires two or more setting prompts using a setting prompt template, gives each of the two or more setting prompts to the generation AI, acquires a speech order determination prompt using a speech order determination prompt template for determining the speech order of each of the two or more agents, gives the speech order determination prompt to the generation AI, and further includes a speech order determination unit that determines the speech order of the agents corresponding to each of the two or more setting prompts. The idea acquisition unit is an idea creation support device that acquires ideas from each agent in the order indicated by the speech order of the two or more agents determined by the speech order determination unit.

[0016] With such a configuration, when creating ideas using two or more generation AI agents, the discussion can proceed in an appropriate speech order.

Effect of the Invention

[0017] According to the idea creation support device of the present invention, when creating ideas using a generation AI, the progress of the discussion can be appropriately controlled.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29

Figure 30

Figure 31

Figure 32

Figure 33

Mode for Carrying Out the Invention

[0019] Hereinafter, embodiments of a creation support device and the like will be described with reference to the drawings. In the embodiments, components denoted by the same reference numerals perform the same operations, and thus the description may be omitted again.

[0020] (Embodiment 1) In the present embodiment, a device for assisting in creating ideas by two or more parties including agents of one or more generative AIs will be described. The device acquires two or more ideas in the idea generation phase, and then acquires and outputs one or more ideas from the two or more acquired ideas in the subsequent idea selection phase.

[0021] Also, in the present embodiment, a creation support device in which human participation is also possible in the creation of ideas will be described.

[0022] Also, in the present embodiment, a creation support device that examines an input from a person and may or may not give the input to the generative AI according to the examination result will be described. In the present embodiment, when the examination result of the input from a person is an error, an error message is output or the class of the error is output.

[0023] Also, in the present embodiment, a creation support device having a moderator agent will be described.

[0024] Also, in the present embodiment, a creation support device that operates so that the moderator agent gives a prompt to other agents when a predetermined condition is satisfied will be described.

[0025] Also, in the present embodiment, a creation support device that outputs answers from a generation AI for creating ideas and the like in a manner that allows the current phase to be understood within the overall phase of creating ideas will be described.

[0026] Also, in the present embodiment, a creation support device that receives a theme from a user and creates ideas according to the theme will be described.

[0027] Also, in the present embodiment, a creation support device that automatically determines necessary agents will be described.

[0028] Also, in the present embodiment, a creation support device that evaluates the set of output ideas from the perspective of diversity will be described.

[0029] Furthermore, in the present embodiment, a creation support device that manages two or more phases and phase transition conditions until an idea is created and controls the phase transition based on the managed information will be described.

[0030] Note that in this specification, information X being associated with information Y means that information Y can be obtained from information X or information X can be obtained from information Y, and the method of association is not limited. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0031] Also, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag for information Z, etc., as long as information Z can be accessed.

[0032] Figure 1 is a conceptual diagram of the information system A in the present embodiment. The information system A includes a creation support device 1, one or two or more terminal devices 2, and one or two or more generation AI devices 3. Note that the program stored in the generation AI device 3 is referred to as a generation AI. Also, the generation AI device 3 may be referred to as a generation AI. The information system A may have one generation AI device 3 or two or more. When there are two or more generation AI devices 3, it is preferable that there is a generation AI device 3 corresponding to each agent described later. Note that the generation AI device is an external device with respect to the information system A, and the information system A may be considered not to have the generation AI device 3.

[0033] The creation support device 1 is, for example, a cloud server or an ASP server, but its type does not matter. The creation support device 1 may be a terminal. When the creation support device 1 is a terminal, the terminal device 2 is not necessary for the information system A. When the creation support device 1 is a terminal, it may be considered that the creation support device 1 also serves as the terminal device 2. When the creation support device 1 is a terminal, the creation support device 1 is, for example, a so-called personal computer, smartphone, or tablet terminal, but its type does not matter.

[0034] Note that the creation support device 1 may have one or two or more generation AIs. In such a case, the information system A may not have the generation AI device 3.

[0035] The terminal device 2 is a terminal used by the user. The user is a person who uses the creation support device 1. The user may be a person who inputs ideas or a person who checks the ideas output by the creation support device 1.

[0036] The generation AI device 3 is, for example, a server of ChatGPT (registered trademark) or a server of Bard (registered trademark).

[0037] It is preferable that the creation support device 1 and each of the one or more terminal devices 2, and the creation support device 1 and each of the one or more generation AI devices 3 can communicate with each other via a network such as the Internet.

[0038] Figure 2 is a block diagram of the information system A in the present embodiment. Figure 3 is a block diagram of the creation support device 1.

[0039] The creation support device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a transition management unit 111, a prompt management unit 112, an attribute value storage unit 113, and a current management unit 114. The reception unit 12 includes an attribute value reception unit 121 and an idea reception unit 122. The processing unit 13 includes an agent determination unit 130, a person setting unit 131, a control unit 132, a master of ceremony determination unit 133, a perspective acquisition unit 134, an idea acquisition unit 135, an idea criticism unit 136, an idea selection unit 137, an analysis unit 138, and a score acquisition unit 139. The output unit 14 includes an answer output unit 141, an idea output unit 142, a score output unit 143, and an error output unit 144.

[0040] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit 26.

[0041] Various types of information are stored in the storage unit 11 that constitutes the creation support device 1. The various types of information are, for example, the transition information described later and the prompt template described later.

[0042] The transition management unit 111 stores transition information and transition conditions. The transition information is information that specifies the transition between two or more phases for creating an idea. The phase may be referred to as a procedure, a step, a stage, etc. For example, the phase is represented by a node, and the transition between phases is represented by an edge. The transition information usually has two or more phase identifiers. The transition information has, for example, edge information that links two phases. The edge information has, for example, two phase identifiers. The edge information has, for example, an edge identifier.

[0043] A transition condition is a condition under which a phase transitions. A transition condition is a condition associated with the phase before the transition and the phase after the transition. A transition condition is a condition associated with edge information. Two or more transition conditions may be associated with a single phase information. When two or more transition conditions are associated with a single phase information, there are two or more phases after the transition. That is, when two or more transition conditions are associated with a single phase information, the phase branches.

[0044] Each of the two or more phases specified by the transition information is a step until an idea is created. Each of the two or more phases specified by the transition information includes (a) an idea generation phase and (b) an idea selection phase. Each of the two or more phases specified by the transition information is, for example, (1) an idea perspective / evaluation perspective consideration phase, (2) an idea generation phase, (3) an idea criticism phase, and (4) an idea selection phase. The phase identifiers included in the transition information are, for example, "idea perspective / evaluation perspective consideration", "idea generation", "idea criticism", and "idea selection".

[0045] Note that the idea selection phase may be a phase of selecting some ideas from two or more ideas, or may be a phase of ranking two or more ideas. That is, here, the ranking of ideas may also be considered to be included in the selection of ideas.

[0046] The prompt management unit 112 stores various prompt templates. A prompt template is information for constructing a prompt. A prompt template usually includes variables. A prompt is constructed by substituting information into the variable locations. However, a prompt template may be a prompt that does not include variables. A prompt is information given to a generative AI. By giving a prompt to a generative AI, an answer is usually returned from the generative AI. A prompt may also be referred to as an inquiry, a query, etc. Giving a prompt to a generative AI is, for example, giving the prompt as an argument of the API of the generative AI and executing the API.

[0047] The prompt management unit 112 stores one or more setting prompt templates and one or more phase prompt templates. The prompt management unit 112 stores, for example, one or more agent determination prompt templates. The prompt management unit 112 stores, for example, an idea analysis prompt template.

[0048] It is preferable that the prompt management unit 112 stores a setting prompt template for the emcee and a phase prompt template for the emcee. An emcee is a person who conducts the emcee in a role-play for creating ideas.

[0049] A setting prompt template is a prompt template for setting the characters of agents. One setting prompt template is information for setting the characters of one or more agents. The setting prompt template is associated with, for example, an agent identifier. The setting prompt template has, for example, variables "name", "occupation", "role", and "specialty".

[0050] An agent is, here, a role played by a generative AI. An agent is, here, a virtual person in the position of creating ideas, criticizing ideas, or selecting ideas. An agent may also be referred to as a persona or the like.

[0051] An agent determination prompt template is a prompt template for determining one or more agents. The agent determination prompt template usually has a variable into which a theme is substituted. The agent determination prompt template has, for example, variables into which one or more idea perspectives and one or more evaluation perspectives are substituted. The agent determination prompt template is, for example, "When creating ideas related to the theme of "<theme>", what kind of person would be needed for the required position?"

[0052] A phase prompt prototype is a prompt prototype in any phase. A phase prompt prototype is usually associated with a phase identifier. Note that being associated with a phase identifier may also mean that all or part of the phase identifier is included in the prompt prototype identifier.

[0053] In the prompt management unit 112, for example, an idea perspective prompt prototype and an evaluation perspective prompt prototype are stored in association with the phase identifier "Idea perspective and evaluation perspective study phase". An idea perspective prompt prototype is a prototype of a prompt for obtaining one or more idea perspectives. An idea perspective prompt prototype usually has a variable into which a theme is substituted. The idea perspective prompt prototype may, for example, have a variable into which an idea perspective given by the user is substituted. The idea perspective prompt prototype is, for example, "Tell me the perspective of ideas regarding the theme <theme>!". An evaluation perspective prompt prototype is a prototype of a prompt for obtaining one or more evaluation perspectives. An evaluation perspective prompt prototype usually has a variable into which a theme is substituted. The evaluation perspective prompt prototype may, for example, have a variable into which an evaluation perspective given by the user is substituted. The evaluation perspective prompt prototype is, for example, "Tell me the perspective for evaluating ideas regarding the theme <theme>!".

[0054] An idea perspective is a perspective regarding an idea. Idea perspectives are, for example, "Clarification of purpose", "Technical feasibility", "Regulatory requirements", "Economic feasibility". An evaluation perspective is a perspective when evaluating an idea. Evaluation perspectives are, for example, "Development cost", "Usability", "Market applicability", "Compliance with regulations".

[0055] In the prompt management unit 112, for example, an idea generation prompt template is stored in association with the phase identifier "idea generation phase". The idea generation prompt template is information for constructing a prompt for idea generation. The idea generation prompt template usually has variables into which a theme is substituted. It is preferable that the idea generation prompt template has variables into which an idea perspective and an evaluation perspective are substituted. It is preferable that the idea generation prompt template has variables into which all or part of the agent information (for example, "name") is substituted. The idea generation prompt template is, for example, "You are Mr. <name>. Regarding <theme>, please come up with ideas considering the following idea perspectives and the following idea evaluation perspectives. <Idea perspective>, <Evaluation perspective>".

[0056] In the prompt management unit 112, for example, an idea criticism prompt template is stored in association with the phase identifier "idea criticism phase". The idea criticism prompt template is a template for a prompt for obtaining one or more criticisms of an idea. The idea criticism prompt template usually has a variable into which an idea is substituted. The idea criticism prompt template is, for example, "Regarding <theme>, please list the problems and issues of the idea \"<Idea>\".

[0057] In the prompt management unit 112, for example, an idea selection prompt template is stored in association with the phase identifier "idea selection phase". The idea selection prompt template is a template for a prompt for selecting or ranking ideas. The idea selection prompt template has variables into which two or more ideas are substituted. Note that the selection of ideas may also be a ranking of ideas. The idea selection prompt template is, for example, "Request to the emcee. Please rank the following set of ideas. <Set of ideas>""Request to the emcee. Please select five ideas that seem to be good ideas from the following set of ideas. <Set of ideas>".

[0058] An idea analysis prompt prototype is a prototype of a prompt for analyzing ideas. An idea analysis prompt prototype usually has variables for substituting ideas. An idea analysis prompt prototype has, for example, a variable for substituting a theme. An idea analysis prompt prototype is, for example, "Answer whether the following idea is appropriate as an idea related to <theme> with either appropriate '1' or inappropriate '0'! <idea>".

[0059] One or more idea attribute values are stored in the attribute value storage unit 113. An idea attribute value is information related to the idea to be created. The one or more idea attribute values are, for example, a theme, a purpose, a perspective to be included in the idea, and a perspective for idea criticism. The idea attribute value in the attribute value storage unit 113 may be information input from the user, information stored in advance, or information obtained based on an answer from a generative AI.

[0060] The current management unit 114 stores a current identifier. A current identifier is information for identifying the current. The current is the current phase among two or more phases. The two or more phases usually include an idea generation phase and an idea selection phase.

[0061] The reception unit 12 receives various instructions and information. The various instructions and information are, for example, one or more idea attribute values, one or more ideas, and a start instruction.

[0062] Here, reception usually means receiving information transmitted via a wired or wireless communication line, but it may also be a concept including receiving information input from an input device such as a keyboard, a mouse, or a touch panel, and receiving information read from a recording medium such as an optical disk, a magnetic disk, or a semiconductor memory.

[0063] The start instruction is an instruction to start creating an idea. The start instruction includes, for example, one or more idea attribute values including a theme.

[0064] The attribute value receiving unit 121 receives one or more idea attribute values. It is preferable that the one or more idea attribute values include a theme. The one or more idea attribute values include, for example, an idea perspective and an evaluation perspective. The attribute value receiving unit 121 receives, for example, one or more idea attribute values from the terminal device 2.

[0065] The idea receiving unit 122 receives one or more ideas from people. The idea receiving unit 122 receives, for example, one or more ideas from the terminal device 2.

[0066] The processing unit 13 performs various processes. The various processes are, for example, processes performed by the agent determination unit 130, the person setting unit 131, the control unit 132, the emcee determination unit 133, the perspective acquisition unit 134, the idea acquisition unit 135, the idea criticism unit 136, the idea selection unit 137, the analysis unit 138, or the score acquisition unit 139.

[0067] The agent determination unit 130 determines one or two or more agents. Determining an agent usually involves acquiring agent information. Note that the agent information may be given in advance. That is, the agent information may be stored in the storage unit 11 in advance.

[0068] Agent information is information about an agent. Agent information usually includes an agent identifier. An agent identifier is information for identifying an agent. The agent identifier is, for example, an occupation or a specialty. Agent information includes, for example, ability information indicating the ability of the agent.

[0069] The agent determination unit 130, for example, gives an agent determination prompt to the generation AI and acquires one or two or more pieces of agent information from the generation AI.

[0070] The agent determination unit 130, for example, substitutes a theme or the like into the variables of the agent determination prompt template of the prompt management unit 112 to obtain an agent determination prompt, gives the agent determination prompt to the generation AI, and obtains one or more pieces of agent information from the generation AI.

[0071] It is preferable that the agent determination unit 130 obtains one or more pieces of agent information from the generation AI only when the agent acquisition conditions are met. The agent acquisition conditions are the conditions for acquiring an agent. The agent acquisition conditions are, for example, conditions regarding the given agent information. The agent acquisition conditions are, for example, that the number of the given agent information is 0 or below a threshold value.

[0072] The agent determination unit 130, for example, obtains one or more pieces of agent information paired with the theme of idea creation from the agent correspondence table. The agent correspondence table is a table showing the correspondence between the theme and the agent information. The agent correspondence table has two or more pieces of agent correspondence information. The agent correspondence information has a theme and agent information.

[0073] The character setting unit 131 obtains one or more setting prompts using the setting prompt template and gives each of the one or more setting prompts to the generation AI.

[0074] The character setting unit 131, for example, acquires a setting prompt prototype from the prompt management unit 112, replaces variables in the setting prompt prototype with agent information of one or more agents, constructs a setting prompt, and provides the setting prompt to the generation AI. The character setting unit 131 may construct a setting prompt for each agent and provide the setting prompt for each agent to the generation AI. Further, the character setting unit 131 may construct a setting prompt including agent information of two or more agents and provide the setting prompt to the generation AI. Such agent information may be agent information regarding one or more agents determined by the agent determination unit 130, or may be pre-provided agent information. That is, the character setting unit 131 may acquire setting prompts for one or more agents determined by the agent determination unit 13 and provide the setting prompts to the generation AI.

[0075] It is preferable that the character setting unit 131 also provides the generation AI with a setting prompt for the emcee. That is, there may be two or more agents, and among the two or more agents, one agent may be the emcee agent. The setting prompt for the emcee is stored in the prompt management unit 112, for example.

[0076] The control unit 132 determines whether or not it matches the transition condition associated with the current phase of the current phase, and when it matches the transition condition, changes the current phase from the current phase to the post-transition phase associated with the transition condition. The control unit 132 usually changes the phase identifier of the current of the current management unit 114 to the phase identifier of the post-transition phase.

[0077] The emcee determination unit 133 determines whether or not the prompt given to the generation AI or the answer from the generation AI satisfies the emcee speech condition. The emcee speech condition may be any transition condition.

[0078] The master of ceremonies' speaking conditions are the conditions under which the agent of the master of ceremonies speaks, and are conditions related to the prompt given to the generative AI or conditions related to the answer from the generative AI. The master of ceremonies' speaking conditions are, for example, "ideas have been obtained from all two or more parties" and "a predetermined period of time has elapsed in a situation where there is no input from people".

[0079] The viewpoint acquisition unit 134 acquires one or more idea viewpoints or one or more evaluation viewpoints. The viewpoint acquisition unit 134 acquires, for example, one or more idea viewpoints received by the attribute value reception unit 121. The viewpoint acquisition unit 134 acquires, for example, one or more evaluation viewpoints received by the attribute value reception unit 121.

[0080] The viewpoint acquisition unit 134, for example, substitutes the theme into the variable of the idea viewpoint prompt prototype, constructs the idea viewpoint prompt, passes the idea viewpoint prompt to the generative AI, and acquires one or more idea viewpoints from the generative AI. Note that the idea viewpoint prompt prototype is, for example, "Tell me the viewpoints when creating ideas about the following theme! <theme>". Also, <theme> is a variable into which the acquired theme is substituted. The character string enclosed in "<" and ">" indicates that it is a variable.

[0081] The viewpoint acquisition unit 134, for example, substitutes the theme into the variable of the evaluation viewpoint prompt prototype, constructs the evaluation viewpoint prompt, passes the evaluation viewpoint prompt to the generative AI, and acquires one or more evaluation viewpoints from the generative AI. Note that the evaluation viewpoint prompt prototype is, for example, "Tell me the viewpoints for evaluating the ideas of the following theme! <theme>".

[0082] The viewpoint acquisition unit 134 preferably determines, for example, whether or not it meets the viewpoint acquisition conditions, and acquires the viewpoint only when it is determined that it meets the conditions. The viewpoint acquisition conditions are, for example, conditions related to the idea viewpoint. The viewpoint acquisition conditions are, for example, conditions related to the evaluation viewpoint. The viewpoint acquisition unit 134 determines, for example, that it acquires the idea viewpoint when the number of received idea viewpoints is equal to or less than a threshold value. The viewpoint acquisition unit 134 determines, for example, that it acquires the evaluation viewpoint when the number of received evaluation viewpoints is equal to or less than a threshold value. Note that the threshold value is a natural number of 1 or more.

[0083] The idea acquisition unit 135 acquires a prompt using a phase prompt prototype corresponding to one or more phases, gives the prompt to the generative AI, and acquires two or more ideas.

[0084] The idea acquisition unit 135 acquires a prompt using, for example, a phase prompt prototype corresponding to the idea generation phase and one or two or more idea attribute values, gives the prompt to one or more agents of the generative AI, and acquires two or more ideas. The one or more idea attribute values here are, for example, one or two or more pieces of information among a theme, an idea viewpoint, and an evaluation viewpoint. It is preferable that the idea acquisition unit 135 acquires a prompt using the theme and the idea viewpoint, gives the prompt to one or more agents of the generative AI, and acquires two or more ideas. The idea acquisition unit 135 may acquire a prompt using the theme, the idea viewpoint, and the evaluation viewpoint, give the prompt to one or more agents of the generative AI, and acquire two or more ideas.

[0085] Note that giving the prompt to one or more agents of the generative AI is, for example, giving the generative AI a prompt including a string indicating that it is an inquiry to one or more agents. Giving the generative AI a prompt usually means executing an API of the generative AI that includes the prompt as an argument.

[0086] The idea acquisition unit 135, for example, corresponds to the idea generation phase, obtains a prompt using a phase prompt template for the emcee and one or more idea attribute values, provides the prompt to the generative AI, and obtains ideas from one or more of the two or more agents.

[0087] The idea acquisition unit 135, for example, when the emcee determination unit 133 determines that the emcee speech condition is satisfied, corresponds to the idea generation phase, obtains a prompt for one or more agents other than the emcee, provides the prompt to the generative AI, and obtains two or more ideas. It is preferable that the idea acquisition unit 135 obtains ideas from one or more agents not just once, but two or more times.

[0088] The idea criticism unit 136 obtains one or more criticisms for each of the two or more ideas obtained by the idea acquisition unit 135. The criticism may be referred to as a problem point, an issue, etc. The criticism is a character string.

[0089] The idea criticism unit 136, for example, substitutes the idea obtained by the idea acquisition unit 135 into the variable of the criticism prompt template corresponding to the idea criticism phase, configures the criticism prompt, passes the criticism prompt to the generative AI, and obtains one or more criticisms from the generative AI. The idea criticism unit 136 may also substitute one or more evaluation perspectives into the variable of the criticism prompt template, configure the criticism prompt, pass the criticism prompt to the generative AI, and obtain one or more criticisms from the generative AI.

[0090] The idea criticism unit 136, for example, for each of the two or more ideas obtained by the idea acquisition unit 135, substitutes the idea into the variable of the criticism prompt template, configures the criticism prompt, passes the criticism prompt to the generative AI, and obtains one or more criticisms from the generative AI.

[0091] The idea criticism unit 136, for example, for each of two or more ideas acquired by the idea acquisition unit 135 and for each of two or more agents, substitutes part or all of the idea and agent information into the variables of the criticism prompt template, constructs a criticism prompt, passes the criticism prompt to the generative AI, and acquires one or more criticisms from the generative AI.

[0092] The idea criticism unit 136 may, for example, construct a criticism prompt for each of two or more evaluation perspectives, pass the criticism prompt to the generative AI, and acquire one or more criticisms from the generative AI. The criticism prompt template in such a case is, for example, "You are <name>. Regarding <theme>, please list the problems and issues of the idea '<idea>' from the evaluation perspective '<evaluation perspective>'." Through the above processing, the idea criticism unit 136 obtains one or two or more criticisms for each of two or more ideas and for each of two or more evaluation perspectives.

[0093] The idea selection unit 137 obtains a prompt using the phase prompt template corresponding to the idea selection phase and two or more ideas acquired by the idea acquisition unit 135, gives the prompt to the generative AI, and acquires one or more ideas selected based on the two or more ideas acquired by the idea acquisition unit 135. Note that the one or more selected ideas may be two or more ranked ideas.

[0094] The idea selection unit 137, for example, for each of two or more agents, substitutes the set of two or more ideas and part or all of the agent information into the variables of the idea selection prompt template, constructs an idea selection prompt, gives the idea selection prompt to the generative AI, and acquires one or two or more ideas.

[0095] The idea selection unit 137, for example, substitutes the two or more ideas acquired by the idea acquisition unit 135 into the variables of the phase prompt template corresponding to the idea selection phase, obtains a prompt, gives the prompt to the generative AI, and acquires one or more selected ideas.

[0096] The idea selection unit 137 substitutes, for example, two or more ideas acquired by the idea acquisition unit 135 and one or more criticisms acquired by the idea criticism unit 136 into variables of a phase prompt prototype corresponding to the idea selection phase, obtains a prompt, gives the prompt to the generation AI, and acquires one or more selected ideas.

[0097] The idea selection unit 137 obtains a prompt using a phase prompt prototype corresponding to the idea selection phase, two or more ideas acquired by the idea acquisition unit 135, and one or more ideas received by the idea reception unit 122, gives the prompt to the generation AI, and acquires one or more selected ideas based on two or more ideas acquired by the idea acquisition unit 135 and one or more ideas received by the idea reception unit 122.

[0098] The idea selection unit 137 obtains a prompt using, for example, a phase prompt prototype corresponding to the idea selection phase and two or more ideas excluding the ideas determined by the analysis unit 138 not to meet the examination conditions, gives the prompt to the generation AI, and acquires one or more selected ideas based on two or more ideas acquired by the idea acquisition unit 135 and one or more ideas received by the idea reception unit 122.

[0099] The idea selection unit 137 obtains a prompt using, for example, a phase prompt prototype corresponding to the idea selection phase for the emcee and two or more ideas acquired by the idea acquisition unit 135, gives the prompt to the generation AI, and acquires one or more selected ideas based on two or more ideas acquired by the idea acquisition unit 135.

[0100] The analysis unit 138 analyzes each of one or more ideas received by the idea reception unit 122 and obtains error classes. Note that two or more classes of errors usually include "normal".

[0101] The analysis unit 138 substitutes each of the one or more ideas received by the idea reception unit 122 into the variables of the idea analysis prompt prototype, constructs the idea analysis prompt, passes the idea analysis prompt to the generation AI, and may obtain from the generation AI an answer as to whether the idea is normal or an error.

[0102] The analysis unit 138 may, for example, perform natural language processing on the character strings of each of the one or more ideas received by the idea reception unit 122, determine whether it corresponds to an "idea", and obtain a class. Note that the technique of classifying character strings is a known technique.

[0103] The score acquisition unit 139 performs natural language processing on two or more ideas acquired by the idea acquisition unit 135 or the idea selection unit 137, and acquires a score regarding the diversity of the ideas. The score acquisition unit 139 acquires, for example, a Remote-Clique (RC value) or a Chamfer Distance (CD value), which is a score regarding the diversity of two or more ideas, using the character strings of the two or more ideas. Since the techniques for acquiring the RC value and the CD value are known techniques, detailed descriptions thereof are omitted.

[0104] The score acquisition unit 139 may also acquire the scores of each of the one or two or more ideas acquired by the idea acquisition unit 135 or the idea selection unit 137. The score acquisition unit 139 preferably acquires the score of the idea, for example, using one or more criticisms corresponding to the idea and one or more criticisms acquired by the idea criticism unit 136. It does not matter how the score acquisition unit 139 acquires the scores of each of the one or more ideas using the one or more criticisms of each idea.

[0105] For example, the score acquisition unit 139 substitutes, for each of two or more evaluation viewpoints, one or more criticisms for two or more ideas into a variable of a ranking prompt template for causing ranking of two or more ideas, constructs a ranking prompt, gives the ranking prompt to the generation AI, and obtains rankings of two or more ideas for each of two or more evaluation viewpoints from the generation AI. Next, the score acquisition unit 139 obtains a higher score for each of two or more ideas as the ranking for each of two or more evaluation viewpoints is higher. For example, the score acquisition unit 139 obtains scores for each of two or more ideas for each of two or more evaluation viewpoints, and calculates a score by an increasing function (for example, sum, average value, median, etc.) using the two or more scores as parameters. Note that the score for each of two or more evaluation viewpoints for an idea is calculated by a decreasing function using, for example, the ranking of the evaluation viewpoint as a parameter. The decreasing function is, for example, "Score for each evaluation viewpoint = (100 * (number of ideas - ranking)) / (number of evaluation viewpoints * (number of ideas - 1))".

[0106] Also, the score acquisition unit 139 obtains a lower score as the number of criticisms corresponding to an idea is larger. The score acquisition unit 139 calculates a score by a decreasing function using, for example, the number of criticisms corresponding to an idea as a parameter.

[0107] When the score acquisition unit 139 obtains two or more scores, the idea selection unit 137 may associate ranks based on the scores with two or more ideas (or may perform ranking) using the scores. The idea selection unit 137 assigns a higher rank to an idea with a higher score.

[0108] The output unit 14 outputs various types of information. The various types of information are, for example, all or part of the answer passed from the generation AI, or one or two or more ideas.

[0109] The output unit 14 preferably outputs all or part of the answer passed from the generation AI in a manner that can grasp the current identified by the current identifier.

[0110] Here, the output is usually transmission to the terminal device 2, but may also be a concept including display on a display, projection using a projector, printing by a printer, sound output, storage in a recording medium, delivery of a processing result to another processing device or another program, etc.

[0111] The answer output unit 141 outputs all or part of the answer passed from the generation AI. The answer passed from the generation AI may include ideas.

[0112] The idea output unit 142 outputs one or more ideas acquired by the idea selection unit 137. It is preferable that the idea output unit 142 outputs two or more ideas ranked by the idea selection unit 137 in a manner where the ranking is known.

[0113] The score output unit 143 outputs the score acquired by the score acquisition unit 139.

[0114] When the analysis unit 138 determines that the examination conditions are not satisfied, the error output unit 144 outputs an error message. It is preferable that the error output unit 144 outputs an error message including the class of the error.

[0115] Various types of information are stored in the terminal storage unit 21 that constitutes the terminal device 2. The various types of information are, for example, user identifiers. A user identifier is information for identifying a user.

[0116] The terminal reception unit 22 receives various types of information, instructions, etc. The various types of information, instructions, etc. are, for example, one or more ideas, one or more idea attribute values. The input means for the various types of information, instructions, etc. can be anything, such as a touch panel, keyboard, mouse, microphone, menu screen, etc.

[0117] The terminal processing unit 23 performs various processes. The various processes are, for example, processes of converting received information, instructions, etc. into information, instructions, etc. having a structure for transmission. The various processes are, for example, processes of converting received information into information having a structure for output.

[0118] The terminal transmission unit 24 transmits various information, instructions, etc. to the idea creation support device 1. The various information, instructions, etc. are, for example, one or more ideas, one or more idea attribute values.

[0119] The terminal reception unit 25 receives various information. The various information is, for example, answers, ideas, scores, error messages.

[0120] The terminal output unit 26 outputs various information. The various information is, for example, answers, ideas, scores, error messages.

[0121] For the storage unit 11, the transition management unit 111, the prompt management unit 112, the attribute value storage unit 113, the current management unit 114, and the terminal storage unit 21, a non-volatile recording medium is preferable, but it can also be realized with a volatile recording medium.

[0122] The process of storing information in the storage unit 11 etc. is not limited. For example, information may be stored in the storage unit 11 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 11 etc., or information input via an input device may be stored in the storage unit 11 etc.

[0123] The reception unit 12, the attribute value reception unit 121, and the idea reception unit 122 are usually realized by wireless or wired communication means, but may also be realized by means of receiving broadcasts, device drivers of input means such as touch panels and keyboards, control software of menu screens, etc.

[0124] The processing unit 13, agent determination unit 130, character setting unit 131, control unit 132, emcee determination unit 133, viewpoint acquisition unit 134, idea acquisition unit 135, idea criticism unit 136, idea selection unit 137, analysis unit 138, score acquisition unit 139, and terminal processing unit 23 can generally be realized from a processor, memory, etc. The processing procedures of the processing unit 13 etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). Note that the processor may be a CPU, MPU, GPU, etc., and its type is not limited.

[0125] The output unit 14, answer output unit 141, idea output unit 142, score output unit 143, and error output unit 144 are generally realized by wireless or wired communication means, but may also be realized by driver software for output devices such as displays and speakers, or by driver software for output devices and output devices etc.

[0126] The terminal reception unit 22 can be realized by a device driver for input means such as a touch panel or keyboard, control software for a menu screen, etc.

[0127] The terminal transmission unit 24 is generally realized by wireless or wired communication means, but may also be realized by broadcast means.

[0128] The terminal reception unit 25 is generally realized by wireless or wired communication means, but may also be realized by means for receiving broadcasts.

[0129] The terminal output unit 26 may or may not be considered to include output devices such as displays and speakers. The terminal output unit 26 can be realized by driver software for output devices, or by driver software for output devices and output devices etc.

[0130] Next, an operation example of the creation support device 1 will be described using the flowchart of FIG. 4.

[0131] (Step S401) The attribute value reception unit 121 determines whether it has received a start instruction. If it has received the start instruction, it proceeds to step S402; if not, it returns to step S401.

[0132] (Step S402) The processing unit 13 performs preprocessing. An example of the preprocessing will be described using the flowchart of FIG. 5.

[0133] (Step S403) The viewpoint acquisition unit 134 determines whether to acquire a viewpoint. If it is to acquire a viewpoint, it proceeds to step S404; if not, it proceeds to step S405.

[0134] (Step S404) The viewpoint acquisition unit 134 acquires a viewpoint. An example of such viewpoint acquisition processing will be described using the flowchart of FIG. 8.

[0135] (Step S405) The idea acquisition unit 135 performs idea acquisition processing. An example of the idea acquisition processing will be described using the flowchart of FIG. 9.

[0136] (Step S406) The control unit 132 acquires from the transition management unit 111 the transition conditions for moving from the idea generation phase to the next phase. The control unit 132 determines whether the transition conditions are satisfied. If the transition conditions are satisfied, it proceeds to step S407; if not, it returns to step S405.

[0137] (Step S407) The control unit 132 refers to the transition management unit 111 and determines whether the next phase is the idea criticism phase. If it is the idea criticism phase, it proceeds to step S408; if not, it proceeds to step S410. Here, the control unit 132 stores the phase identifier of the next phase in the current management unit 114.

[0138] (Step S408) The idea criticism unit 136 acquires criticism of the idea. An example of such idea criticism processing will be described using the flowchart of FIG. 11.

[0139] (Step S409) The control unit 132 obtains, from the idea criticism phase, the transition conditions for transitioning to the next phase from the transition management unit 111, and determines whether or not the transition conditions are satisfied. If the transition conditions are satisfied, the process proceeds to step S410, and if the transition conditions are not satisfied, the process returns to step S408.

[0140] (Step S410) The idea selection unit 137 performs an idea selection process. An example of the idea selection process will be described using the flowchart of FIG. 12. Here, the control unit 132 stores the phase identifier "idea selection" of the next phase in the current management unit 114.

[0141] (Step S411) The idea output unit 142 outputs one or more ideas obtained in step S410. The process returns to step S401. Note that the idea output unit 142 transmits, for example, one or more ideas to the terminal device 2.

[0142] (Step S412) The score acquisition unit 139 acquires a score based on one or more ideas obtained in step S410.

[0143] (Step S413) The score output unit 143 outputs the score obtained in step S412. The process returns to step S401.

[0144] Note that in the flowchart of FIG. 4, the answer output unit 141 may output all or part of the answer obtained from the generation AI.

[0145] Also, in the flowchart of FIG. 4, the process ends due to a power-off or a processing end interrupt.

[0146] Next, an example of the preprocessing of step S402 will be described using the flowchart of FIG. 5.

[0147] (Step S501) The processing unit 13 acquires the theme and the like included in the start instruction. The theme and the like are, for example, a theme and one or more agent information, or a theme. The theme and the like include, for example, one or two or more idea perspectives, and one or two or more evaluation perspectives.

[0148] (Step S502) The processing unit 13 acquires one or two or more idea perspectives included in the start instruction. Here, the processing unit 13 does not necessarily have to acquire the idea perspectives.

[0149] (Step S503) The processing unit 13 acquires one or two or more evaluation perspectives included in the start instruction. Here, the processing unit 13 does not necessarily have to acquire the evaluation perspectives.

[0150] (Step S504) The agent determination unit 130 determines whether agent information exists in the information acquired in Step S501. If agent information exists, it proceeds to Step S505, and if it does not exist, it proceeds to Step S506.

[0151] (Step S505) The agent determination unit 130 acquires one or more agent information from the information acquired in Step S501. It proceeds to Step S507.

[0152] (Step S506) The agent determination unit 130 performs agent determination processing. An example of the agent determination processing will be described using the flowchart of FIG. 6.

[0153] (Step S507) The character setting unit 131 performs character setting processing. It returns to the upper-level processing. An example of the character setting processing will be described using the flowchart of FIG. 7.

[0154] In the flowchart of FIG. 5, when the start instruction does not have agent information, the agent determination unit 130 obtains agent information through agent determination processing. However, in the flowchart of FIG. 5, when the number of agent information included in the start instruction is less than or equal to the threshold value, the agent determination unit 130 may obtain agent information through agent determination processing.

[0155] Next, an example of the agent determination process in step S506 will be described with reference to the flowchart of FIG. 6.

[0156] (Step S601) The agent determination unit 130 obtains an agent determination prompt template from the prompt management unit 112.

[0157] (Step S602) The agent determination unit 130 obtains the received theme and the like.

[0158] (Step S603) The agent determination unit 130 substitutes the theme and the like obtained in step S602 into the variables of the agent determination prompt template obtained in step S601 to obtain an agent determination prompt.

[0159] (Step S604) The agent determination unit 130 passes the agent determination prompt obtained in step S603 to the generation AI.

[0160] (Step S605) The agent determination unit 130 determines whether an answer has been obtained from the generation AI. If an answer has been obtained, it proceeds to step S606; if no answer has been obtained, it returns to step S605.

[0161] (Step S606) The agent determination unit 130 obtains one or more pieces of agent information from the answer.

[0162] (Step S607) The response output unit 141 outputs one or more pieces of agent information and returns to the upper-level process. The response output unit 141 transmits, for example, one or more pieces of agent information to the terminal device 2.

[0163] Next, an example of the person setting process in step S507 will be described using the flowchart of FIG. 7.

[0164] (Step S701) The person setting unit 131 acquires a setting prompt template from the prompt management unit 112.

[0165] (Step S702) The person setting unit 131 acquires the agent information of the host. Note that the agent information of the host may be included in the start instruction or may be stored in advance in the storage unit 11.

[0166] (Step S703) The person setting unit 131 substitutes the agent information of the host acquired in step S702 into the variable of the setting prompt template acquired in step S701 to obtain the setting prompt of the host.

[0167] (Step S704) The person setting unit 131 provides the setting prompt of the host acquired in step S703 to the generation AI.

[0168] (Step S705) The person setting unit 131 substitutes 1 into the counter i.

[0169] (Step S706) The person setting unit 131 determines whether there is the i-th agent information among the acquired agent information excluding the agent information of the host. If the i-th agent information exists, it proceeds to step S707; if not, it returns to the upper-level process.

[0170] (Step S707) The person setting unit 131 acquires the i-th agent information.

[0171] (Step S708) The character setting unit 131 substitutes the i-th agent information into the variable of the setting prompt prototype, and obtains the setting prompt of the i-th agent.

[0172] (Step S709) The character setting unit 131 provides the setting prompt of the i-th agent obtained in Step S708 to the generation AI.

[0173] (Step S710) The character setting unit 131 increments the counter i by 1. Return to Step S706.

[0174] Next, an example of the viewpoint acquisition process in Step S404 will be described using the flowchart in FIG. 8.

[0175] (Step S801) The viewpoint acquisition unit 134 acquires the idea viewpoint prompt prototype from the prompt management unit 112.

[0176] (Step S802) The viewpoint acquisition unit 134 acquires information such as a theme, which is the information to be substituted into the idea viewpoint prompt prototype acquired in Step S801. The viewpoint acquisition unit 134 substitutes the theme etc. into the idea viewpoint prompt prototype and acquires the idea viewpoint prompt.

[0177] (Step S803) The viewpoint acquisition unit 134 provides the idea viewpoint prompt acquired in Step S802 to the generation AI.

[0178] (Step S804) The viewpoint acquisition unit 134 determines whether an answer has been obtained from the generation AI. If an answer has been obtained, go to Step S805; if no answer has been obtained, return to Step S804.

[0179] (Step S805) The viewpoint acquisition unit 134 acquires one or more idea viewpoints from the answer obtained from the generation AI in Step S804.

[0180] (Step S806) The answer output unit 141 outputs one or more idea perspectives acquired in step S805. The answer output unit 141 transmits one or more idea perspectives to the terminal device 2, for example.

[0181] (Step S807) The viewpoint acquiring unit 134 acquires an evaluation viewpoint prompt template from the prompt managing unit 112.

[0182] (Step S808) The viewpoint acquiring unit 134 acquires a theme or the like, which is information to be substituted into the evaluation viewpoint prompt template acquired in step S807. The viewpoint acquiring unit 134 assigns the theme or the like to the evaluation viewpoint prompt template and acquires an evaluation viewpoint prompt.

[0183] (Step S809) The viewpoint acquisition unit 134 provides the evaluation viewpoint prompt acquired in step S808 to the generation AI.

[0184] (Step S810) The viewpoint acquisition unit 134 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S811, and if an answer has not been acquired, the process returns to step S810.

[0185] (Step S811) The viewpoint acquisition unit 134 acquires one or more evaluation viewpoints from the answer acquired from the generation AI in step S810.

[0186] (Step S812) The answer output unit 141 outputs the one or more evaluation criteria acquired in step S811. The answer output unit 141 transmits the one or more evaluation criteria to the terminal device 2, for example.

[0187] Next, an example of the idea acquisition process in step S405 will be described with reference to the flowchart in FIG.

[0188] (Step S901) The idea acquiring unit 135 acquires an idea generation prompt template from the prompt managing unit 112.

[0189] (Step S902) The idea acquisition unit 135 assigns 1 to the counter i.

[0190] (Step S903) The idea acquisition unit 135 determines whether the i-th agent excluding the moderator exists. If the i-th agent exists, it proceeds to step S904; if the i-th agent does not exist, it proceeds to step S911. Note that whether the i-th agent exists is determined by whether the i-th agent information exists.

[0191] (Step S904) The idea acquisition unit 135 acquires the i-th agent information.

[0192] (Step S905) The idea acquisition unit 135 substitutes part or all of the i-th agent information into the variables of the idea presentation prompt template, and obtains an idea presentation prompt for the i-th agent.

[0193] (Step S906) The idea acquisition unit 135 provides the idea presentation prompt obtained in step S905 to the generation AI.

[0194] (Step S907) The idea acquisition unit 135 determines whether it has obtained an answer from the generation AI. If it has obtained an answer, it proceeds to step S908; if it has not obtained an answer, it returns to step S907.

[0195] (Step S908) The idea acquisition unit 135 obtains one or more ideas from the answer obtained in step S907.

[0196] (Step S909) The idea output unit 142 outputs the one or more ideas obtained in step S908. The idea output unit 142 transmits, for example, one or more ideas to the terminal device 2.

[0197] (Step S910) The idea acquisition unit 135 increments the counter i by 1. It returns to step S903.

[0198] (Step S911) The idea acquisition unit 135 determines whether to accept the input of ideas from people. If accepting the input of ideas from people, it proceeds to step S912; if not, it returns to the upper-level process.

[0199] (Step S912) The idea acquisition unit 135 substitutes 1 for the counter i.

[0200] (Step S913) The idea acquisition unit 135 determines whether the i-th person who inputs an idea exists. If the i-th person exists, it proceeds to step S914; if not, it returns to the upper-level process.

[0201] (Step S914) The idea acquisition unit 135 determines whether it has received one or more ideas from people. If it has received ideas, it proceeds to step S915; if not, it returns to step S914. Here, in the case of a timeout, it may also proceed to S919. Also, the acceptance of ideas from people is, for example, the reception of ideas from the terminal device 2.

[0202] (Step S915) The analysis unit 138 analyzes one or more ideas received in step S914. An example of such idea analysis processing will be described using the flowchart of FIG. 10.

[0203] (Step S916) The idea acquisition unit 135 determines whether the analysis result in step S915 is "error". If it is "error", it proceeds to step S918; if not, it proceeds to step S917.

[0204] (Step S917) The idea acquisition unit 135 acquires one or more ideas received in step S914.

[0205] (Step S918) The error output unit 144 outputs an error message. The error output unit 144 transmits the error message to, for example, the terminal device 2 that has transmitted one or more ideas.

[0206] (Step S919) The idea acquisition unit 135 increments the counter i by 1. It returns to step S913.

[0207] Next, an example of the idea analysis process in step S915 will be described using the flowchart of FIG. 10.

[0208] (Step S1001) The analysis unit 138 acquires an idea analysis prompt template from the prompt management unit 112.

[0209] (Step S1002) The analysis unit 138 substitutes 1 for the counter i.

[0210] (Step S1003) The analysis unit 138 determines whether the i-th idea exists. If the i-th idea exists, it proceeds to step S1004; if not, it returns to the upper-level process.

[0211] (Step S1004) The analysis unit 138 acquires the i-th idea.

[0212] (Step S1005) The analysis unit 138 substitutes the i-th idea into the idea analysis prompt template acquired in step S1001 to obtain an idea analysis prompt.

[0213] (Step S1006) The analysis unit 138 passes the idea analysis prompt acquired in step S1005 to the generation AI.

[0214] (Step S1007) The analysis unit 138 determines whether it has obtained an answer from the generation AI. If it has obtained an answer, it proceeds to step S1008; if not, it returns to step S1007.

[0215] (Step S1008) The analysis unit 138 obtains an analysis result (e.g., "normal" or "error") from the response obtained in step S1007 and associates it with the i-th idea.

[0216] (Step S1009) The analysis unit 138 increments the counter i by 1. Return to step S1003.

[0217] Next, an example of the idea criticism process in step S408 will be described using the flowchart in FIG. 11.

[0218] (Step S1101) The idea criticism unit 136 obtains an idea criticism prompt template from the prompt management unit 112.

[0219] (Step S1102) The idea criticism unit 136 assigns 1 to the counter i.

[0220] (Step S1103) The idea criticism unit 136 determines whether the i-th idea to be criticized exists. If the i-th idea exists, go to step S1104; if not, return to the upper-level process.

[0221] (Step S1104) The idea criticism unit 136 assigns 1 to the counter j.

[0222] (Step S1105) The idea criticism unit 136 determines whether the j-th agent exists. If the j-th agent exists, go to step S1106; if not, go to step S1113.

[0223] (Step S1106) The idea criticism unit 136 obtains the j-th agent information.

[0224] (Step S1107) The idea criticism unit 136 substitutes part or all of the i-th idea and the j-th agent information into the idea criticism prompt template obtained in step S1101 to obtain an idea criticism prompt.

[0225] (Step S1108) The idea criticism unit 136 passes the idea criticism prompt obtained in step S1107 to the generation AI.

[0226] (Step S1109) The idea criticism unit 136 determines whether an answer has been obtained from the generation AI. If an answer has been obtained, it proceeds to step S1110; if not, it returns to step S1109.

[0227] (Step S1110) The idea criticism unit 136 obtains one or more criticisms from the answer from the generation AI obtained in step S1109.

[0228] (Step S1111) The answer output unit 141 outputs one or more criticisms obtained in step S1110 in association with the i-th idea.

[0229] (Step S1112) The idea criticism unit 136 increments the counter j by 1. It returns to step S1105.

[0230] (Step S1113) The idea criticism unit 136 increments the counter i by 1. It returns to step S1103.

[0231] Next, an example of the idea selection process in step S410 will be described using the flowchart in FIG. 12.

[0232] (Step S1201) The idea selection unit 137 obtains an idea selection prompt template from the prompt management unit 112.

[0233] (Step S1202) The idea selection unit 137 obtains the ideas obtained by the idea acquisition unit 135, or the ideas obtained by the idea acquisition unit 135 and the ideas received by the idea reception unit 122. It is preferable for the idea selection unit 137 to obtain one or more criticisms obtained by the idea criticism unit 136.

[0234] (Step S1203) The idea selection unit 137 substitutes two or more ideas, or two or more ideas and one or more criticisms, into the idea selection prompt prototype obtained in Step S1201 to obtain an idea selection prompt.

[0235] (Step S1204) The idea selection unit 137 passes the idea selection prompt obtained in Step S1203 to the generative AI.

[0236] (Step S1205) The idea selection unit 137 determines whether an answer has been obtained from the generative AI. If an answer has been obtained, it proceeds to Step S1206; if no answer has been obtained, it returns to Step S1205.

[0237] (Step S1206) The idea selection unit 137 obtains one or more ideas from the answer obtained in Step S1205. It returns to the upper-level process. Here, it is preferable for the idea selection unit 137 to obtain two or more ranked ideas.

[0238] Next, a specific operation example of the information system A in this embodiment will be described.

[0239] Currently, a transition management table shown in FIG. 13 is stored in the transition management unit 111 of the creation support device 1. The transition management table is a table that manages the transition of phases for idea creation. The transition management table manages two or more records having "ID", "phase identifier", "transition condition", and "next phase identifier". "ID" is information for identifying a record. The combination of "transition condition" and "next phase identifier" indicates that when the transition condition is met in the current phase identified by the "phase identifier", the process transitions to the next phase indicated by the next phase identifier.

[0240] In FIG. 13, when the idea score and evaluation score included in the start instruction satisfy the transition condition of "ID = 1", the "Idea Perspective and Evaluation Perspective Consideration" phase is skipped.

[0241] In the record of "ID=2" in FIG. 13, two sets of "transition conditions" and "next phase identifier" are associated with one phase identifier, "idea generation". That is, the record of "ID=2" indicates that it transitions to different next phases according to the matching transition conditions from the phase "idea generation". The record of "ID=2" indicates that it can branch in the phase transition.

[0242] In addition, the prompt management unit 112 stores a prompt management table shown in FIG. 14. The prompt management table is a table for managing prompt templates. The prompt management table manages a large number of records having "prompt template identifier" and "prompt template". The "prompt template identifier" may be associated with each phase identifier. The "idea perspective prompt template" and the "evaluation perspective prompt template" are associated with the phase identifier "idea perspective and evaluation consideration". The "idea generation prompt template" is associated with the phase identifier "idea generation". The "idea criticism prompt template" is associated with the phase identifier "idea criticism". The "idea selection prompt template" is associated with the phase identifier "idea selection". The "idea generation prompt template" has variables <idea perspective> and <evaluation perspective>, but may not have the variable <evaluation perspective>. The "idea criticism prompt template" may have the variable <evaluation perspective>. In such a case, the "idea criticism prompt template" is, for example, "You are <name>. Regarding <theme>, please list the issues and problems of the idea '<idea>' in consideration of the following idea evaluation perspectives. [evaluation perspective] <evaluation perspective>".

[0243] In the above situation, user U wants to create an idea about "a solution using AI and a camera" together with two or more agents of the idea generation AI, and inputs a start instruction including "<Theme> Solution using AI and a camera <Agent><Name> Mr. A <Agent Name> AI Engineer <Role> Utilize AI-related technologies to promote the use of AI in ideas and products and enhance problem-solving capabilities. <Persona> ['Having deep knowledge and experience in AI technologies such as machine learning, deep learning, and natural language processing.', 'Proficient in preprocessing of datasets, training and evaluation of models, and deployment of AI solutions.', 'Having an awareness of developing while considering the ethical aspects and social impacts of AI.']< / Agent>" into terminal device 2.

[0244] Next, terminal device 2 receives the start instruction and transmits the start instruction to creation support device 1.

[0245] Next, reception unit 12 of creation support device 1 receives the start instruction. Next, processing unit 13 performs preprocessing as follows.

[0246] That is, the processing unit 13 acquires the theme "Solutions Utilizing AI and Cameras" included in the start instruction. Also, the processing unit 13 attempts to acquire the idea perspective and evaluation perspective from the start instruction but fails to do so. Next, the agent determination unit 130 acquires an agent determination prompt template from the prompt management table (Fig. 14). The agent determination unit 130 acquires, from the start instruction, the theme and "<agent><name>Mr. <agent name>AI Engineer...< / agent>". Then, the agent determination unit 130 substitutes "Solutions Utilizing AI and Cameras" into the variable <theme> of the agent determination prompt template, substitutes "AI Engineer" of <agent name> into the variable <user-specified agent>, and acquires the agent determination prompt. Next, the agent determination unit 130 passes the agent determination prompt to the generating AI. Next, the agent determination unit 130 acquires an answer from the generating AI and acquires one or more pieces of agent information from the answer. Here, it is assumed that the agent determination unit 130 has acquired the agent information of "Data Scientist" and "Sales" (see Fig. 15). That is, the agent determination unit 130 has acquired the "AI Engineer" given by the user U and the agent information of "Data Scientist" and "Sales", which is the answer from the generating AI.

[0247] Next, the character setting unit 131 performs character setting processing according to the processing described using the flowchart of Fig. 7 as follows. That is, the character setting unit 131 acquires a setting prompt template from the prompt management table (Fig. 14). The character setting unit 131 substitutes <name><agent name><role><persona> into the setting prompt template from each of the agent information input by the user U and the agent information acquired by the agent determination unit 130, acquires a setting prompt for each character, and passes the setting prompt to the generating AI. As a result, the character settings of AI Engineer, Data Science, and Sales are completed. Also, the character setting unit 131 acquires the agent information of the emcee in the storage unit 11, performs the same processing, and performs the character setting of the emcee. Thus, the preprocessing is completed.

[0248] Next, since the start instruction does not include an idea perspective and an evaluation perspective, the perspective acquisition unit 134 determines that the idea perspective acquisition condition (the number of idea perspectives included in the start instruction <= threshold a) is satisfied and the evaluation perspective acquisition condition (the number of evaluation perspectives included in the start instruction <= threshold b) is satisfied. Then, the perspective acquisition unit 134 acquires an idea perspective prompt template from the prompt management table (Fig. 14). The perspective acquisition unit 134 acquires <theme> and <input idea perspective> to be substituted into the idea perspective prompt template. Here, <input idea perspective> is not acquired. The perspective acquisition unit 134 substitutes the theme into the idea perspective prompt template to obtain an idea perspective prompt. ) The perspective acquisition unit 134 provides the generated AI with the idea perspective prompt. Then, for example, the perspective acquisition unit 134 is assumed to have obtained "entry market" and "technological innovation" as idea perspectives.

[0249] Also, the perspective acquisition unit 134 acquires an evaluation perspective prompt template from the prompt management table (Fig. 14). The perspective acquisition unit 134 acquires <theme> and <input evaluation perspective> to be substituted into the evaluation perspective prompt template. Here, <input evaluation perspective> is not acquired. The perspective acquisition unit 134 substitutes the theme into the evaluation perspective prompt template to obtain an evaluation perspective prompt. ) The perspective acquisition unit 134 provides the generated AI with the evaluation perspective prompt. Then, for example, the perspective acquisition unit 134 is assumed to have obtained "technical feasibility", "user convenience", and "market needs" as evaluation perspectives.

[0250] Next, the idea acquisition unit 135 performs the idea acquisition process described using the flowchart of FIG. 9 as follows. That is, the idea acquisition unit 135 acquires an idea prompt template from the prompt management table (FIG. 14). Also, the idea acquisition unit 135 acquires the names "Mr. A, Mr. S, Mr. X" that are the agent information other than the host among the acquired agent information. Also, the idea acquisition unit 135 acquires the theme "Solutions using AI and cameras". Also, the idea acquisition unit 135 acquires the acquired idea perspectives "Entry market", "Innovation of technology", and the evaluation perspectives "Technical feasibility", "Convenience for users", "Market needs". Next, the idea acquisition unit 135 substitutes "name", "theme", "idea perspective", and "evaluation perspective" into each variable of the idea prompt template for each of the three names, and acquires three idea prompts. Then, the idea acquisition unit 135 gives the three idea prompts to the generation AI and acquires an answer from the generation AI. Next, the idea acquisition unit 135 acquires ideas from each of the three answers. As a result, it is assumed that the idea acquisition unit 135 has acquired "Smart assist glasses", "AI-driven traffic monitoring system", and "Personalized retail experience system".

[0251] Next, the output unit 14 sequentially transmits the prompts and ideas obtained from the answers to the terminal device 2.

[0252] Next, the terminal device 2 receives and outputs the prompts, answers, etc. transmitted from the creation support device 1. An example of such output is shown in FIG. 16.

[0253] Note that the phase identifier "Idea generation" is stored in the current management unit 114 of the creation support device 1. That is, in the process of creating ideas, the current phase is "Idea generation". And as shown in 1601 of FIG. 16, the output unit 14 transmits the answer (ideas, etc.) passed from the generation AI in a manner that can grasp the current "Idea generation" identified by the current identifier.

[0254] Next, the idea acquisition unit 135 determines that there is a first person who inputs an idea. Then, the output unit 14 transmits screen information prompting the user U to input an idea to the terminal device 2 of the user U.

[0255] Next, the terminal device 2 of the user U receives and outputs the screen information. An example of such output is shown in FIG. 17. Then, it is assumed that the user U substitutes an idea such as "customer estimation smart cash register system" into the field 1701 for inputting an idea and presses the send button 1702.

[0256] Next, the idea acquisition unit 135 receives an idea such as "customer estimation smart cash register system" from the terminal device 2. Next, it is assumed that the analysis unit 138 analyzes one or more ideas received from the user and determines that they are "normal". As a result, the idea acquisition unit 135 acquires the received idea such as "customer estimation smart cash register system".

[0257] Next, the control unit 132 acquires two transition conditions for moving to the next phase from the idea-giving phase from the transition management table. Then, the control unit 132 acquires the number of ideas "4", which is a parameter of the transition condition. Also, the control unit 132 acquires "there is a person's idea". Next, the control unit 132 determines that neither of the two transition conditions is satisfied.

[0258] Then, it is assumed that the idea acquisition unit 135 acquires idea-giving prompts requested from each of Mr. A, Mr. S, and Mr. X by the emcee, passes each prompt to the generation AI, and obtains an answer. Next, it is assumed that the idea acquisition unit 135 acquires ideas "smart security monitoring system", "AI-driven real-time traffic optimization system", and "AI-driven personal shopping assistant" from each of the three answers, respectively.

[0259] Also, the output unit 14 transmits the ideas obtained from the prompts given to the generation AI and the answers to the terminal device 2.

[0260] Next, the terminal device 2 receives and outputs the prompt given to the generation AI. Also, the terminal device 2 receives and outputs ideas.

[0261] Next, the control unit 132 obtains, from the transition management table (Fig. 14), two transition conditions for moving to the next phase from the idea generation phase. Assume that the number of ideas "7" obtained satisfies the transition condition "number of ideas >= x3". That is, "x3" is a natural number less than or equal to 7.

[0262] Next, the control unit 132 refers to the transition management table and obtains the next phase identifier "idea criticism" that pairs with the transition condition "number of ideas >= x3".

[0263] Then, the control unit 132 updates the current of the current management unit 114 to "idea criticism".

[0264] Next, the idea criticism unit 136 performs the idea criticism process described using the flowchart of FIG. 11. That is, the idea criticism unit 136 acquires an idea criticism prompt template from the prompt management table (FIG. 14). Also, the idea criticism unit 136 acquires the names "Mr. A, Mr. S, Mr. X" that each agent information has. Also, the idea criticism unit 136 acquires the theme "Solution using AI and camera". Also, the idea criticism unit 136 acquires the seven ideas that have been acquired. The idea criticism unit 136 substitutes "name", "theme", and "idea" into the idea criticism prompt template for each idea and for each agent's name, and acquires an idea criticism prompt. For example, the idea criticism unit 136 acquires the idea criticism prompt "You are Mr. A. Please list the problems and issues of the idea'smart assist glasses' regarding the'solution using AI and camera'." Next, the idea criticism unit 136 passes each idea criticism prompt to the generation AI. The output unit 14 transmits the prompt given to the generation AI to the terminal device 2. Also, the idea criticism unit 136 acquires an answer from the generation AI. The idea criticism unit 136 acquires one or more criticisms from the answer from the generation AI. The output unit 14 transmits the one or more criticisms acquired to the terminal device 2. The output unit 14 transmits the one or more criticisms passed from the generation AI in a manner that can grasp the current identified by the current identifier.

[0265] The terminal device 2 receives and outputs the idea criticism prompt. Also, the terminal device 2 receives and outputs one or more criticisms for each idea and for each agent's name. An example of such output is shown in FIG. 18. 1801 in FIG. 18 is the criticism of "Mr. A" for the idea "smart assist glasses". Also, in FIG. 18, it is clearly shown that the current is "idea criticism" (1802).

[0266] In the idea criticism phase, the above operations are repeated for each idea and for each agent.

[0267] Next, the control unit 132 obtains from the idea criticism phase the transition condition "number of criticisms >= x5" for transitioning to the next phase from the transition management table (Fig. 13), and determines that the said transition condition is satisfied. Assume that the control unit 132 has obtained the number of criticisms "21" and determines that it satisfies "number of criticisms >= x5".

[0268] Next, the idea selection unit 137 performs the idea selection process described using the flowchart in Fig. 12. That is, the idea selection unit 137 obtains the idea selection prompt template from the prompt management table (Fig. 14). The idea selection unit 137 obtains all the ideas acquired by the idea acquisition unit 135 and the ideas received by the idea reception unit 122. The set of such ideas is, here, the seven "smart assist glasses", "AI-driven traffic monitoring system", "personalized retail experience system", "customer estimation smart cash register system", "smart security monitoring system", "AI-driven real-time traffic optimization system", and "AI-driven personal shopping assistant". Also, the idea selection unit 137 obtains the 21 criticisms acquired. Next, the idea selection unit 137 substitutes the seven ideas into the variable <idea set> of the idea selection prompt template, substitutes the 21 criticisms acquired into the variable <previously given criticisms>, and obtains the idea selection prompt. Next, the idea selection unit 137 passes the idea selection prompt to the generation AI. Then, the idea selection unit 137 obtains an answer from the generation AI. Next, the idea selection unit 137 obtains one or more ideas from the answer. Here, the idea selection unit 137 obtains the seven ranked ideas from the answer.

[0269] The output unit 14 transmits the idea selection prompt to the terminal device 2. Also, the idea output unit 142 transmits the information of the seven ranked ideas acquired by the idea selection unit 137 to the terminal device 2.

[0270] The terminal device 2 receives and outputs an idea selection prompt. Also, the terminal device 2 receives and outputs information on seven ranked ideas. An example of such output is shown in FIG. 19. In FIG. 19, the idea selection prompt is 1901, and the information on the seven ranked ideas is 1902. Also, in FIG. 19, it is clearly shown that the current is "idea selection" (1903).

[0271] As described above, according to the present embodiment, it is possible to assist in creating appropriate ideas using the generation AI.

[0272] Also, according to the present embodiment, it is possible to assist in creating appropriate ideas through cooperation between a person and the generation AI.

[0273] Also, according to the present embodiment, inappropriate human inputs can be excluded. Further, according to the present embodiment, when there is an inappropriate human input, it is possible to notify the person that the input is inappropriate.

[0274] Also, according to the present embodiment, the emcee agent can assist in creating more appropriate ideas using the generation AI.

[0275] Also, according to the present embodiment, an appropriate prompt by the emcee agent can be given to the generation AI at an appropriate timing.

[0276] Furthermore, according to the present embodiment, it is possible to clearly present the flow of discussion for creating appropriate ideas using the generation AI.

[0277] In addition, in the present embodiment, as described above, the score acquisition unit 139 acquires the scores of each of the one or more ideas acquired by the idea acquisition unit 135 or the idea selection unit 137, and the output unit 14 may output the scores of the respective ideas. For example, when the theme is "New planning ideas for soft drinks", the idea acquisition unit 135 acquires five ideas, "Tropical Coconut (Expected to grow due to the increasing inbound demand)", "Refresh Sadistic (Demand is expected to increase due to the nutritional deficiency of the younger generation)", "Refreshing Grapefruit (Demand is expected to increase as the aging progresses)", "Secret Orange (Expected to grow from the increasing popularity of e-sports)", "Anonymous Grape (The office population is at an all-time high, but differentiating from other companies is an issue)" by the above-described processing. Next, the idea criticism unit 136 acquires one or more criticisms for each of the five ideas and for each evaluation perspective by the above-described processing. Next, the score acquisition unit 139 ranks each of the five ideas for each evaluation perspective by the above-described processing. Here, it is assumed that the evaluation perspectives are three: "market size", "growth potential", and "barriers to entry". And the score acquisition unit 139 acquired the rankings of the five ideas in each of the three perspectives as follows. 1. Market size 1st place: Refresh Sadistic (The market for nutritional supplements for the younger generation is about 300 billion yen, the largest) 2nd place: Refreshing Grapefruit (The market for beverages for the elderly is about 80 billion yen, relatively large)? 3rd place: Anonymous Grape (The market for office drinking water is 110 billion yen, medium scale) 4th place: Tropical Coconut (The specific market size of beverages for resort areas is unknown) 5th place: Secret Orange (The e-sports related market is 143 billion yen, relatively small) 2. Growth potential 1st place: Tropical Coconut (Expected to grow due to the increasing inbound demand) 2nd place: Refresh Sadistic (Demand is expected to increase due to the nutritional deficiency of the younger generation) 3rd place: Refreshing Grapefruit (Demand is expected to increase as the aging progresses) 4th Secret Orange (Expected to grow due to the increasing popularity of e-sports) 5th Anonymous Grape (The office population is at an all-time high, but differentiation from other companies is an issue) 3. Barriers to entry? 1st Anonymous Grape (There are many plain PET bottle products of the same kind on the market) 2nd Refreshing Sadistic (Many manufacturers have already entered, and it is difficult to differentiate) 3rd Tropical Coconut (Stable supply is an issue due to seasonal and regional demand fluctuations) 4th Refreshing Grapefruit (A market where large manufacturers have already actively entered) 5th Secret Orange (Although there are similar products, there is still room for new entry)

[0278] Next, the score acquisition unit 139 calculates the score of each evaluation perspective of each idea using the above-mentioned arithmetic formula "Score for each evaluation perspective = (100 * (number of ideas - rank)) / (number of evaluation perspectives * (number of ideas - 1))". Next, the score acquisition unit 139 calculates the sum of the scores of the three evaluation perspectives for each of the five scores and ranks them. Then, the output unit outputs the ranks and scores (total scores) of the five ideas as follows in the "Overall Evaluation". Overall Evaluation 1st Refreshing Sadistic 33.3 + 25.0 + 25.0 = 83.3 2nd Tropical Coconut 8.3 + 33.3 + 16.6 = 58.2 3rd Refreshing Grapefruit 25.0 + 16.6 + 8.3 = 49.9 4th Anonymous Grape 16.6 + 0.0 + 33.3 = 49.9 5th Secret Orange 0.0 + 8.3 + 0.0 = 8.3

[0279] Note that for the scores in each evaluation perspective, the 1st place is 33.3 points, the 2nd place is 25.0 points, the 3rd place is 16.6 points, the 4th place is 8.3 points, and the 5th place is 0.0 points.

[0280] In addition, the processing in this embodiment may be realized by software. And this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and distributed. Note that this also applies to other embodiments in this specification. The software that realizes the idea creation support device 1 in this embodiment is a program as follows. That is, this program includes a setting prompt template for configuring prompts for setting the characters of one or more agents, and a phase prompt template for configuring prompts to be given to the generation AI in two or more phases including an idea generation phase and an idea selection phase, and a prompt management unit in which the phase prompt template is stored, and a computer that can access an attribute value storage unit in which one or more idea attribute values, which are attribute values regarding the ideas to be created, are stored. A program for functioning as a character setting unit that acquires one or more setting prompts using the setting prompt template and gives the one or more setting prompts to the generation AI, an idea acquisition unit that acquires a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values and gives the prompt to each of the one or more agents of the generation AI to acquire two or more ideas, an idea selection unit that acquires a prompt using the phase prompt template corresponding to the idea selection phase and the two or more ideas acquired by the idea acquisition unit, gives the prompt to the generation AI, and acquires one or more ideas selected based on the two or more ideas acquired by the idea acquisition unit, and an idea output unit that outputs the one or more ideas acquired by the idea selection unit.

[0281] (Embodiment 2) In this embodiment, a creation support device that performs processing for changing the flow of discussion, detailed content of the discussion, etc. when the discussion change conditions are met will be described. Note that the processing for changing the flow of discussion, detailed content of the discussion, etc. is, for example, a speaking order change process for changing the speaking order of two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea reacquisition process for giving a prompt to one or more agents again to acquire ideas.

[0282] In this embodiment, a creation support device that determines a person's rank based on the ideas put forward by the person will be described.

[0283] In this embodiment, a creation support device that automatically determines the speaking order of agents will be described.

[0284] The conceptual diagram of information system B in this embodiment is the same as FIG. 1 except for the reference numerals of the creation support device. Information system B includes a creation support device 4, one or two or more terminal devices 2, and one or two or more generation AI devices 3.

[0285] The creation support device 4 is, for example, a cloud server or an ASP server, but its type does not matter. Note that the creation support device 4 may have one or two or more generation AIs. In such a case, information system B may not have a generation AI device 3.

[0286] The creation support device 4 and one or two or more terminal devices 2, and the creation support device 4 and one or two or more generation AI devices 3 can communicate with each other via a network such as the Internet.

[0287] FIG. 20 is a block diagram of the creation support device 4 that constitutes information system B in this embodiment.

[0288] The idea creation support device 4 includes a storage unit 41, a reception unit 42, a processing unit 43, and an output unit 44. The storage unit 41 includes a transition management unit 111, a prompt management unit 412, an attribute value storage unit 113, a current management unit 114, and a human resource management unit 411. The reception unit 42 includes an attribute value reception unit 121, an idea reception unit 122, and an additional instruction reception unit 421. The processing unit 43 includes an agent determination unit 130, a person setting unit 131, a speaking order determination unit 431, a control unit 132, a master of ceremony determination unit 133, a viewpoint acquisition unit 134, an idea acquisition unit 135, an idea criticism unit 136, an idea selection unit 137, an analysis unit 138, a score acquisition unit 139, a determination unit 432, a discussion change unit 433, an additional instruction unit 434, an evaluation unit 435, a ranking unit 436, and a reward processing unit 437. The output unit 44 includes a response output unit 141, an idea output unit 142, a score output unit 143, an error output unit 144, an evaluation output unit 441, and a rank output unit 442.

[0289] Various types of information are stored in the storage unit 41 that constitutes the idea creation support device 4. The various types of information are, for example, transition information, various types of prompt templates, idea attribute values, current identifiers, and human resource information described later.

[0290] One or more pieces of human resource information are stored in the human resource management unit 411. The human resource information is information about candidates who can come up with ideas. The candidates can be proposers who come up with ideas. The candidates or proposers can simply be referred to as people. The human resource information has, for example, one or more pieces of theme information and a person identifier. The human resource information may have notification destination information, points, ranks, account information, and electronic money information.

[0291] The theme information is information about themes on which candidates can come up with ideas. The theme information can be a theme, or can be keywords indicating the field of the theme, the characteristics of the theme, etc. The theme information can be any information related to the theme.

[0292] The person identifier is information for identifying a person. The person identifier is, for example, the ID of the candidate, email address, phone number, or name.

[0293] The notification destination information is information for specifying the notification destination. The notification destination information is, for example, the candidate's ID, email address, or phone number. The notification destination information may be the same as the person identifier.

[0294] Points are points held by a person. The points may be rewards. The points may also be the cumulative points given so far.

[0295] Rank is information indicating a person's rank. The rank may be, for example, five levels or three levels. The five-level rank is represented by a natural number from "1" to "5", for example. The three-level rank is, for example, any one of "A", "B", and "C".

[0296] Account information is information for paying a person a reward (for example, money). The account information is, for example, bank account information (for example, bank name, account number, etc.). The account information may be considered to include electronic money information. The electronic money information has a user ID of electronic money (for example, Paypay (registered trademark)).

[0297] The prompt management unit 412 stores a setting prompt template and a phase prompt template. The phase prompt template stored in the prompt management unit 412 here may be only the phase prompt template corresponding to the idea generation phase. That is, in this embodiment, the phase may be only the idea generation phase.

[0298] The prompt management unit 412 may store a prompt template for determining the speaking order. The prompt template for determining the speaking order is a prompt template for obtaining a prompt for determining the speaking order of two or more parties. The prompt template for determining the speaking order may be a prompt template for obtaining a prompt for determining the speaking order of two or more parties participating in idea generation, including one or more people and one or more agents. The prompt template for determining the speaking order has, for example, one or more variables. The variables are, for example, variables into which a theme is substituted, and variables into which two or more parties are substituted. That is, the prompt for determining the speaking order has information on the theme and two or more parties. Here, a party is a person who generates ideas and can be an agent or a person. The information on the party has, for example, information indicating the role of the party, and attribute values of the party (for example, job title, age, gender, department, specialty, and expertise).

[0299] The prompt management unit 412 may store the same prompt template as the prompt management unit 112.

[0300] The reception unit 42 receives various instructions and information. The various instructions and information are, for example, one or more idea attribute values, one or more ideas, a start instruction, additional instructions described later, and a discussion change instruction.

[0301] The discussion change instruction is an instruction to change the discussion. The discussion change instruction is, for example, an instruction to change the speaking order of the agent, an instruction to give new information to the generative AI, and an instruction to make the agent generate ideas again. Here, the new information is, for example, a new perspective or detailed information on the theme.

[0302] The additional instruction reception unit 421 receives additional instructions. The additional instruction reception unit 421 receives additional instructions from a person. The additional instructions are usually information constituting a prompt to be given to the generative AI. The content of the additional instructions is not limited. The additional instructions are, for example, information thought up by a person and information that can be changed by the output ideas or the like. The additional instructions may be the new information described above.

[0303] Here, reception generally refers to the reception of information transmitted via a wired or wireless communication line, but may also include concepts such as the reception of information input from input devices such as keyboards, mice, touch panels, etc., and the reception of information read from recording media such as optical disks, magnetic disks, semiconductor memories, etc.

[0304] The processing unit 43 performs various processes. The various processes are, for example, processes performed by the agent determination unit 130, the person setting unit 131, the speech order determination unit 431, the control unit 132, the emcee determination unit 133, the viewpoint acquisition unit 134, the idea acquisition unit 135, the idea criticism unit 136, the idea selection unit 137, the analysis unit 138, the score acquisition unit 139, the determination unit 432, the discussion change unit 433, the additional instruction unit 434, the evaluation unit 435, the ranking unit 436, or the reward processing unit 437.

[0305] The speech order determination unit 431 determines the speech order of agents corresponding to two or more setting prompts. The speech order determination unit 431 may, for example, determine the speech order of two or more parties involved in idea generation, including a person and one or more agents.

[0306] The speech order determination unit 431, for example, acquires a speech order determination prompt using a speech order determination prompt template for determining the speech order of two or more agents, gives the speech order determination prompt to the generation AI, and determines the speech order of agents corresponding to two or more setting prompts.

[0307] The speech order determination unit 431 may determine the speech order only when the order determination conditions are satisfied. The order determination conditions are, for example, that the number of agents is equal to or greater than a threshold value, that a person is included in the parties involved in idea generation, or that a person is not included in the parties involved in idea generation.

[0308] The determination unit 432 determines whether it meets the discussion change conditions. The discussion change conditions are, for example, conditions related to ideas and conditions related to the time until an idea is accepted. The conditions related to ideas are, for example, conditions related to the ideas acquired by the idea acquisition unit 135 and conditions related to the ideas accepted by the idea reception unit 122. The discussion change conditions are, for example, that a discussion change instruction has been received.

[0309] The determination unit 432 determines, for example, whether the ideas acquired by the idea acquisition unit 135, one or more ideas accepted by the idea reception unit 122, the time until the idea reception unit 122 accepts one or more ideas from a person, or the received instruction meets the discussion change conditions. Note that the received instruction that meets the discussion change conditions is a discussion change instruction.

[0310] The discussion change conditions are, for example, that the total number of ideas acquired by the idea acquisition unit 135 is less than or equal to a threshold value, the inspection result of the ideas accepted by the idea reception unit 122 is an error, the time is longer than or equal to a threshold value since the start of accepting ideas from a person, or the idea reception unit 122 has not accepted any ideas. The discussion change conditions are, for example, that a discussion change instruction input by a person from the terminal device 2 has been received. Note that the discussion change instruction input by a person is, for example, an instruction for a button on the screen displayed on the terminal device 2. The button is, for example, a button for inputting an additional instruction. Due to the button instruction, for example, a screen for inputting an additional instruction is displayed on the terminal device 2.

[0311] When the determination unit 432 determines that it meets the discussion change conditions, the discussion change unit 433 performs a discussion change process, which is a process for changing the discussion. The discussion change process is, for example, a process for changing the speaking order, an additional instruction input process, an idea re-acquisition process, and a phase change process.

[0312] The speaking order change process is a process of changing the speaking order of two or more parties. The speaking order change process may include a process of removing one or two or more parties (for example, people) from the parties who come up with ideas. The speaking order change process is, for example, moving the person who input an idea that results in an error to the last speaker (party), or removing the person who input an idea that results in an error from the parties. The speaking order change process may also be an agent addition process of adding an agent with a new position. The agent addition process is, for example, giving an agent addition prompt to a generative AI, obtaining information on a new agent, and performing the above-described person setting process using the information. Note that the agent addition prompt is, for example, "Please introduce an agent necessary to come up with even better ideas."

[0313] The additional instruction input process is a process for having a person input an additional instruction. The additional instruction input process is, for example, a process of obtaining screen information for having a person input an additional instruction and transmitting the screen information to the terminal device 2 of the person.

[0314] The idea re-acquisition process is a process of giving a prompt to one or two or more agents again to acquire ideas.

[0315] The phase change process is a process of changing the current phase to another phase. The phase change process is, for example, a process of changing a current identifier to a different phase identifier. The phase change process is, for example, a process of skipping a specific phase (for example, an idea selection phase, an idea criticism phase).

[0316] The discussion change unit 433 performs, for example, an idea re-acquisition process of giving a prompt corresponding to the idea generation phase to a generative AI to acquire ideas again. The idea re-acquisition process may be a process of giving one or more ideas acquired by the idea acquisition unit 135 or one or more ideas received by the idea reception unit 122 to the generative AI and giving a prompt corresponding to the idea generation phase to the generative AI to acquire ideas again.

[0317] The additional instruction unit 434 passes a prompt with additional instructions to the generation AI. The prompt with additional instructions is, for example, a prompt including additional viewpoints or a prompt including more detailed information about the theme.

[0318] The evaluation unit 435 obtains evaluation information that is an evaluation of the ideas received by the idea reception unit 122 from the proposers.

[0319] The evaluation information is information regarding the evaluation of the ideas. The evaluation information is information that specifies the evaluation of the ideas. The evaluation information is, for example, an evaluation value, information indicating whether an idea is good or bad, or a score of the idea. That is, the evaluation unit 435 may be a score acquisition unit 139. The score acquisition unit 139 may obtain a score for the ideas received by the idea reception unit 122 through the above-described processing.

[0320] The evaluation unit 435 obtains, for example, evaluation information that is a score for an idea when the idea received by the idea reception unit 122 is selected by the idea selection unit 137.

[0321] The evaluation unit 435 substitutes, for example, an idea received from a person (which may be referred to as a proposer) into the variable <idea> of the prompt template "Please evaluate the following idea and answer with an evaluation value. The evaluation value should be answered on a five-point scale. The highest level value is '5'. [Idea]<idea>", constructs a prompt, passes the prompt to the generation AI, and obtains evaluation information that is an evaluation value from the generation AI.

[0322] The evaluation unit 435 obtains, for example, one or more parameters from the ideas received from the proposers and obtains evaluation information that is an evaluation value using the one or more parameters. The parameters are, for example, the number of ideas, the number of characters included in the ideas, or the number of technical terms included in the ideas. Note that the process of obtaining technical terms from a character string is a known technique (for example, "TermExtract").

[0323] The ranking unit 436 determines the rank of a person using one or more ideas received by the idea reception unit 122, and accumulates the rank in pairs with a person identifier that identifies the person.

[0324] Note that a person identifier is usually associated with the idea received by the idea reception unit 122. Then, the ranking unit 436 determines the rank using one or two or more ideas received by the idea reception unit 122, and accumulates the rank in pairs with the person identifier associated with the idea.

[0325] The ranking unit 436 obtains the rank of the person who proposed the idea, for example, using the evaluation information obtained by the evaluation unit 435. Usually, the ranking unit 436 obtains a higher rank for a person corresponding to higher evaluation information.

[0326] The reward processing unit 437 performs reward processing for giving a reward to the proposer. The reward processing unit 437 determines, for example, the amount of the reward to be given to the proposer, and performs reward processing for giving the reward amount to the proposer.

[0327] Reward processing is processing for giving a reward. Reward processing is, for example, processing for increasing points paired with a person identifier that identifies the proposer, processing for transferring money to a bank account specified by the account information paired with a person identifier that identifies the proposer, and processing for sending electronic money to the user using the user ID included in the electronic money information paired with a person identifier that identifies the proposer.

[0328] The output unit 44 outputs various types of information. The various types of information are, for example, all or part of the answer passed from the generation AI, or one or two or more ideas, scores, error messages, evaluation information, and ranks.

[0329] Here, the output usually refers to transmission to the terminal device 2, but it may also be a concept including display on a display, projection using a projector, printing by a printer, sound output, storage in a recording medium, delivery of the processing result to other processing devices or other programs, etc.

[0330] The evaluation output unit 441 outputs the evaluation information acquired by the evaluation unit 435. The evaluation output unit 441 accumulates, for example, the evaluation information in pairs with the person identifier. The evaluation output unit 441 transmits the evaluation information to the terminal device 2 corresponding to the person identifier, for example.

[0331] The rank output unit 442 outputs the rank acquired by the ranking unit 436. The rank output unit 442 accumulates, for example, the rank in pairs with the person identifier. The rank output unit 442 transmits the rank to the terminal device 2 corresponding to the person identifier, for example.

[0332] The storage unit 41, the human resource management unit 411, and the prompt management unit 412 are preferably a non-volatile recording medium, but can also be realized with a volatile recording medium.

[0333] The process of storing information in the storage unit 41 or the like is not limited. For example, the information may be stored in the storage unit 41 or the like via a recording medium, the information transmitted via a communication line or the like may be stored in the storage unit 41 or the like, or the information input via an input device may be stored in the storage unit 41 or the like.

[0334] The reception unit 42 and the additional instruction reception unit 421 are preferably realized by wireless or wired communication means, but may also be realized by means of receiving broadcasts, device drivers of input means such as touch panels and keyboards, control software of menu screens, etc.

[0335] The processing unit 43, the speaking order determination unit 431, the determination unit 432, the discussion change unit 433, the addition instruction unit 434, the evaluation unit 435, the ranking unit 436, and the reward processing unit 437 can usually be realized from a processor, a memory, and the like. The processing procedures of the processing unit 43 and the like are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (a dedicated circuit). Note that the processor may be a CPU, an MPU, a GPU, or the like, and the type thereof is not limited.

[0336] The output unit 44, the evaluation output unit 441, and the rank output unit 442 are usually realized by wireless or wired communication means, but may be realized by driver software of an output device such as a display or a speaker, or by driver software of the output device and the output device.

[0337] Next, an operation example of the creation support device 4 will be described with reference to the flowchart of FIG. 21. In the flowchart of FIG. 21, the description of the same steps as in the flowchart of FIG. 4 will be omitted. In the flowchart of FIG. 21, the reception of the start instruction in step S401 is, for example, that the start time of idea generation has arrived or that an instruction from a person has been received. The start time is, for example, a time set automatically or manually.

[0338] (Step S2101) The speaking order determination unit 431 acquires information on the number of agents or whether a person is included in the parties generating ideas, and determines whether the information satisfies the order determination condition. If the order determination condition is satisfied, the process proceeds to step S2102, and if not, the process proceeds to step S2103.

[0339] (Step S2102) The speaking order determination unit 43 establishes a speaking order for agents and the like. An example of such speaking order determination processing will be described with reference to the flowchart of FIG. 22. Note that the speaking order

[0340] (Step S2103) The idea acquisition unit 135 etc. acquires ideas. An example of such idea acquisition processing will be described using the flowchart of FIG. 23.

[0341] (Step S2104) The reward processing unit 437 performs reward processing. An example of the reward processing will be described using the flowchart of FIG. 24.

[0342] (Step S2105) The ranking unit 436 performs rank acquisition processing. An example of the rank acquisition processing will be described using the flowchart of FIG. 25.

[0343] Note that in the flowchart of FIG. 21, the processing ends due to a power-off or an interrupt for ending the processing.

[0344] Next, an example of the speech order determination processing in step S2102 will be described using the flowchart of FIG. 22.

[0345] (Step S2201) The speech order determination unit 431 acquires the speech order determination prompt template from the storage unit 41.

[0346] (Step S2202) The speech order determination unit 431 substitutes 1 for the counter i.

[0347] (Step S2203) The speech order determination unit 431 determines whether the i-th agent information exists. If the i-th agent information exists, it proceeds to step S2204, and if it does not exist, it proceeds to step S2206. Here, the agent information is the information of the agent who is the party for idea generation.

[0348] (Step S2204) The speech order determination unit 431 acquires the i-th agent information and adds the agent information to the position of the variable for substituting the agent information in the speech order determination prompt template.

[0349] (Step S2205) The speaking order determination unit 431 increments the counter i by 1. Return to step S2203.

[0350] (Step S2206) The speaking order determination unit 431 assigns 1 to the counter i.

[0351] (Step S2207) The speaking order determination unit 431 determines whether the i-th person identifier exists among the person identifiers of those participating in idea generation. If the i-th person identifier exists, go to step S2208; if not, go to step S2210.

[0352] (Step S2208) The speaking order determination unit 431 obtains the i-th personnel information from the personnel management unit 411 and adds the personnel information to the position of the variable for substituting the personnel information in the speaking order determination prompt template.

[0353] (Step S2209) The speaking order determination unit 431 increments the counter i by 1. Return to step S2207.

[0354] (Step S2210) The speaking order determination unit 431 provides the completed speaking order determination prompt to the generation AI.

[0355] (Step S2211) The speaking order determination unit 431 obtains the response corresponding to the speaking order determination prompt from the generation AI and obtains the speaking order information from the response. Return to the upper-level process. The speaking order information is, for example, the information of the parties arranged in the speaking order.

[0356] Next, an example of the idea acquisition process in step S2103 will be described using the flowchart of FIG. 23.

[0357] (Step S2301) The idea acquisition unit 135 obtains the idea generation prompt template from the prompt management unit 112.

[0358] (Step S2302) The idea acquisition unit 135 substitutes 1 for the counter i.

[0359] (Step S2303) The idea acquisition unit 135 refers to the speaking order information and determines whether the i-th party excluding the moderator exists. If the i-th party exists, it proceeds to step S904. If the i-th party does not exist, it proceeds to step S911. Note that whether the i-th party exists is determined by whether the i-th information exists in the agent information and the person identifier.

[0360] (Step S2304) The idea acquisition unit 135 determines whether the i-th party is an agent or a person. If the i-th party is an agent, it proceeds to step S2305. If it is a person, it proceeds to step S2309.

[0361] (Step S2305) The idea acquisition unit 135 etc. perform agent idea processing. Agent idea processing is processing related to the ideas put forward by the agent. An example of agent idea processing will be described using the flowchart of FIG. 26.

[0362] (Step S2306) The determination unit 432 determines whether one or more ideas acquired in step S2305 satisfy the discussion change condition. If the discussion change condition is satisfied, it proceeds to step S2307. If the discussion change condition is not satisfied, it proceeds to step S2312.

[0363] (Step S2307) The additional instruction reception unit 421 receives an additional instruction from a person. Usually, the additional instruction reception unit 421 outputs a screen for the person to input an additional instruction to the terminal device 2 used by the person, and receives the additional instruction input to the screen.

[0364] (Step S2308) The discussion change unit 433 gives the additional instruction to the generation AI. It returns to step S2305.

[0365] (Step S2309) The idea acquisition unit 135 etc. perform human idea processing. Human idea processing is processing related to ideas put forward by people. An example of human idea processing will be described using the flowchart of FIG. 27.

[0366] (Step S2310) The determination unit 432 determines whether one or more ideas acquired in Step S2309 satisfy the discussion change condition. If the discussion change condition is satisfied, it proceeds to Step S2311, and if the discussion change condition is not satisfied, it proceeds to Step S2312.

[0367] (Step S2311) The discussion change unit 433 changes the speaking order. Note that changing the speaking order includes preventing people or agents from speaking. Changing the speaking order is, for example, moving the person identifier (the identifier of the person who put forward the idea) paired with the idea received in Step S2309 to the lowest position in the speaking order information, or deleting the person identifier paired with the idea received in Step S2309 from the speaking order information. Deleting the person identifier from the speaking order information means removing the person from the parties.

[0368] (Step S2312) The idea acquisition unit 135 sets the counter i to 1 and increments it. It returns to Step S2303.

[0369] (Step S2313) The determination unit 432 determines whether one or more ideas acquired so far satisfy the discussion change condition. If the discussion change condition is satisfied, it proceeds to Step S2314, and if the discussion change condition is not satisfied, it returns to the upper-level process. Note that the discussion change condition here is, for example, that the total number of ideas is less than or equal to a threshold value or less than the threshold value.

[0370] (Step S2314) The processing unit 43 determines whether to accept an additional instruction. If it accepts the additional instruction, it proceeds to step S2315; if it does not accept it, it returns to step S2302. When it returns to step S2302, each party will put forward ideas again. The processing unit 43 determines to accept the additional instruction, for example, when the acceptance of the previous additional instructions is less than or equal to a threshold value.

[0371] (Step S2315) The additional instruction reception unit 421 accepts an additional instruction from a person. For example, the additional instruction reception unit 421 transmits an input screen for the additional instruction to the terminal device 2 and receives the additional instruction from the terminal device 2.

[0372] (Step S2316) The discussion change unit 433 gives the additional instruction received in step S2315 to the generation AI. Then it returns to step S2302.

[0373] Next, an example of the reward processing in step S2104 will be described with reference to the flowchart of FIG. 24.

[0374] (Step S2401) The reward processing unit 437 assigns 1 to the counter i.

[0375] (Step S2402) The reward processing unit 437 determines whether the i-th proposer exists. If the i-th proposer exists, it proceeds to step S2403; if not, it returns to the upper-level processing.

[0376] Here, for example, the reward processing unit 437 determines whether the i-th person identifier paired with the theme identifier of the theme exists.

[0377] (Step S2403) The reward processing unit 437 acquires the person identifier of the i-th proposer.

[0378] (Step S2404) The reward processing unit 437 acquires the evaluation information obtained by the evaluation unit 435, which is the evaluation information paired with the person identifier acquired in step S2403.

[0379] (Step S2405) The reward processing unit 437 acquires the rank corresponding to the person identifier acquired in Step S2403.

[0380] (Step S2406) The reward processing unit 437 acquires the reward amount using the evaluation information acquired in Step S2404 and the rank acquired in Step S2405. Usually, the higher the evaluation indicated by the evaluation information and the higher the rank, the higher the reward amount acquired by the reward processing unit 437. The reward processing unit 437 may acquire the reward amount based on only the evaluation information or only the rank. The reward processing unit 437 may acquire a fixed reward amount from the storage unit 41.

[0381] (Step S2407) The reward processing unit 437 performs a reward process of giving the reward indicated by the reward amount acquired in Step S2406 to the person identified by the person identifier of the i-th proposer.

[0382] (Step S2408) The reward processing unit 437 acquires the notification destination information corresponding to the person identifier of the i-th proposer. The reward processing unit 437 transmits information indicating that the reward indicated by the reward amount has been given to the notification destination indicated by the notification destination information.

[0383] (Step S2409) The reward processing unit 437 increments the counter i by 1. Return to Step S2402.

[0384] Next, an example of the rank acquisition process in Step S2105 will be described using the flowchart of FIG. 25.

[0385] (Step S2501) The ranking unit 436 substitutes 1 for the counter i.

[0386] (Step S2502) The ranking unit 436 determines whether the i-th proposer exists. If the i-th proposer exists, go to Step S2503; if not, return to the upper-level process.

[0387] (Step S2503) The ranking unit 436 acquires the person identifier of the i-th proposer.

[0388] (Step S2504) The ranking unit 436 acquires the rank paired with the person identifier from the human resource management unit 411. Such rank is the original rank.

[0389] (Step S2505) The ranking unit 436 acquires the information used for the determination of rank up. Such information is, for example, the score acquired by the score acquisition unit 139, the evaluation information acquired by the evaluation unit 435, and whether or not the idea of the proposer is included in the ideas selected by the idea selection unit 137.

[0390] (Step S2506) The ranking unit 436 determines whether or not the one or more pieces of information acquired in Step S2505 meet the rank up conditions. If they meet the rank up conditions, it proceeds to Step S2507; if not, it proceeds to Step S2509.

[0391] (Step S2507) The ranking unit 436 acquires the new rank obtained by incrementing the original rank acquired in Step S2504 by 1.

[0392] (Step S2508) The ranking unit 436 stores the new rank acquired in Step S2507 in the human resource management unit 411 in pair with the person identifier of the proposer.

[0393] (Step S2509) The ranking unit 436 increments the counter i by 1. It returns to Step S2502.

[0394] Note that in the flowchart of FIG. 25, it is preferable not to perform the rank up process for the proposer who already corresponds to the highest rank.

[0395] Next, an example of the agent idea processing in step S2305 will be described using the flowchart of FIG. 26. The flowchart of FIG. 26 corresponds to steps S904 to S909 in FIG. 9.

[0396] Next, an example of the human idea processing in step S2309 will be described using the flowchart of FIG. 27. In the flowchart of FIG. 27, the description of the same steps as in the flowchart of FIG. 9 will be omitted.

[0397] (Step S2701) The idea acquisition unit 135 outputs an idea input screen to the terminal device 2. The process proceeds to step S914.

[0398] Hereinafter, a specific operation example of the information system B in the present embodiment will be described.

[0399] Currently, the transition management table shown in FIG. 13 is stored in the transition management unit 111 of the creation support device 4. Also, the prompt management table shown in FIG. 28 is stored in the prompt management unit 112 of the creation support device 4. The prompt management table shown in FIG. 28 has, in addition to the prompt prototype of the prompt management table in FIG. 14, a speech order determination prompt prototype added. The speech order determination prompt prototype is "List the appropriate speech order of the following agents and the following proposers when creating ideas regarding the theme of "<theme>"! [Agent] <agent information> [Proposer] <keyword> expert". Note that <agent information> is substituted with the information of one or more agents. Also, "<keyword> expert" is replaced with the information of one or more people.

[0400] Now, assume that the human resource management table shown in FIG. 29 is stored in the human resource management section 411 of the creation support device 4. The human resource management table is a table for managing human resource information. The human resource management table manages one or more records having "ID" and "human resource information". "Human resource information" has "person identifier", "notification destination information", "theme information", "account information", "points", and "rank". "Theme information" has "field" and "keyword". "Field" is the field in which the candidate is proficient. "Keyword" is a keyword indicating the candidate's specialized technology. Also, in this specific example, assume that the people who come up with ideas are the proposers of the person identifiers "P01" and "P03".

[0401] Also, assume that the storage section 41 of the creation support device 4 stores the order determination condition "number of parties >= 5".

[0402] Also, assume that the storage section 41 stores the discussion change management table shown in FIG. 30. The discussion change management table is a table for managing information related to discussion changes. The discussion change management table manages one or more records having "ID", "target", "discussion change condition", and "discussion change process identifier". "ID" is information for identifying a record. "Target" is the inspection target. "Discussion change condition" is the discussion change condition. "Discussion change process identifier" is information for identifying the process to be performed when the discussion change condition is met. The record with "ID = 1" in FIG. 30 means that when there is no input of an idea for more than 3 minutes after the order in which the proposers input ideas, a speech order change process is performed to remove the proposer from the speaker (the person who inputs the idea). The record with "ID = 2" indicates that when the analysis result of the idea obtained in one speech of one party is an error, a process of re-acquiring the idea for the party is performed. The record with "ID = 3" indicates that when the total number of ideas presented is 6 or less, a person (proposer) is prompted to input an additional instruction (for example, a new perspective), the additional instruction is received, and after giving the additional instruction to the generation AI, a process of re-acquiring ideas for all parties is performed.

[0403] Furthermore, assume that "solutions using AI and cameras" is given as the theme for which ideas are to be put forward.

[0404] In the above situation, assume that the agent determination unit 130 automatically determined four agents, namely, "· Market analysis agent · Technology trend agent · Business model agent · Regulatory agent", through the above-described processing.

[0405] From the above, the parties participating in idea generation are a total of six parties, namely two people and four agents.

[0406] Next, the person setting unit 131 performs person setting processing according to the processing described using the flowchart of FIG. 7 as follows.

[0407] Also, assume that the viewpoint acquisition unit 134 obtained idea viewpoints of "entry market" and "technological innovativeness" through the same processing as that described in Embodiment 1. Also, assume that the viewpoint acquisition unit 134 obtained evaluation viewpoints of "technical feasibility", "user convenience", and "market needs".

[0408] Also, the speaking order determination unit 431 acquires the number of parties "6" and determines that the number of parties satisfies the order determination condition of the storage unit 41, "number of parties >= 5".

[0409] Then, the speaking order determination unit 431 constructs the speaking order determination prompt of FIG. 31 using the speaking order determination prompt prototype (FIG. 28) through the processing described using the flowchart of FIG. 22, passes the prompt to the generation AI, and obtains the answer of FIG. 32 from the generation AI. Then, the speaking order determination unit 431 obtains speaking order information of "1. Market analysis agent 2. Technology trend agent 3. AI and machine learning expert 4. AI and natural language processing expert 5. Business model agent 6. Regulatory agent" from the answer.

[0410] Then, the idea acquisition unit 135 and the like perform the idea acquisition process described using the flowchart of FIG. 23. Here, the idea acquisition unit 135 acquires ideas from the agent or the proposer in the order indicated by the speaking order information.

[0411] Also, during the process of idea acquisition, after the proposer "3. AI, Machine Learning Specialist" reached the order of inputting his / her own idea, and 3 minutes passed without inputting an idea, the determination unit 432 refers to the table in FIG. 30 and determines to exclude the proposer from the parties. Then, the discussion change unit 433 changes the speaking order information from "1. Market Analysis Agent 2. Technology Trend Agent 3. AI, Machine Learning Specialist 4. AI, Natural Language Processing Specialist 5. Business Model Agent 6. Regulatory Agent" to "1. Market Analysis Agent 2. Technology Trend Agent 3. AI, Natural Language Processing Specialist 4. Business Model Agent 5. Regulatory Agent". As a result, in subsequent idea submissions, the proposer "AI, Machine Learning Specialist" will not be prompted to input an idea.

[0412] Also, at the stage when one round of idea submissions is completed, assume that the total number of ideas submitted is "5".

[0413] Next, the determination unit 432 refers to the table in FIG. 30 and determines that the discussion change condition of "ID = 3" is satisfied. Next, the discussion change unit 433 refers to the table in FIG. 30 and performs the discussion change process identifiers of "ID = 3", namely, "Additional Instruction Input Process" and "Idea Reacquisition Process". That is, the discussion change unit 433 sends an additional instruction (here, an instruction to input a new perspective for creating an idea) to the terminal device 2 of the proposer "AI, Natural Language Processing Specialist". And assume that the proposer inputs the additional instruction "User - Customer Perspective".

[0414] Next, it is assumed that the discussion change unit 433 receives the additional instruction "user / customer perspective" from the terminal device 2, constructs the prompt "Come up with ideas from the user / customer perspective!", and gives the prompt to the generation AI. Note that the discussion change unit 433 substitutes the received additional instruction "user / customer perspective" into the variable <additional instruction> of the prompt template "<additional instruction> Come up with ideas too!" of the prompt management unit 412 to construct the prompt "Come up with ideas from the user / customer perspective!". Note that giving the prompt to the generation AI means giving the additional instruction to the generation AI.

[0415] Next, it is assumed that the discussion change unit 433 instructs the idea acquisition unit 135, etc. to perform the idea acquisition process described using the flowchart of FIG. 23 again, and the idea acquisition process is performed again.

[0416] As a result of the above processing, it is assumed that a large number of six or more ideas are acquired.

[0417] Next, as described in the specific example of Embodiment 1, the idea criticism unit 136 performs the idea criticism process described using the flowchart of FIG. 11. Also, the idea selection unit 137 performs the idea selection process described using the flowchart of FIG. 12.

[0418] As a result of the above processing, the terminal device 2 receives and outputs information on, for example, seven ranked ideas. Such an output example is shown in FIG. 19.

[0419] Also, in this specific example, the evaluation unit 435 acquires the evaluation information of the idea proposed by the proposer "P03". Also, the evaluation output unit 441 transmits the evaluation information to the terminal device 2 of the user U and the terminal device 2 of the proposer.

[0420] The terminal device 2 of the user U and the terminal device 2 of the proposer "P03" receive and output the evaluation information of the idea proposed by the proposer "P03".

[0421] Also, the ranking unit 436 updates the rank of the proposer 1 identified by the person identifier "P03" from, for example, "3" to "4" by the above-described process. Further, the ranking unit 436 subtracts and updates the rank paired with the person identifier "P01" of the person who did not come up with an idea from "4" to "3".

[0422] Also, the reward processing unit 437 determines the amount of reward for the proposer 1 identified by the person identifier "P03" by the above-described process.

[0423] As described above, according to the present embodiment, when creating ideas using the generation AI, the progress of the discussion can be appropriately controlled.

[0424] Also, according to the present embodiment, when creating ideas using two or more generation AI agents, the discussion can proceed in an appropriate speaking order.

[0425] Also, according to the present embodiment, it is possible to support the creation of appropriate ideas through the cooperation between humans and the generation AI.

[0426] Also, according to the present embodiment, the rank of the person who participated in the creation of the idea can be determined.

[0427] Note that the software for implementing the idea creation support device 4 in this embodiment is a program as follows. That is, this program includes a setting prompt template for configuring prompts for character settings of one or more agents, and a phase prompt template for configuring prompts given to the generation AI in one or more phases including the idea generation phase, and a prompt management unit that stores these; a computer that can access an attribute value storage unit that stores one or more idea attribute values, which are attribute values related to the ideas to be created and include the theme of the target for idea generation; a person setting unit that acquires one or more setting prompts using the setting prompt template and gives the one or more setting prompts to the generation AI; an idea acquisition unit that acquires a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, gives the prompt to the one or more agents of the generation AI, and acquires ideas; an idea output unit that outputs the ideas acquired by the idea acquisition unit; a determination unit that determines whether the discussion change conditions are met; and a discussion change unit that, when the determination unit determines that the discussion change conditions are met, functions as a speech order change process for changing the speech order of the two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea re-acquisition process for giving the prompt to the one or more agents again and acquiring ideas.

[0428] Further, FIG. 33 is a block diagram of a computer system 300 that executes the program described in this specification to implement the idea creation support device 4 and the like of the various embodiments described above.

[0429] In FIG. 33, the computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0430] In FIG. 33, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012 and the like, a ROM 3015 for storing programs such as a boot-up program, a RAM 3016 connected to the MPU 3013 for temporarily storing instructions of an application program and providing a temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Here, although not shown, the computer 301 may further include a network card for providing connection to a LAN.

[0431] A program for causing the computer system 300 to execute functions such as the creation support apparatus 4 of the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 when executed. The program may be loaded directly from the CD-ROM 3101 or the network.

[0432] The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute functions such as the creation support apparatus 4 of the above-described embodiment. The program only needs to include a part of instructions that call appropriate functions (modules) in a controlled manner so as to obtain a desired result. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0433] Note that in the above program, in steps such as the step of transmitting information and the step of receiving information, processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (processing that can only be performed by hardware) is not included.

[0434] Also, the computer that executes the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

[0435] Also, in each of the above embodiments, it goes without saying that two or more communication means existing in one device may be physically realized by one medium.

[0436] Also, in each of the above embodiments, each process may be realized by being centrally processed by a single device, or may be realized by being distributedly processed by a plurality of devices.

[0437] The present invention is not limited to the above embodiments, and various modifications are possible, and it goes without saying that those are also included in the scope of the present invention.

Industrial Applicability

[0438] As described above, the idea creation support device 4 according to the present invention has an effect of being able to appropriately control the progress of discussion when creating an idea using a generative AI, and is useful as a server or the like for supporting the creation of an idea.

Explanation of Signs

[0439] A, B Information system 1, 4 Idea creation support device 2 Terminal device 3 Generative AI device 11, 41 Storage unit 12, 42 Reception unit 13, 43 Processing unit 14, 44 Output unit 21 Terminal storage unit 22 Terminal reception unit 23 Terminal processing unit 24 Terminal transmission unit 25 Terminal reception unit 26 Terminal output unit 111 Transition management unit 112, 412 Prompt Management Department 113 Attribute Value Storage Department 114 Current Management Department 121 Attribute Value Reception Department 122 Idea Reception Department 130 Agent Determination Department 131 Character Setting Department 132 Control Department 133 Moderator Judgment Department 134 Perspective Acquisition Department 135 Idea Acquisition Department 136 Idea Criticism Department 137 Idea Selection Department 138 Analysis Department 139 Score Acquisition Department 141 Answer Output Department 142 Idea Output Department 143 Score Output Department 144 Error Output Department 411 Human Resource Management Department 421 Additional Instruction Reception Department 431 Speaking Order Determination Department 432 Judgment Department 433 Discussion Change Department 434 Additional Instruction Department 435 Evaluation Department 436 Ranking Department 437 Reward Processing Department 441 Evaluation Output Department 442 Rank Output Department

Claims

1. A creation support device for assisting idea creation by two or more parties including one or more agents of a generative AI, a prompt management unit that stores a setting prompt template for configuring a prompt for character setting of each of one or more agents, and a phase prompt template for configuring a prompt to be given to the generative AI in each of one or more phases including an idea generation phase, an attribute value storage unit that stores one or more idea attribute values that are attribute values related to the idea to be created and include a theme of the target for generating an idea, a character setting unit that acquires one or more setting prompts using the setting prompt template and gives each of the one or more setting prompts to the generative AI, an idea acquisition unit that acquires a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, gives the prompt to each of the one or more agents of the generative AI, and acquires an idea, an idea output unit that outputs the idea acquired by the idea acquisition unit, a determination unit that determines whether it meets the discussion change condition, a discussion change unit that, when the determination unit determines that it meets the discussion change condition, performs a speaking order change process for changing the speaking order of the two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or gives the prompt to each of the one or more agents again to perform an idea reacquisition process for acquiring an idea, and an idea reception unit that receives one or more ideas from a person, wherein the idea output unit outputs the idea acquired by the idea acquisition unit or the one or more ideas received by the idea reception unit, and the determination unit is a creation support device that determines whether the idea acquired by the idea acquisition unit, the one or more ideas received by the idea reception unit, the time until the idea reception unit receives one or more ideas from the person, or the received instruction meets the discussion change condition.

2. The discussion change unit performs the additional instruction input process, further includes an additional instruction reception unit that receives the additional instruction, and an additional instruction unit that passes a prompt having the additional instruction to the generative AI. The creation support device according to claim 1.

3. A creation support device for assisting idea creation by two or more parties including one or more agents of a generative AI, a setting prompt template for configuring a prompt for character setting of one or more agents, and a phase prompt template for configuring a prompt to be given to the generative AI in one or more phases including an idea generation phase, stored in a prompt management unit; an attribute value storage unit storing one or more idea attribute values which are attribute values regarding the idea to be created and include a theme of the target for idea generation; a character setting unit that acquires one or more setting prompts using the setting prompt template and gives the one or more setting prompts to the generative AI; an idea acquisition unit that acquires a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, gives the prompt to the one or more agents of the generative AI, and acquires an idea; an idea output unit that outputs the idea acquired by the idea acquisition unit; a determination unit that determines whether it meets the discussion change condition; a discussion change unit that, when the determination unit determines that it meets the discussion change condition, performs a speaking order change process for changing the speaking order of the two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea re-acquisition process for giving the prompt to the one or more agents again and acquiring an idea; an idea reception unit that receives one or more ideas from a person, and the discussion change unit is a creation support device that gives the idea acquired by the idea acquisition unit or the one or more ideas received by the idea reception unit to the generative AI, and gives the prompt corresponding to the idea generation phase to the generative AI, and performs the idea re-acquisition process of acquiring an idea.

4. The creation support device according to claim 1, further comprising a ranking unit that determines the rank of the person using the one or more ideas received by the idea reception unit and accumulates the rank in a pair with a person identifier for identifying the person.

5. A creation support device for assisting idea creation by two or more parties including one or more agents of a generative AI, A setting prompt template for configuring a prompt for character settings of one or more agents, and a phase prompt template for configuring a prompt to be given to a generative AI in one or more phases including an idea generation phase are stored in a prompt management unit. An attribute value storage unit stores one or more idea attribute values that are attribute values related to the ideas to be created and include a theme of the target for idea generation. A character setting unit obtains one or more setting prompts using the setting prompt template and gives the one or more setting prompts to the generative AI. An idea acquisition unit obtains a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, gives the prompt to each of the one or more agents of the generative AI, and acquires ideas. An idea output unit outputs the ideas acquired by the idea acquisition unit. A determination unit determines whether the discussion change conditions are met. When the determination unit determines that the discussion change conditions are met, a discussion change unit performs a speaking order change process for changing the speaking order of the two or more parties, or an additional instruction input process for causing a person to input an additional instruction, or an idea reacquisition process for giving the prompt to each of the one or more agents again and acquiring ideas. The character setting unit obtains two or more setting prompts using the setting prompt template, gives the two or more setting prompts to the generative AI. The character setting unit further includes a speaking order determination unit that obtains a speaking order determination prompt using a speaking order determination prompt template for determining the speaking order of two or more agents and gives the speaking order determination prompt to the generative AI to determine the speaking order of the agents corresponding to the two or more setting prompts. The idea acquisition unit A creative support device that acquires ideas from each agent in the order indicated by the speaking order of the two or more agents determined by the speaking order determination unit.

6. The character setting unit obtains two or more setting prompts using the setting prompt template, gives the two or more setting prompts to the generative AI. An utterance order determination prompt is obtained using an utterance order determination prompt template for determining the utterance order of each of two or more agents, and the utterance order determination prompt is given to the generation AI, and further includes an utterance order determination unit that determines the utterance order of the agents corresponding to the two or more setting prompts. The idea acquisition unit The creation support device according to any one of claims 1 to 4, wherein ideas are obtained from each agent in the order indicated by the utterance order of the two or more agents determined by the utterance order determination unit.

7. A creation support method for causing a computer to execute all processes performed by the creation support device according to any one of claims 1 to 5.

8. A computer A program for causing a computer to function as the creation support device according to any one of claims 1 to 5.

Images