Creation support device

Abstract

In the past, it was difficult for generative AI and humans to work together to generate ideas on a single theme. [Solution] A creation support device 4 including a recruitment processing unit 431 that performs a recruitment process to recruit people to submit ideas for a theme and determines proposers who will submit ideas for the theme, a person setting unit 131 that provides the generation AI with one or more setting prompts for setting a person, an idea acquisition unit 135 that provides prompts for generating ideas to one or more agents of the generation AI and acquires ideas, an idea receiving unit 122 that accepts ideas from the proposers determined by the recruitment processing unit 431, and an idea output unit 142 that outputs the ideas acquired by the idea acquisition unit 135 and the ideas acquired by the idea receiving unit 122, can support the generation AI and people in creating ideas for a theme together.

Description

[Technical field]

[0001] The present invention relates to a creation support device that supports the creation of ideas using a generative AI. [Background technology]

[0002] Conventionally, there has been an idea creation support system that is said to be a platform that provides an environment in which participants can easily create ideas (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-35936 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, with conventional technology, it was difficult for generative AI and humans to work together to generate ideas on a single theme. [Means for solving the problem]

[0005] The first invention of the creation support device is a creation support device comprising: a prompt management unit in which a setting prompt template for constructing a prompt for character setting of one or more agents and a phase prompt template for constructing a prompt to be given to the generation AI in each of one or more phases including the idea generation phase are stored; an attribute value storage unit in which one or more idea attribute values ​​which are attribute values ​​related to the idea to be created and include a theme for which the ideas are to be generated are stored; a recruitment processing unit that performs a recruitment process to recruit people to submit ideas for the theme and determines a proposer who will submit ideas for the theme; a character setting unit that obtains one or more setting prompts using the setting prompt template and provides the one or more setting prompts to the generation AI; an idea acquisition unit that obtains prompts using a phase prompt template corresponding to the idea generation phase and one or more idea attribute values, and provides the prompts to one or more agents of the generation AI to acquire ideas; an idea receiving unit that accepts ideas from the proposer determined by the recruitment processing unit, and an idea output unit that outputs the ideas acquired by the idea acquisition unit and the ideas acquired by the idea receiving unit.

[0006] This configuration can help generative AI and people work together to generate ideas on a single theme.

[0007] In addition, the creativity support device of the second invention is a creativity support device in which, compared to the first invention, the prompt management unit stores a setting prompt template and a phase prompt template for constructing a prompt to be given to the generation AI in each of two or more phases including the idea generation phase and the idea selection phase, and further includes an idea selection unit that acquires a prompt using the phase prompt template corresponding to the idea selection phase, the idea acquired by the idea acquisition unit, and the idea accepted by the idea receiving unit, provides the prompt to the generation AI, and acquires one or more ideas selected based on the idea acquired by the idea acquisition unit and the idea accepted by the idea receiving unit, and the idea output unit outputs one or more ideas acquired by the idea selection unit in addition to the ideas acquired by the idea acquisition unit and the ideas acquired by the idea receiving unit, or in place of the ideas acquired by the idea acquisition unit and the ideas acquired by the idea receiving unit.

[0008] With this configuration, the generation AI and humans can work together to select appropriate ideas from among the ideas they come up with on a single theme.

[0009] The creation support device of the third invention is a creation support device further including a reward processing unit that performs reward processing for giving a reward to a proposer for the first or second invention.

[0010] With this configuration, it is possible to give a reward to the person who proposes the idea.

[0011] In addition, the creation support device of the fourth invention is a creation support device further comprising an attribute value receiving unit for receiving a theme with respect to any one of the first to third inventions, and the recruitment processing unit refers to a human resources management unit in which two or more human resources information having theme information related to the theme and a human identifier identifying a person is stored, and acquires one or more human identifiers identifying candidates who correspond to the theme, an offer means for making an offer to submit ideas related to the theme to each of the one or more candidates acquired by the candidate determination means, and a proposer determination means for receiving permission information from one or more of the one or more candidates, and determining a proposer who is a candidate corresponding to the permission information and a candidate who can submit an idea.

[0012] With this configuration, people who fit the theme can be offered the opportunity to participate in idea generation.

[0013] In addition, the creation support device of the fifth invention is a creation support device further including, with respect to any one of the first to fourth inventions, an evaluation unit that acquires evaluation information indicating an evaluation of the idea accepted by the idea accepting unit, and an evaluation output unit that outputs the evaluation information.

[0014] With this configuration, the ideas put forward by the proposers can be evaluated.

[0015] In addition, the creative support device of the sixth invention is a creative support device that, compared to the fifth invention, further includes a ranking unit that uses the evaluation information acquired by the evaluation unit to acquire a rank of the proposer who submitted the idea, and a rank output unit that outputs the rank.

[0016] This configuration allows the candidates submitting ideas to be ranked. Effect of the Invention

[0017] The creation support device according to the present invention can support a generation AI and a person working together to create ideas on a single theme. [Brief description of the drawings]

[0018] [Figure 1] Conceptual diagram of information system A in embodiment 1. [Diagram 2] Block diagram of Information System A [Diagram 3] Block diagram of the creation support device 1 [Figure 4] A flowchart illustrating an example of the operation of the creation support device 1. [Diagram 5] A flowchart illustrating an example of the pre-processing [Figure 6] A flowchart illustrating an example of the agent determination process. [Figure 7] Flowchart for explaining an example of same person setting processing [Figure 8] Flowchart for explaining an example of viewpoint acquisition processing [Figure 9] A flowchart illustrating an example of the idea acquisition process. [Figure 10] A flowchart illustrating an example of the idea analysis process. [Figure 11] A flowchart illustrating an example of the idea criticism process. [Figure 12] A flowchart illustrating an example of the idea selection process. [Figure 13] FIG. 2 shows the transition management table. [Figure 14] A diagram showing the prompt management table [Figure 15] A diagram showing an example of agent information [Figure 16] A diagram showing an example of the output [Figure 17] A diagram showing an example of the output [Figure 18] A diagram showing an example of the output [Figure 19] A diagram showing an example of the output [Figure 20] Block diagram of creation support device 4 in embodiment 2 [Figure 21] A flowchart for explaining an example of the operation of the creation support device 4. [Figure 22] A flowchart illustrating an example of the idea acquisition process. [Diagram 23] A flowchart illustrating an example of the idea evaluation process. [Figure 24] Flowchart showing an example of the compensation process [Diagram 25] A flowchart illustrating an example of a rank acquisition process. [Figure 26] A flowchart illustrating an example of the offer process. [Figure 27] A flowchart for explaining an example of the operation of the terminal device 2 [Figure 28] An example of the personnel management table [Figure 29] Block diagram of a computer system according to the above embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] Hereinafter, an embodiment of the creation support device and the like will be described with reference to the drawings. Note that, in the embodiments, components with the same reference numerals perform similar operations, and therefore repeated description may be omitted.

[0020] (Embodiment 1) In this embodiment, we describe a creation support device that supports the creation of ideas by two or more parties including one or more generation AI agents, which acquires two or more ideas in an idea generation phase, and then acquires and outputs one or more ideas from the two or more ideas acquired in a subsequent idea selection phase.

[0021] In this embodiment, a creation support device that allows people to participate in the creation of ideas will be described.

[0022] In this embodiment, a creation support device is described that checks input from a person and, depending on the result of the check, may or may not provide the input to the generation AI. In this embodiment, if the result of the check of the input from a person is an error, an error message or a class of error is output.

[0023] In this embodiment, a creation support device in which a moderator agent exists will be described.

[0024] In addition, in this embodiment, a creation support device will be described in which the moderator's agent operates to give a prompt to the other agents when a predetermined condition is satisfied.

[0025] In addition, in this embodiment, a creation support device is described that outputs answers, etc. from a generation AI for creating ideas in a manner that allows the current phase to be known within the overall phases of creating ideas.

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

[0027] In this embodiment, a creation support device that automatically determines a necessary agent will be described.

[0028] In this embodiment, a creation support device that evaluates a set of output ideas from the viewpoint of diversity will be described.

[0029] Furthermore, in this embodiment, a creation support device that manages two or more phases leading up to the creation of an idea and the transition conditions of the phases, and controls the phase transitions based on the managed information, will be described.

[0030] 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 important. 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] Furthermore, 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., and is sufficient as long as information Z can be accessed.

[0032] FIG. 1 is a conceptual diagram of information system A in this embodiment. Information system A includes a creation support device 1, one or more terminal devices 2, and one or more generating AI devices 3. The program stored in the generating AI device 3 is referred to as the generating AI. The generating AI device 3 may also be referred to as the generating AI. Information system A may have one generating AI device 3, or two or more generating AI devices 3. When there are two or more generating AI devices 3, it is preferable that there is a generating AI device 3 corresponding to each agent described below. The generating AI device is an external device to information system A, and information system A may be considered not to have a generating AI device 3.

[0033] The creation support device 1 is, for example, a cloud server or an ASP server, but the type is not important. The creation support device 1 may also be a terminal. If the creation support device 1 is a terminal, the information system A does not require a terminal device 2. If 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. If 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 the type is not important.

[0034] In addition, the creation support device 1 may have one or more generation AIs. In such a case, the information system A does not need to have the generation AI device 3.

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

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

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

[0038] Fig. 2 is a block diagram of an information system A according to the present embodiment. Fig. 3 is a block diagram of a 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 character setting unit 131, a control unit 132, a moderator judgment 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, 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 .

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

[0042] The transition management unit 111 stores transition information and transition conditions. The transition information is information that specifies a transition between two or more phases for creating an idea. A phase may be called a procedure, a step, a stage, or the like. For example, a phase is represented by a node, and a 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 transition occurs. A transition condition is a condition associated with a phase before a transition and a phase after the transition. A transition condition is a condition associated with edge information. Two or more transition conditions may be associated with one piece of phase information. When two or more transition conditions are associated with one piece of phase information, there are two or more phases after the transition. In other words, when two or more transition conditions are associated with one piece of phase information, the phase branches.

[0044] Each of the two or more phases specified by the transition information is a step leading to the creation of an idea. 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. Phase identifiers held by the transition information are, for example, "idea perspective / evaluation perspective consideration," "idea generation," "idea criticism," and "idea selection."

[0045] The idea selection phase may be a phase in which some ideas are selected from two or more ideas, or a phase in which two or more ideas are prioritized. In other words, the ranking of ideas may be considered to be included in the selection of ideas.

[0046] Various prompt templates are stored in the prompt management unit 112. A prompt template is information for constructing a prompt. A prompt template usually includes variables. A prompt is constructed by substituting information in the place of the variables. However, a prompt template may be a prompt that does not include variables. A prompt is information provided to a generating AI. By providing a prompt to a generating AI, an answer is usually passed from the generating AI. A prompt may also be called an inquiry, query, etc. Providing a prompt to a generating AI means, for example, providing the prompt as an argument to the API of the generating 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 a setting prompt template for the facilitator and a phase prompt template for the facilitator are stored in the prompt management unit 112. The facilitator is a person who acts as a moderator in a role-play for generating ideas.

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

[0050] An agent is a role played by generative AI. An agent is a virtual person who creates ideas, criticizes ideas, and selects ideas. An agent can be called a persona.

[0051] An agent determination prompt template is a template for a prompt for determining one or more agents. An agent determination prompt template typically has a variable into which a theme is substituted. An agent determination prompt template has variables into which, for example, one or more idea perspectives and one or more evaluation perspectives are substituted. An example of an agent determination prompt template is, "What kind of people in a position necessary to generate ideas related to the theme '<theme>'?"

[0052] A phase prompt template is a prompt template for one of the phases. A phase prompt template is usually associated with a phase identifier. Note that being associated with a phase identifier may mean that the prompt template identifier includes all or part of the phase identifier.

[0053] The prompt management unit 112 stores, for example, an idea perspective prompt template and an evaluation perspective prompt template in association with a phase identifier "idea perspective / evaluation perspective examination phase." The idea perspective prompt template is a template of a prompt for acquiring one or more idea perspectives. The idea perspective prompt template usually has a variable into which a theme is substituted. The idea perspective prompt template may have a variable into which, for example, an idea perspective given by a user is substituted. The idea perspective prompt template is, for example, "Tell me a perspective for an idea on a theme called <theme>!" The evaluation perspective prompt template is a template of a prompt for acquiring one or more evaluation perspectives. The evaluation perspective prompt template usually has a variable into which a theme is substituted. The evaluation perspective prompt template may have a variable into which, for example, an evaluation perspective given by a user is substituted. The evaluation perspective prompt template is, for example, "Tell me a perspective for evaluating an idea on a theme called <theme>!"

[0054] An idea perspective is a perspective related to ideas. Examples of idea perspectives include "clarification of purpose," "technical feasibility," "legal regulations," and "economic feasibility." An evaluation perspective is a perspective for evaluating ideas. Examples of evaluation perspectives include "development cost," "usability," "market applicability," and "compliance with regulations."

[0055] The prompt management unit 112 stores an idea generation prompt template in association with, for example, a phase identifier "idea generation phase." The idea generation prompt template is information for configuring a prompt for idea generation. The idea generation prompt template usually has a variable 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 a variable into which all or part of the agent information (e.g., "name") is substituted. For example, the idea generation prompt template is "You are <name>. For <theme>, please consider the following idea perspectives and the following idea evaluation perspectives and come up with an idea. <idea perspective>, <evaluation perspective>."

[0056] The prompt management unit 112 stores an idea critique prompt template, for example, in association with a phase identifier "idea critique phase." An idea critique prompt template is a prompt template for obtaining one or more critiques of an idea. An idea critique prompt template typically has variables into which ideas are assigned. An example of an idea critique prompt template is "Please list issues or problems with idea '<idea>' in relation to <theme>."

[0057] The prompt management unit 112 stores, for example, an idea selection prompt template in association with a phase identifier "idea selection phase." The idea selection prompt template is a template for a prompt for selecting and ranking ideas. The idea selection prompt template has a variable into which two or more ideas are assigned. Note that the selection of ideas may also be a ranking of ideas. The idea selection prompt template is, for example, "This is a request to the moderator. Please rank the following set of ideas. <set of ideas>" or "This is a request to the moderator. Please select five ideas that you think are good from the following set of ideas. <set of ideas>."

[0058] An idea analysis prompt template is a template for a prompt for analyzing an idea. An idea analysis prompt template usually has a variable into which an idea is assigned. For example, an idea analysis prompt template has a variable into which a theme is assigned. For example, an idea analysis prompt template is, "Please answer whether the following idea is appropriate as an idea related to <theme> by either "1" for appropriate or "0" for inappropriate! <idea>."

[0059] The attribute value storage unit 113 stores one or more idea attribute values. The idea attribute value is information about the idea to be created. The one or more idea attribute values ​​are, for example, a theme, a purpose, a viewpoint to be included in the idea, and a viewpoint for criticism of the idea. The idea attribute value in the attribute value storage unit 113 may be information input by a user, information stored in advance, or information acquired based on a response from the generation AI.

[0060] The current management unit 114 stores a current identifier. The 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 receiving unit 12 receives various instructions and information, such as one or more idea attribute values, one or more ideas, and a start instruction.

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

[0063] The start instruction is an instruction to start creating an idea. The start instruction includes one or more idea attribute values ​​including, for example, 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 the one or more idea attribute values ​​from, for example, the terminal device 2.

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

[0066] The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by an agent determination unit 130, a person setting unit 131, a control unit 132, a moderator judgment 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, or a score acquisition unit 139.

[0067] The agent determination unit 130 determines one or more agents. Determining an agent usually means acquiring agent information. Note that the agent information may be given in advance. In other words, the agent information may be stored in the storage unit 11 in advance.

[0068] Agent information is information about an agent. Agent information typically includes an agent identifier. An agent identifier is information that identifies an agent. An agent identifier is, for example, an occupation or specialty. Agent information includes, for example, ability information that indicates the agent's abilities.

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

[0070] The agent determination unit 130, for example, assigns a theme or the like to variables of an agent determination prompt template in the prompt management unit 112, obtains an agent determination prompt, provides 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 acquires one or more pieces of agent information from the generation AI only when the agent acquisition conditions are met. The agent acquisition conditions are conditions for acquiring an agent. The agent acquisition conditions are, for example, conditions related to the given agent information. The agent acquisition condition is, for example, that the number of pieces of given agent information is 0 or less than a threshold value.

[0072] The agent determination unit 130, for example, acquires one or more pieces of agent information paired with the theme of idea creation from an 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 person setting unit 131 obtains one or more setting prompts using a setting prompt template, and provides each of the one or more setting prompts to the generation AI.

[0074] The person setting unit 131, for example, obtains a setting prompt template from the prompt management unit 112, replaces variables of the setting prompt template with one or more pieces of agent information to configure a setting prompt, and provides the setting prompt to the generation AI. The person setting unit 131 may configure a setting prompt for each agent and provide the setting prompt for each agent to the generation AI. The person setting unit 131 may also configure a setting prompt including agent information for 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 agent information provided in advance. In other words, the person setting unit 131 may obtain a setting prompt for one or more agents determined by the agent determination unit 130, and provide the setting prompt to the generation AI.

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

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

[0077] The moderator judgment unit 133 judges whether the prompt given to the generation AI or the response from the generation AI satisfies the moderator's statement condition. The moderator's statement condition may be any transition condition.

[0078] The moderator's speaking condition is the condition for the moderator's agent to speak, and is a condition related to the prompt given to the generation AI or a condition related to the answer from the generation AI. For example, the moderator's speaking condition is "ideas have been acquired from all two or more parties" or "a certain amount of time has passed without any human input."

[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 accepted by the attribute value acceptance unit 121. The viewpoint acquisition unit 134 acquires, for example, one or more evaluation viewpoints accepted by the attribute value acceptance unit 121.

[0080] The viewpoint acquisition unit 134, for example, assigns a theme to a variable of an idea viewpoint prompt template, constructs an idea viewpoint prompt, passes the idea viewpoint prompt to the generation AI, and acquires one or more idea viewpoints from the generation AI. Note that an idea viewpoint prompt template is, for example, "Please tell me a viewpoint when creating an idea for the following theme! <theme>". Also, <theme> is a variable to which the acquired theme is assigned. A character string surrounded by "<" and ">" indicates a variable.

[0081] The viewpoint acquisition unit 134, for example, assigns a theme to a variable of an evaluation viewpoint prompt template, constructs an evaluation viewpoint prompt, passes the evaluation viewpoint prompt to the generation AI, and acquires one or more evaluation viewpoints from the generation AI. Note that the evaluation viewpoint prompt template is, for example, "Please tell me the viewpoints for evaluating ideas with the following theme! <theme>".

[0082] The viewpoint acquisition unit 134 preferably determines, for example, whether the viewpoint acquisition condition is met, and acquires the viewpoint only when it is determined that the viewpoint acquisition condition is met. The viewpoint acquisition condition is, for example, a condition related to an idea viewpoint. The viewpoint acquisition condition is, for example, a condition related to an evaluation viewpoint. The viewpoint acquisition unit 134 determines, for example, that an idea viewpoint is acquired when the number of accepted idea viewpoints is equal to or less than a threshold value. The viewpoint acquisition unit 134 determines, for example, that an evaluation viewpoint is acquired when the number of accepted evaluation viewpoints is equal to or less than a threshold value. The threshold value is a natural number equal to or greater than 1.

[0083] The idea acquisition unit 135 acquires a prompt using a phase prompt template corresponding to each of one or more phases, and gives the prompt to the generation AI to acquire two or more ideas.

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

[0085] Providing a prompt to each of one or more agents of the generated AI means, for example, providing the generated AI with a prompt that includes a character string indicating that the prompt is a query to one or more agents. Providing a prompt to the generated AI usually means executing the generated AI's API that includes the prompt as an argument.

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

[0087] For example, when the moderator judgment unit 133 judges that the moderator statement condition is satisfied, the idea acquisition unit 135 corresponds to the idea generation phase, acquires a prompt for each of one or more agents other than the moderator, gives the prompt to the generation AI, and acquires two or more ideas. It is preferable that the idea acquisition unit 135 acquires an idea from each of one or more agents not only once, but twice or more times.

[0088] The idea criticism unit 136 acquires one or more criticisms for each of the two or more ideas acquired by the idea acquisition unit 135. The criticisms may be called problems, issues, etc. The criticisms are character strings.

[0089] The idea critique unit 136, for example, assigns the idea acquired by the idea acquisition unit 135 to a variable of a critique prompt template corresponding to the idea critique phase, constructs a critique prompt, passes the critique prompt to the generation AI, and acquires one or more critiques from the generation AI. The idea critique unit 136 may also assign one or more evaluation perspectives to a variable of the critique prompt template, constructs a critique prompt, passes the critique prompt to the generation AI, and acquires one or more critiques from the generation AI.

[0090] The idea critique unit 136, for example, for each of two or more ideas acquired by the idea acquisition unit 135, assigns the idea to a variable in a critique prompt template, constructs a critique prompt, passes the critique prompt to the generation AI, and acquires one or more critiques from the generation AI.

[0091] The idea critique unit 136, for example, for each of two or more ideas and each of two or more agents acquired by the idea acquisition unit 135, assigns some or all of the idea and agent information to variables of a critique prompt template to construct a critique prompt, passes the critique prompt to the generation AI, and acquires one or more critiques from the generation AI.

[0092] The idea critique unit 136 may, for example, construct a critique prompt for each of the two or more evaluation perspectives, pass the critique prompt to the generation AI, and obtain one or more critiques from the generation AI. A critique prompt template in such a case may be, for example, "You are <name>. Please list issues or problems with the idea "<idea>" for the evaluation perspective "<evaluation perspective>" regarding <theme>." Through the above process, the idea critique unit 136 obtains one or more critiques for each of the two or more ideas and for each of the two or more evaluation perspectives.

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

[0094] The idea selection unit 137, for example, for each of two or more agents, assigns a set of two or more ideas and some or all of the agent information to variables of an idea selection prompt template to construct an idea selection prompt, provides the idea selection prompt to a generation AI, and obtains one or two or more ideas.

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

[0096] The idea selection unit 137, for example, assigns two or more ideas acquired by the idea acquisition unit 135 and one or more critiques acquired by the idea criticism unit 136 to variables of a phase prompt template corresponding to the idea selection phase, acquires a prompt, provides the prompt to the generation AI, and acquires one or more selected ideas.

[0097] The idea selection unit 137 acquires a prompt using a phase prompt template corresponding to the idea selection phase, two or more ideas acquired by the idea acquisition unit 135, and one or more ideas accepted by the idea receiving unit 122, provides 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 135 and the one or more ideas accepted by the idea receiving unit 122.

[0098] The idea selection unit 137 obtains a prompt using, for example, a phase prompt template corresponding to the idea selection phase and two or more ideas excluding ideas that the analysis unit 138 has determined do not satisfy the consideration conditions, and provides the prompt to the generation AI to obtain one or more ideas selected based on the two or more ideas obtained by the idea acquisition unit 135 and the one or more ideas received by the idea receiving unit 122.

[0099] The idea selection unit 137 corresponds to, for example, an idea selection phase, obtains a prompt using a phase prompt template for the moderator and two or more ideas obtained by the idea acquisition unit 135, provides the prompt to a generation AI, and obtains one or more ideas selected based on the two or more ideas obtained by the idea acquisition unit 135.

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

[0101] The analysis unit 138 may substitute one or more ideas received by the idea receiving unit 122 into variables of an idea analysis prompt template to construct an idea analysis prompt, pass the idea analysis prompt to the generation AI, and 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 character strings that are one or more ideas received by the idea receiving unit 122, determine whether or not the character strings correspond to "ideas," and acquire a class. Note that the technology for classifying character strings is a publicly known technology.

[0103] The score acquiring unit 139 performs natural language processing on the two or more ideas acquired by the idea acquiring unit 135 or the idea selecting unit 137, and acquires a score related to the diversity of the ideas. For example, the score acquiring unit 139 uses character strings of two or more ideas to acquire a Remote-Clique (RC value) or a Chamfer Distance (CD value), which is a score related to the diversity of the two or more ideas. The technology for acquiring the RC value and the CD value is a known technology, and therefore a detailed description thereof will be omitted.

[0104] The score acquiring unit 139 may acquire a score for each of the one or more ideas acquired by the idea acquiring unit 135 or the idea selecting unit 137. It is preferable that the score acquiring unit 139 acquires the score for the idea by using, for example, one or more critiques corresponding to the idea, which are acquired by the idea critique unit 136. It does not matter how the score acquiring unit 139 acquires the score for each idea by using the one or more critiques for each idea.

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

[0106] Also, for example, the more the number of reviews corresponding to the idea, the lower the score acquired by the score acquiring unit 139. For example, the score acquiring unit 139 calculates the score by a decreasing function using the number of reviews corresponding to the idea as a parameter.

[0107] In addition, when the score acquisition unit 139 acquires each score of 2 or more, the idea selection unit 137 may use the score to associate (rank) the two or more ideas with a ranking based on the score. The idea selection unit 137 may assign a higher ranking to an idea with a higher score.

[0108] The output unit 14 outputs various information, such as all or part of the answer passed from the generation AI, or one or more ideas.

[0109] It is preferable that the output unit 14 outputs all or part of the answer passed from the generation AI in a manner that allows the output unit 14 to grasp the current identified by the current identifier.

[0110] Here, output usually means transmission to terminal device 2, but it may also be a concept including display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and handing over the processing results to other processing devices or other programs.

[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 an idea.

[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 that makes the ranking clear.

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

[0114] The error output unit 144 outputs an error message when the analysis unit 138 determines that the review conditions are not satisfied. It is preferable that the error output unit 144 outputs an error message including an error class.

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

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

[0117] The terminal processing unit 23 performs various types of processing. For example, the various types of processing are processing for converting received information, instructions, etc. into information or instructions with a structure to be transmitted. For example, the various types of processing are processing for converting received information into information with a structure to be output.

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

[0119] The terminal receiving unit 25 receives various types of information, such as answers, ideas, scores, and error messages.

[0120] The terminal output unit 26 outputs various types of information, such as answers, ideas, scores, and error messages.

[0121] The storage unit 11, transition management unit 111, prompt management unit 112, attribute value storage unit 113, current management unit 114, and terminal storage unit 21 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0122] There is no restriction on the process by which information is stored in the storage unit 11, etc. 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 inputted 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 typically realized by wireless or wired communication means, but may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0124] The processing unit 13, agent determination unit 130, character setting unit 131, control unit 132, moderator judgment 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 device processing unit 23 can usually be realized by a processor, memory, etc. The processing procedure of the processing unit 13, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). The processor is a CPU, MPU, GPU, etc., and the type is not important.

[0125] The output unit 14, the answer output unit 141, the idea output unit 142, the score output unit 143, and the error output unit 144 are usually realized by wireless or wired communication means, but may also be realized by driver software for an output device such as a display or speaker, or by a combination of driver software for an output device and an output device, etc.

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

[0127] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0128] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

[0129] The terminal output unit 26 may be considered to include, or may not include, an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or a combination of driver software for an output device and an output device, etc.

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

[0131] (Step S401) The attribute value receiving unit 121 judges whether or not a start instruction has been received. If a start instruction has been received, the process proceeds to step S402, and if not, the process returns to step S401.

[0132] (Step S402) The processing unit 13 performs pre-processing. An example of the pre-processing will be described with reference to the flowchart of FIG.

[0133] (Step S403) The viewpoint acquisition unit 134 judges whether or not to acquire a viewpoint. If a viewpoint is to be acquired, the process proceeds to step S404, and if not, the process 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 with reference to the flowchart of FIG.

[0135] (Step S405) The idea acquisition section 135 performs an idea acquisition process. An example of the idea acquisition process will be described with reference to the flowchart of FIG.

[0136] (Step S406) The control unit 132 acquires a transition condition for moving from the idea generation phase to the next phase from the transition management unit 111. The control unit 132 judges whether or not the transition condition is satisfied. If the transition condition is satisfied, the process proceeds to step S407, and if the transition condition is not satisfied, the process 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 an idea criticism phase. If it is the idea criticism phase, the process proceeds to step S408. If it is not the idea criticism phase, the process proceeds to step S410. Here, the control unit 132 accumulates the phase identifier of the next phase in the current management unit 114.

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

[0139] (Step S409) The control unit 132 acquires a transition condition for moving from the idea criticism phase to the next phase from the transition management unit 111, and judges whether the transition condition is satisfied. If the transition condition is satisfied, the process proceeds to step S410, and if the transition condition is 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 with reference to the flowchart in Fig. 12. Here, the control unit 132 accumulates 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 acquired in step S410. Return to step S401. Note that the idea output unit 142 transmits one or more ideas to the terminal device 2, for example.

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

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

[0144] In the flowchart of FIG. 4, the answer output unit 141 may output all or part of the answer acquired from the generation AI.

[0145] In the flowchart of FIG. 4, the process ends when the power is turned off or an interrupt occurs to end the process.

[0146] Next, an example of the pre-processing in step S402 will be described with reference to the flowchart in FIG.

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

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

[0149] (Step S503) The processing unit 13 acquires one or more evaluation aspects included in the start instruction. Note that here, the processing unit 13 does not have to acquire the evaluation aspects.

[0150] (Step S504) The agent determination unit 130 judges whether or not agent information is present in the information acquired in step S501. If agent information is present, the process proceeds to step S505, and if not, the process proceeds to step S506.

[0151] (Step S505) The agent determination unit 130 acquires one or more pieces of agent information from the information acquired in step S501. Then, the process proceeds to step S507.

[0152] (Step S506) The agent determination unit 130 performs an agent determination process. An example of the agent determination process will be described with reference to the flowchart of FIG.

[0153] (Step S507) The person setting unit 131 performs a person setting process. Then, the process returns to the upper level process. An example of the person setting process will be described with reference to the flowchart in FIG.

[0154] In the flowchart of Fig. 5, when the start instruction does not have agent information, the agent determination unit 130 acquires agent information through the agent determination process. However, in the flowchart of Fig. 5, when the amount of agent information included in the start instruction is equal to or less than the threshold value or is less than the threshold value, the agent determination unit 130 may acquire agent information through the agent determination process.

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

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

[0157] (Step S602) The agent determining unit 130 acquires the accepted theme and the like.

[0158] (Step S603) The agent determination unit 130 assigns the theme and the like acquired in step S602 to the variables of the agent determination prompt template acquired in step S601, and acquires an agent determination prompt.

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

[0160] (Step S605) The agent determination unit 130 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S606, and if an answer has not been acquired, the process returns to step S605.

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

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

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

[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 facilitator. Note that the agent information of the facilitator may be included in the start instruction or may be stored in the storage unit 11 in advance.

[0166] (Step S703) The person setting unit 131 assigns the agent information of the facilitator acquired in step S702 to the variable of the setting prompt template acquired in step S701, and acquires the setting prompt of the facilitator.

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

[0168] (Step S705) The person setting unit 131 assigns 1 to a counter i.

[0169] (Step S706) The person setting unit 131 judges whether or not the i-th agent information, excluding the agent information of the facilitator, exists among the acquired agent information. If the i-th agent information exists, the process proceeds to step S707, and if not, the process returns to the upper processing.

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

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

[0172] (Step S709) The person setting unit 131 gives the setting prompt of the i-th agent acquired in step S708 to the generation AI.

[0173] (Step S710) The person setting unit 131 increments the counter i by 1. The process returns to step S706.

[0174] Next, an example of the viewpoint acquisition process in step S404 will be described with reference to the flowchart in FIG.

[0175] (Step S801) The viewpoint acquiring unit 134 acquires an idea viewpoint prompt template from the prompt managing unit 112.

[0176] (Step S802) The viewpoint acquiring unit 134 acquires a theme, etc., which is information to be substituted into the idea viewpoint prompt template acquired in step S801. The viewpoint acquiring unit 134 assigns the theme, etc., to the idea viewpoint prompt template to acquire an 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 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S805, and if an answer has not been acquired, the process returns to step S804.

[0179] (Step S805) The viewpoint acquiring unit 134 acquires one or more idea viewpoints from the answer acquired from the generating 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, etc., which is information to be substituted into the evaluation viewpoint prompt template acquired in step S807. The viewpoint acquiring unit 134 assigns the theme, etc., to the evaluation viewpoint prompt template to acquire 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 judges 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 acquiring 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 viewpoints acquired in step S811. The answer output unit 141 transmits the one or more evaluation viewpoints 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 obtaining unit 135 assigns 1 to a counter i.

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

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

[0192] (Step S905) The idea acquiring section 135 assigns a part or all of the i-th agent information to the variables of the idea generating prompt template, and acquires an idea generating prompt for the i-th agent.

[0193] (Step S906) The idea acquiring unit 135 gives the idea generating prompt acquired in step S905 to the generating AI.

[0194] (Step S907) The idea acquiring unit 135 judges whether or not an answer has been acquired from the generating AI. If an answer has been acquired, the process proceeds to step S908, and if an answer has not been acquired, the process returns to step S907.

[0195] (Step S908) The idea acquiring unit 135 acquires one or more ideas from the answers acquired in step S907.

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

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

[0198] (Step S911) The idea acquiring unit 135 judges whether or not to accept an input of an idea from a person. If an input of an idea from a person is accepted, the process proceeds to step S912, and if not, the process returns to the upper process.

[0199] (Step S912) The idea obtaining unit 135 assigns 1 to a counter i.

[0200] (Step S913) The idea acquiring unit 135 judges whether or not there is an i-th person who inputs an idea. If there is an i-th person, the process proceeds to step S914, and if there is no i-th person, the process returns to the upper process.

[0201] (Step S914) The idea acquisition unit 135 judges whether or not one or more ideas have been received from a person. If an idea has been received, the process proceeds to step S915, and if not, the process returns to step S914. Note that if a timeout occurs here, the process may proceed to S919. Also, receiving an idea from a person is, for example, receiving an idea from the terminal device 2.

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

[0203] (Step S916) The idea obtaining section 135 judges whether or not the analysis result in step S915 was an “error.” If it is an “error,” the process proceeds to step S918, and if it is not an “error,” the process proceeds to step S917.

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

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

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

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

[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 assigns 1 to a counter i.

[0210] (Step S1003) The analysis unit 138 judges whether or not the i-th idea exists. If the i-th idea exists, the process proceeds to step S1004, and if not, the process 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, and acquires 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 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S1008, and if an answer has not been acquired, the process returns to step S1007.

[0215] (Step S1008) The analysis unit 138 obtains an analysis result (for example, "normal" or "error") from the answer 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. The process returns to step S1003.

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

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

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

[0220] (Step S1103) The idea critique unit 136 judges whether or not the i-th idea to be critiqued exists. If the i-th idea exists, the process proceeds to step S1104, and if not, the process returns to the upper process.

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

[0222] (Step S1105) The idea criticism unit 136 judges whether or not the jth agent exists. If the jth agent exists, the process proceeds to step S1106, and if not, the process proceeds to step S1113.

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

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

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

[0226] (Step S1109) The idea criticism unit 136 judges whether or not an answer has been obtained from the generating AI. If an answer has been obtained, the process proceeds to step S1110, and if not, the process returns to step S1109.

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

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

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

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

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

[0232] (Step S1201) The idea selecting unit 137 acquires an idea selection prompt template from the prompt managing unit 112.

[0233] (Step S1202) The idea selection unit 137 acquires an idea acquired by the idea acquisition unit 135, or an idea acquired by the idea acquisition unit 135 and an idea accepted by the idea acceptance unit 122. It is preferable that the idea selection unit 137 acquires one or more criticisms acquired by the idea criticism unit 136.

[0234] (Step S1203) The idea selection unit 137 assigns two or more ideas, or two or more ideas and one or more reviews, to the idea selection prompt template acquired in step S1201, to acquire an idea selection prompt.

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

[0236] (Step S1205) The idea selection unit 137 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S1206, and if an answer has not been acquired, the process returns to step S1205.

[0237] (Step S1206) The idea selection unit 137 acquires one or more ideas from the answers acquired in step S1205. The process returns to the upper level process. Note that, here, it is preferable that the idea selection unit 137 acquires two or more ranked ideas.

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

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

[0240] In FIG. 13, if the number of idea perspectives and the number of evaluation perspectives included in the start instruction satisfy the transition condition of "ID=1", the "idea perspective / evaluation perspective consideration" phase is skipped.

[0241] In the record of "ID=2" in Figure 13, two pairs of "transition condition" and "next phase identifier" correspond to one phase identifier "idea generation". In other words, the record of "ID=2" indicates that the phase "idea generation" will transition to a different next phase depending on the matching transition condition. The record of "ID=2" indicates that branching is possible in the phase transition.

[0242] Furthermore, 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 a "prompt template identifier" and a "prompt template". Each of the "prompt template identifiers" may correspond to a phase identifier. The "idea perspective prompt template" and the "evaluation perspective prompt template" correspond to the phase identifier "idea perspective / evaluation consideration". The "idea generation prompt template" corresponds to the phase identifier "idea generation". The "idea criticism prompt template" corresponds to the phase identifier "idea criticism". The "idea selection prompt template" corresponds to the phase identifier "idea selection". The "idea generation prompt template" has a variable <idea perspective> and a variable <evaluation perspective>, but does not have to have the variable <evaluation perspective>. The "idea criticism prompt template" may have a variable <evaluation perspective>. In such a case, the "idea critique prompt template" might be, for example, "You are <name>. Regarding <topic>, please list the challenges and problems with the idea "<idea>" while taking into consideration the following idea evaluation criteria: [Evaluation criteria] <Evaluation criteria>."

[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 generation AI, and creates a solution using AI and a camera. <Theme> Solution using AI and a camera <Agent><Name> Mr. A <Agent name> AI engineer <Role> Utilizing AI-related technologies, promote the use of AI in ideas and products and improve problem-solving capabilities. <Persona> ['Has deep knowledge and experience of AI technologies such as machine learning, deep learning, and natural language processing', 'Skilled in preprocessing of data sets, training and evaluation of models, and deployment of AI solutions', 'Conscious of working on development that takes into account the ethical aspects and social impact of AI']< / エージェント> " is input to terminal device 2.

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

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

[0246] That is, the processing unit 13 obtains the theme "Solution using AI and a camera" contained in the start instruction. The processing unit 13 also attempts to obtain an idea perspective and an evaluation perspective from the start instruction, but is unable to do so. Next, the agent determination unit 130 obtains an agent determination prompt template from the prompt management table (FIG. 14). The agent determination unit 130 obtains the theme and "<agent><name>Mr. A <agent name>AI Engineer..." from the start instruction.< / エージェント> ". Then, the agent determination unit 130 assigns "Solution using AI and a camera" to the variable <theme> of the agent determination prompt template, assigns "AI engineer" of the <agent name> to the variable <user-specified agent>, and acquires an agent determination prompt. Next, the agent determination unit 130 passes the agent determination prompt to the generation AI. Next, the agent determination unit 130 acquires an answer from the generation 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 agent information of "AI engineer" given by the user U, and the agent information of "data scientist" and "sales" which are the answers from the generation AI.

[0247] Next, the person setting unit 131 performs the person setting process according to the process described using the flowchart in FIG. 7 as follows. That is, the person setting unit 131 acquires a setting prompt template from the prompt management table (FIG. 14). The person 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 person, and passes the setting prompt to the generation AI. As a result, the person setting of an AI engineer, data science, and sales has been completed. In addition, the person setting unit 131 acquires the agent information of the moderator from the storage unit 11, performs the same process, and sets the moderator as a person. With the above, the pre-processing is completed.

[0248] Next, the viewpoint acquisition unit 134 determines that the start instruction does not include an idea viewpoint and an evaluation viewpoint, and therefore satisfies the idea viewpoint acquisition condition (the number of idea viewpoints included in the start instruction<=threshold a) and the evaluation viewpoint acquisition condition (the number of evaluation viewpoints included in the start instruction<=threshold b). Then, the viewpoint acquisition unit 134 acquires an idea viewpoint prompt template from the prompt management table (FIG. 14). The viewpoint acquisition unit 134 acquires a <theme> and an <input idea viewpoint> to be substituted into the idea viewpoint prompt template. Note that the <input idea viewpoint> is not acquired here. The viewpoint acquisition unit 134 assigns the theme to the idea viewpoint prompt template and acquires an idea viewpoint prompt. The viewpoint acquisition unit 134 provides the idea viewpoint prompt to the generation AI. Then, it is assumed that the viewpoint acquisition unit 134 has acquired, for example, the idea viewpoints "entry market" and "technological innovativeness".

[0249] The viewpoint acquisition unit 134 also acquires an evaluation viewpoint prompt template from the prompt management table (FIG. 14). The viewpoint acquisition unit 134 acquires a <theme> and an <input evaluation viewpoint> to be substituted into the evaluation viewpoint prompt template. Note that the <input evaluation viewpoint> is not acquired here. The viewpoint acquisition unit 134 assigns the theme to the evaluation viewpoint prompt template to acquire an evaluation viewpoint prompt. The viewpoint acquisition unit 134 provides the evaluation viewpoint prompt to the generation AI. Then, it is assumed that the viewpoint acquisition unit 134 has obtained, for example, the evaluation viewpoints "technical feasibility," "user convenience," and "market needs."

[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 generation prompt template from the prompt management table (FIG. 14). The idea acquisition unit 135 also acquires the names "Mr. A, Mr. S, and Mr. X" that are acquired as agent information and are included in the agent information other than the moderator. The idea acquisition unit 135 also acquires a theme "Solution using AI and a camera." The idea acquisition unit 135 also acquires the idea perspectives "entry market," "technical innovativeness," and evaluation perspectives "technical feasibility," "user convenience," and "market needs" that have been acquired. Next, the idea acquisition unit 135 assigns "name," "theme," "idea perspective," and "evaluation perspective" to each variable of the idea generation prompt template for each of the three names, and acquires three idea generation prompts. Then, the idea acquisition unit 135 gives each of the three idea generation 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, the idea acquisition unit 135 acquires the ideas "smart assist glasses," "AI-driven traffic monitoring system," and "personalized retail experience system."

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

[0252] Next, the terminal device 2 receives and outputs the prompt, answer, and the like transmitted from the creation support device 1. An example of such output is shown in FIG.

[0253] The current management unit 114 of the creation support device 1 stores a phase identifier "idea generation". That is, in the flow of creating ideas, the current phase is "idea generation". As shown in 1601 of Fig. 16, the output unit 14 transmits the answer (idea, etc.) passed from the generation AI in a manner that allows the output unit 14 to grasp the current "idea generation" identified by the current identifier.

[0254] Next, the idea acquiring unit 135 determines that the first person to input an idea exists. Then, the output unit 14 transmits, to the terminal device 2 of the user U, screen information that prompts the user U to input an idea.

[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, the user U enters an idea such as "customer estimation smart register system" into the idea input field 1701 and presses the send button 1702.

[0256] Next, the idea acquisition unit 135 receives the idea "customer estimation smart cash register system" from the terminal device 2. Next, 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 "customer estimation smart cash register system."

[0257] Next, the control unit 132 acquires two transition conditions for moving from the idea generation phase to the next 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. The control unit 132 also acquires "Someone has an idea". Next, the control unit 132 determines that neither of the two transition conditions is satisfied.

[0258] Then, the idea acquisition unit 135 acquires idea generation prompts requested by the moderator from each of A, S, and X, passes each prompt to the generation AI, and acquires answers. Next, the idea acquisition unit 135 acquires the 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] In addition, the output unit 14 transmits to the terminal device 2 the prompt given to the generating AI and the idea obtained from the answer.

[0260] Next, the terminal device 2 receives and outputs the prompt given to the generating AI. The terminal device 2 also receives and outputs the idea.

[0261] Next, the control unit 132 acquires two transition conditions for moving from the idea generation phase to the next phase from the transition management table (FIG. 14), and determines that the acquired number of ideas, "7", satisfies the transition condition "number of ideas >= x3". In other words, "x3" is a natural number equal to or less than 7.

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

[0263] Then, the control unit 132 updates the current in the current management unit 114 to "Idea Criticism."

[0264] Next, the idea critique unit 136 performs the idea critique process described using the flowchart of FIG. 11. That is, the idea critique unit 136 acquires an idea critique prompt template from the prompt management table (FIG. 14). The idea critique unit 136 also acquires the names "Mr. A, Mr. S, Mr. X" that each agent information has. The idea critique unit 136 also acquires the theme "Solution using AI and a camera". The idea critique unit 136 also acquires the seven acquired ideas. The idea critique unit 136 assigns "name", "theme" and "idea" to the idea critique prompt template for each idea and for each agent name, and acquires an idea critique prompt. The idea critique unit 136 acquires, for example, an idea critique prompt "You are Mr. A. Please give us some issues or problems with the idea "Smart Assist Glasses" in relation to "Solution using AI and a camera". Next, the idea critique unit 136 passes each idea critique prompt to the generation AI. The output unit 14 transmits the prompt given to the generation AI to the terminal device 2. In addition, 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 acquired one or more criticisms to the terminal device 2. The output unit 14 transmits the one or more criticisms passed from the generation AI in a manner that allows the output unit 14 to grasp the current identified by the current identifier.

[0265] The terminal device 2 receives and outputs the idea criticism prompt. The terminal device 2 also 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 "Mr. A's" criticism of the idea "Smart Assist Glasses." Also, in FIG. 18, it is clearly indicated that the current is "Idea Criticism" (1802).

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

[0267] Next, the control unit 132 acquires the transition condition "number of reviews >= x5" for moving from the idea criticism phase to the next phase from the transition management table (FIG. 13), and determines that the transition condition is satisfied. It is assumed that the control unit 132 acquires the number of acquired reviews, "21", and determines that "number of reviews >= x5" is satisfied.

[0268] Next, the idea selection unit 137 performs the idea selection process described using the flowchart of FIG. 12. That is, the idea selection unit 137 acquires an idea selection prompt template from the prompt management table (FIG. 14). The idea selection unit 137 acquires all the ideas acquired by the idea acquisition unit 135 and accepted by the idea acceptance unit 122. Here, the set of ideas is seven, namely, "Smart Assist Glasses," "AI-Driven Traffic Monitoring System," "Personalized Retail Experience System," "Customer Estimation Smart Register System," "Smart Security Monitoring System," "AI-Driven Real-Time Traffic Optimization System," and "AI-Driven Personal Shopping Assistant." In addition, the idea selection unit 137 acquires the acquired 21 reviews. Next, the idea selection unit 137 assigns the seven ideas to the variable <Idea Set> of the idea selection prompt template, assigns the acquired 21 reviews to the variable <Previous Review>, and acquires 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 acquires an answer from the generation AI. Next, the idea selection unit 137 acquires one or more ideas from the answer. Here, the idea selection unit 137 acquires seven ideas that have been ranked from the answer.

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

[0270] The terminal device 2 receives the idea selection prompt and outputs it. The terminal device 2 also receives information on seven ranked ideas and outputs it. 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 indicated that the current is "idea selection" (1903).

[0271] As described above, according to this embodiment, it is possible to support the creation of appropriate ideas using a generation AI.

[0272] Furthermore, according to this embodiment, collaboration between humans and generative AI can help create appropriate ideas.

[0273] Moreover, according to the present embodiment, input by an inappropriate person can be excluded. Moreover, according to the present embodiment, when an input by an inappropriate person is detected, the person can be notified that the input is inappropriate.

[0274] Furthermore, according to this embodiment, the moderator agent can assist in creating more appropriate ideas using the generation AI.

[0275] Furthermore, according to this embodiment, the moderator agent can give appropriate prompts to the generation AI at appropriate timing.

[0276] Furthermore, according to this embodiment, the flow of discussion for generating appropriate ideas using generative AI can be presented in an easy-to-understand manner.

[0277] In this embodiment, as described above, the score acquisition unit 139 may acquire the score of 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 score of each of the ideas. For example, when the theme is "new project ideas for soft drinks," the idea acquisition unit 135 acquires five ideas, "Tropical Coconut (expected to grow due to increasing inbound demand)," "Refreshing Sadistic (demand is expected to increase due to nutritional deficiencies among young people)," "Refreshing Grapefruit (demand is expected to increase due to the aging population)," "Secret Orange (expected to grow due to increasing popularity of e-sports)," and "Anonymous Grape (office population is at an all-time high, but differentiation from other companies is an issue)," by the above-mentioned process. Next, the idea critique unit 136 acquires one or more critiques for each of the five ideas and for each evaluation perspective by the above-mentioned process. Next, the score acquisition unit 139 ranks each of the five ideas by evaluation perspective by the above-mentioned process. Here, it is assumed that the evaluation perspectives are "market size," "growth potential," and "barriers to entry." The score acquisition unit 139 then acquired the rankings of the five ideas in each of the three perspectives as follows: 1.Market size 1. Refresh Sadistic (The youth nutritional supplement market is the largest at approximately 300 billion yen) 2nd place: Refreshing Grapefruit (The beverage market for seniors is relatively large at about 80 billion yen) 3. Anonymous Grape (medium-sized office drinking water market of 110 billion yen) 4. Tropical Coconut (The specific market size for resort drinks is unknown) 5. Secret Orange (The eSports-related market is relatively small at 143 billion yen) 2. Growth potential 1st place: Tropical coconut (expected to grow due to rising inbound demand) 2nd place: Refresh Sadistic (Demand is expected to increase due to nutritional deficiencies among young people) 3. Refreshing Grapefruit (Demand is expected to increase due to the aging population) 4. Secret Orange (Expected to grow due to the growing popularity of e-sports) 5. Anonymous Grape (Office population at an all-time high, but differentiation from other companies is an issue) 3. Barriers to entry? 1. Anonymous Grape (There are many similar plain plastic bottle products on the market) 2. Refresh Sadistic (Difficult to differentiate as many manufacturers have already entered the market) 3. Tropical coconut (stable supply is an issue due to seasonal and regional fluctuations in demand) 4. Refreshing Grapefruit (A market in which major manufacturers have already entered aggressively) 5. Secret Orange (Although similar products exist, there is still room for new entrants)

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

[0279] In terms of scores for each evaluation criteria, 1st place was 33.3 points, 2nd place was 25.0 points, 3rd place was 16.6 points, 4th place was 8.3 points, and 5th place was 0.0 points.

[0280] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software that realizes the creation support device 1 in this embodiment is a program as follows. That is, this program causes a computer that can access a prompt management unit that stores 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 generation AI in each of two or more phases including an idea generation phase and an idea selection phase, and an attribute value storage unit that stores one or more idea attribute values ​​that are attribute values ​​related to the idea to be created, The program functions as a character setting unit that obtains one or more setting prompts using the setting prompt template and provides each of the one or more setting prompts to the generation AI; an idea acquisition unit that obtains a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, provides the prompt to each of the one or more agents of the generation AI, and obtains two or more ideas; an idea selection unit that obtains 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, provides the prompt to the generation AI, and obtains 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 supports two or more parties, including one or more personas of a generation AI and one or more people, to generate ideas on a specific theme and recruits people to generate ideas will be described. Note that the parties in this embodiment include people.

[0282] In this embodiment, a creation support device that performs a process for giving a reward to a person who submits an idea will be described. Note that, here, a person who submits an idea will be referred to as a proposer as appropriate.

[0283] In this embodiment, a creation support device will be described that accepts a theme for which ideas are to be submitted and offers ideas to people who are likely to be suited to that theme.

[0284] In this embodiment, a creation support device that evaluates ideas submitted by people and ranks people will be described.

[0285] The conceptual diagram of information system B in this embodiment is the same as that of Fig. 1, except for the reference numeral for the creation support device. Information system B comprises a creation support device 4, one or more terminal devices 2, and a generation AI device 3. Note that the generation AI device is an external device to information system B, and it may be considered that information system B does not have a generation AI device 3.

[0286] The creation support device 4 is, for example, a cloud server or an ASP server, but the type is not important. The creation support device 4 may have one or more generation AIs. In such a case, the information system B may not have the generation AI device 3.

[0287] The creation support device 4 and one or more terminal devices 2, and the creation support device 4 and the generation AI device 3, can communicate with each other via a network such as the Internet.

[0288] FIG. 20 is a block diagram of the creation support device 4 constituting the information system B in this embodiment.

[0289] The creation support device 4 includes a storage unit 41, a reception unit 12, a processing unit 43, and an output unit 44. The storage unit 41 includes a transition management unit 111, a prompt management unit 112, an attribute value storage unit 113, a current management unit 114, and a human resources management unit 411. The reception unit 12 includes an attribute value reception unit 121 and an idea reception unit 122. The processing unit 43 includes an agent determination unit 130, a person setting unit 131, a recruitment processing unit 431, a control unit 132, a moderator judgment 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, an evaluation unit 432, a ranking unit 433, and a reward processing unit 434. The recruitment processing unit 431 includes a candidate determination means 4311, an offer means 4312, and a proposer determination means 4313. The output section 44 includes an answer output section 141 , an idea output section 142 , a score output section 143 , an error output section 144 , an evaluation output section 441 , and a rank output section 442 .

[0290] Various types of information are stored in the storage unit 41 constituting the creation support device 4. The various types of information are, for example, transition information, a prompt template, an idea attribute value, a current identifier, and human resource information to be described later.

[0291] Here, the phase prompt template stored in the prompt management unit 112 may be only a phase prompt template corresponding to the idea generation phase. That is, in this embodiment, the phase may be only the idea generation phase.

[0292] The human resources management unit 411 stores one or more pieces of human resources information. The human resources information is information about candidates who submit ideas. Candidates are people who have the potential to become proposers who submit ideas. Candidates may simply be called people. The human resources information has one or more pieces of theme information and a person identifier. The human resources information may also have notification destination information, points, rank, account information, and electronic money information.

[0293] The theme information is information about a theme on which a candidate can provide an idea. The theme information may be a theme, a field of the theme, or a keyword indicating the characteristics of the theme. The theme information may be any information related to a theme.

[0294] A person identifier is information that identifies a person. Examples of a person identifier include a candidate's ID, email address, phone number, and name.

[0295] The notification destination information is information that identifies the notification destination. The notification destination information is, for example, the candidate's ID, email address, and telephone number. The notification destination information may be the same as the person identifier.

[0296] Points are points that a person possesses. Points can be rewards. Points can be accumulated points that have been given up until now.

[0297] A rank is information indicating the rank of a person. The rank may be, for example, five levels or three levels. The five levels of rank are expressed, for example, by any natural number from "1" to "5." The three levels of rank are, for example, "A," "B," or "C."

[0298] Account information is information for paying remuneration (e.g., money) to a person. Account information is, for example, bank account information (e.g., bank name, account number, etc.). Account information may be considered to include electronic money information. Electronic money information has a user ID for electronic money (e.g., Paypay (registered trademark)).

[0299] The receiving unit 12 here receives, for example, an idea creation request and permission information.

[0300] An idea creation request is a request to create an idea. The idea creation request includes a theme. The idea creation request includes, for example, deadline information, a budget, and offer conditions. Deadline information is information that specifies the deadline for which the idea is proposed. The budget is the amount that a user who wishes to create an idea must pay when receiving a proposed idea. The budget may be determined in advance, or may be specified by the user. Offer conditions are conditions for making an offer to become a proposer. Offer conditions are usually conditions related to the attribute values ​​of a candidate. The attributes of a candidate are, for example, theme information, points, or rank that are contained in human resources information.

[0301] The permission information is information indicating permission to participate in idea generation. The permission information is, for example, information indicating a response to an offer. The permission information usually has a person identifier. The permission information has, for example, a theme identifier. The theme identifier is information that identifies a theme. The theme identifier is, for example, a theme ID, a theme name, or the theme itself.

[0302] The processing unit 43 performs various types of processing. The various types of processing are, for example, processing performed by the agent determination unit 130, the character setting unit 131, the recruitment processing unit 431, the control unit 132, the moderator judgment 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 evaluation unit 432, the ranking unit 433, and the reward processing unit 434.

[0303] The solicitation processing unit 431 performs a solicitation process and determines one or more proposers. A proposer is a person who submits an idea for a theme.

[0304] The solicitation process is a process for soliciting people to submit ideas regarding a theme. The solicitation process is, for example, a process for storing the theme for which ideas are to be submitted in the storage unit 41. The solicitation process is, for example, a process for making the theme for which ideas are to be submitted accessible from one or more terminal devices 2. The process for making the theme accessible is, for example, storing the theme in a memory area accessible by one or more terminal devices 2. The solicitation process is, for example, a process for transmitting the theme for which ideas are to be submitted to one or more candidates. The solicitation process is, for example, a process performed by the candidate determination means 4311, the offer means 4312, and the proposer determination means 4313.

[0305] The candidate determination means 4311 refers to the human resources management unit 411 and acquires one or more person identifiers that identify candidates who are people corresponding to the theme. The candidate determination means 4311 acquires, for example, from the human resources management unit 411, one or more person identifiers that are paired with theme information corresponding to the theme for which ideas are to be submitted.

[0306] Theme information corresponding to a theme is, for example, theme information including the theme from which ideas are generated, theme information whose similarity to the theme is equal to or greater than a threshold, theme information including words (e.g., keywords) included in the theme, and theme information including a character string that matches the field to which the theme belongs.

[0307] The offering means 4312 makes an offer to submit an idea related to the theme to each of the one or more candidates acquired by the candidate determination means 4311. The offering means 4312, for example, acquires notification destination information corresponding to the personal identifier of each of the one or more candidates acquired by the candidate determination means 4311 from the human resources management unit 411, and transmits offer information to each of the one or more candidates using the notification destination information.

[0308] Offer information is information requesting someone to be a proposer of an idea. Offer information usually includes a theme. Offer information includes, for example, an offer string (e.g., "We will hold an idea discussion meeting on <theme>. As you have deep knowledge of <theme>, we would like you to participate in this idea discussion meeting..."). The theme for which the idea is to be submitted is substituted for the variable <theme> in the offer string.

[0309] The proposer determination means 4313 receives permission information from one or more candidates among the one or more candidates, and determines a proposer corresponding to the permission information. The proposer corresponding to the permission information is a person who has transmitted the permission information.

[0310] The proposer determination means 4313, for example, receives permission information from one or more candidates, and acquires a person identifier corresponding to the permission information.

[0311] The proposer determination means 4313, for example, receives consent information from one or more candidates, determines whether the proposer who sent the consent information satisfies the employment conditions, and if the employment conditions are satisfied, obtains a person identifier that identifies the proposer.

[0312] The adoption conditions are conditions for a proposer who submits an idea. The adoption conditions are usually conditions set by a user who wishes to create an idea, but may be conditions set in the idea creation support device 4. Examples of the adoption conditions are "rank is above a threshold" and "the number of proposers is below a threshold." The adoption conditions may be the same as the offer conditions.

[0313] The idea selection unit 137 here normally acquires one or more ideas selected based on one or more ideas acquired by the idea acquisition unit 135 and one or more ideas accepted from the proposer by the idea acceptance unit 122. Note that the creation support device 4 does not need to have the idea selection unit 137.

[0314] The evaluation unit 432 acquires evaluation information that is an evaluation of the idea received by the idea receiving unit 122 from the proposer.

[0315] The evaluation information is information related to the evaluation of an idea. The evaluation information is information specifying the evaluation of an idea. The evaluation information is, for example, an evaluation value, information indicating whether an idea is good or bad, or a score of an idea. That is, the evaluation unit 432 may be the score acquisition unit 139. The score acquisition unit 139 may acquire the score for the idea accepted by the idea accepting unit 122 by the above-mentioned process.

[0316] For example, when an idea accepted by the idea accepting unit 122 is selected by the idea selecting unit 137, the evaluation unit 432 acquires evaluation information, which is a score for the idea.

[0317] The evaluation unit 432, for example, substitutes the idea accepted from the proposer for the variable <idea> of a prompt template such as "Please rate the ideas below and provide an evaluation value. Please provide an evaluation value on a five-level scale, with "5" being the highest level. [Idea] <idea>", constructs a prompt, passes the prompt to the generation AI, and obtains evaluation information, which is the evaluation value, from the generation AI.

[0318] The evaluation unit 432, for example, obtains one or more parameters from the idea accepted from the proposer, and obtains evaluation information, which is an evaluation value, using the one or more parameters. The parameters are, for example, the number of ideas, the number of characters contained in the idea, and the number of technical terms contained in the idea. The process of obtaining technical terms from a character string is a publicly known technique (for example, "TermExtract").

[0319] The ranking unit 433 acquires a rank for the person who submitted the idea, using the evaluation information acquired by the evaluation unit 432. The ranking unit 433 acquires a higher rank for a person corresponding to higher evaluation information.

[0320] The reward processing unit 434 performs reward processing for giving a reward to the proposer. For example, the reward processing unit 434 determines the amount of reward to be given to the proposer and performs reward processing for giving the amount of reward to the proposer.

[0321] The reward process is a process for giving rewards. The reward process is, for example, a process of increasing points paired with a person identifier that identifies a proposer, a process of transferring money to a bank account specified by account information paired with a person identifier that identifies a proposer, and a process of transferring electronic money to a user by using a user ID included in electronic money information paired with a person identifier that identifies a proposer.

[0322] The output unit 44 outputs various information, such as all or part of the answer passed from the generation AI, or one or more ideas.

[0323] Here, output usually means transmission to terminal device 2, but it may also be a concept including display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and handing over the processing results to other processing devices or other programs.

[0324] The evaluation output unit 441 outputs the evaluation information acquired by the evaluation unit 432. For example, the evaluation output unit 441 stores the evaluation information in a pair with a person identifier. For example, the evaluation output unit 441 transmits the evaluation information to the terminal device 2 corresponding to the person identifier.

[0325] The rank output unit 442 outputs the rank acquired by the ranking unit 433. For example, the rank output unit 442 stores the rank in a pair with the person identifier. For example, the rank output unit 442 transmits the rank to the terminal device 2 corresponding to the person identifier.

[0326] The idea output section 142 here outputs, for example, the ideas acquired by the idea acquisition section 135 and the ideas acquired by the idea reception section 122. The idea output section 142 here outputs one or more ideas acquired by the idea selection section 137 in addition to the ideas acquired by the idea acquisition section 135 and the ideas acquired by the idea reception section 122, or instead of the ideas acquired by the idea acquisition section 135 and the ideas acquired by the idea reception section 122.

[0327] The storage unit 41 and the personnel management unit 411 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0328] There is no restriction on the process by which information is stored in the storage unit 41, etc. For example, information may be stored in the storage unit 41, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 41, etc., or information inputted via an input device may be stored in the storage unit 41, etc.

[0329] The processing unit 43, the recruitment processing unit 431, the evaluation unit 432, the ranking unit 433, the reward processing unit 434, and the candidate selection means 4311 can usually be realized by a processor, a memory, or the like. The processing procedure of the processing unit 43, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, or the like, and the type is not important.

[0330] The offer means 4312 and the proposer determination means 4313 are realized, for example, by wireless or wired communication means.

[0331] The output unit 44, the evaluation output unit 441, and the rank output unit 442 are usually realized by wireless or wired communication means.

[0332] Next, an example of the operation 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 those in the flowchart of FIG. 4 will be omitted. Also, in the flowchart of FIG. 21, if a start instruction is not accepted in S401, the process proceeds to step S2104. Also, in the flowchart of FIG. 21, the acceptance of a start instruction in S401 means, for example, that it is time to start coming up with ideas. The start time is, for example, a time that is set automatically or manually.

[0333] (Step S2101) The idea acquisition section 135 performs an idea acquisition process. An example of the idea acquisition process will be described with reference to the flowchart of FIG.

[0334] (Step S2102) The reward processing unit 434 performs reward processing. An example of the reward processing will be described with reference to the flowchart in FIG.

[0335] (Step S2103) The ranking unit 433 performs a rank acquisition process. Return to step S401. An example of the rank acquisition process will be described with reference to the flowchart in Fig. 25. The rank acquisition process is a process for determining the rank of a proposer.

[0336] (Step S2104) The reception unit 12 judges whether or not an idea creation request has been received from the terminal device 2 of a user who wishes to create an idea. If an idea creation request has been received, the process proceeds to step S2103, and if not, the process proceeds to step S2107.

[0337] (Step S2105) The processing unit 43 acquires a unique theme identifier. The processing unit 43 stores requested theme information having the theme identifier. The processing unit 43 stores the requested theme information in the storage unit 11, for example.

[0338] The requested theme information is information about a theme for which an idea creation request has been received. The requested theme information includes, for example, a user identifier of the requesting user, a theme, a theme identifier, deadline information, a budget, and an offer condition.

[0339] (Step S2106) The solicitation processing unit 431 performs an offer process. An example of the offer process will be described with reference to the flowchart in Fig. 26. The offer process is a process for soliciting people to submit ideas on a theme for which an idea creation request has been received.

[0340] (Step S2107) The reception unit 12 judges whether or not permission information has been received from the terminal device 2 of the candidate who has received the offer. If permission information has been received, the process proceeds to step S2108, and if permission information has not been received, the process returns to step S401. The permission information includes, for example, a person identifier and a theme identifier.

[0341] (Step S2108) The proposer determination means 4313 judges whether or not the person identified by the person identifier included in the permission information satisfies the hiring conditions. If the hiring conditions are met, the process proceeds to step S2109, and if not, the process proceeds to step S2112.

[0342] (Step S2109) The proposer determination means 4313 acquires a person identifier included in the permission information. Note that the proposer determination means 4313 may acquire person identifiers included in all of the received permission information without making a decision using the adoption conditions.

[0343] (Step S2110) The proposer determination means 4313 stores the person identifier in association with the theme identifier.

[0344] (Step S2111) The proposer determination means 4313 acquires notification destination information paired with the person identifier from the human resources management unit 411, and transmits information to the notification destination specified by the notification destination information that the person has become a proposer who creates an idea. Return to step S401.

[0345] (Step S2112) The proposer determination means 4313 acquires notification destination information paired with the person identifier from the human resources management unit 411, and transmits information to the notification destination specified by the notification destination information that the person did not become a proposer who creates an idea. Return to step S401.

[0346] In the flowchart of FIG. 21, the process ends when the power is turned off or an interrupt for ending the process occurs.

[0347] Next, an example of the idea acquisition process in step S2101 will be described with reference to the flowchart in Fig. 22. In the flowchart in Fig. 22, the description of the same steps as in the flowchart in Fig. 9 will be omitted.

[0348] (Step S2201) The evaluation unit 432 evaluates one or more ideas received from the proposers. The process proceeds to step S919. An example of such idea evaluation processing will be described with reference to the flowchart of FIG.

[0349] Next, an example of the idea evaluation process in step S2201 will be described with reference to the flowchart in FIG.

[0350] (Step S2301) The evaluation unit 432 judges whether or not the analysis result in step S915 was an “error.” If it is an “error,” the process proceeds to step S2308, and if it is not an “error,” the process proceeds to step S2302.

[0351] (Step S2302) The evaluation unit 432 assigns 1 to the counter i.

[0352] (Step S2303) The evaluation unit 432 judges whether or not the i-th parameter used in evaluating the idea exists. If the i-th parameter exists, the process proceeds to step S2304, and if not, the process proceeds to step S2306.

[0353] The parameters used to evaluate the ideas are predetermined. For example, the parameters used to evaluate the ideas are the number of ideas, the number of characters in the idea, and the evaluation value obtained from the generation AI.

[0354] (Step S2304) The evaluation unit 432 acquires the value of the i-th parameter for acquiring the evaluation value of the idea.

[0355] The evaluation unit 432 acquires, for example, the number of ideas received from the proposer and the number of characters of each of the one or more ideas.

[0356] The evaluation unit 432, for example, substitutes the idea received from the proposer for the variable <idea> of the prompt template “Please rate the ideas below on a scale of 1 to 5 and provide an evaluation value. <idea>”, constructs a prompt, passes the prompt to the generation AI, and obtains an evaluation value for the idea from the generation AI.

[0357] (Step S2305) The evaluation unit 432 increments the counter i by 1. The process returns to step S2303.

[0358] (Step S2306) The evaluation unit 432 acquires an evaluation value of the proposer's idea using one or more parameters acquired in step S2304. Then, the process proceeds to step S2308.

[0359] When the proposer has two or more ideas, the evaluation value of each idea may be the evaluation value of each idea, or the evaluation values ​​of all two or more ideas.

[0360] (Step S2307) The evaluation unit 432 assigns 0 (the lowest score) to the evaluation value.

[0361] (Step S2308) The evaluation unit 432 accumulates the evaluation value acquired in step S2306 or S2307 in a pair with the person identifier, and returns to the upper level process.

[0362] In the flowchart of FIG. 23, the evaluation unit 432 may simply provide an idea to the generation AI and obtain an evaluation value of the idea from the generation AI.

[0363] Next, an example of the reward process in step S2102 will be described with reference to the flowchart in FIG.

[0364] (Step S2401) The reward processing unit 434 assigns 1 to the counter i.

[0365] (Step S2402) The reward processing unit 434 judges whether or not the i-th proposer exists. If the i-th proposer exists, the process proceeds to step S2403, and if not, the process returns to the upper process.

[0366] Here, for example, the reward processing unit 434 determines whether or not there exists an i-th person identifier that pairs with the theme identifier of the theme.

[0367] (Step S2403) The reward processing unit 434 acquires the person identifier of the i-th proposer.

[0368] (Step S2404) The reward processing unit 434 acquires the evaluation information acquired by the evaluation unit 432, which is evaluation information paired with the person identifier acquired in step S2403.

[0369] (Step S2405) The reward processing unit 434 acquires a rank paired with the person identifier acquired in step S2403.

[0370] (Step S2406) The reward processing unit 434 acquires a reward amount using the evaluation information acquired in step S2404 and the rank acquired in step S240. The reward processing unit 434 usually acquires a larger reward amount as the evaluation indicated by the evaluation information is higher and as the rank is higher. The reward processing unit 434 may acquire the reward amount based only on the evaluation information or only on the rank. The reward processing unit 434 may acquire a fixed reward amount from the storage unit 41.

[0371] (Step S2407) Reward processing unit 434 performs reward processing to give a reward indicated by the reward amount acquired in step S2406 to the person identified by the person identifier of the i-th proposer.

[0372] (Step S2408) The reward processing unit 434 acquires notification destination information paired with the person identifier of the i-th proposer. The reward processing unit 434 transmits information to the notification destination indicated by the notification destination information that a reward indicated by the reward amount has been given.

[0373] (Step S2409) The reward processing unit 434 increments the counter i by 1. The process returns to step S2402.

[0374] Next, an example of the rank acquisition process in step S2103 will be described with reference to the flowchart in FIG.

[0375] (Step S2501) The ranking unit 433 assigns 1 to a counter i.

[0376] (Step S2502) The ranking unit 433 judges whether or not the i-th proposer exists. If the i-th proposer exists, the process proceeds to step S2503, and if not, the process returns to the upper process.

[0377] (Step S2503) The ranking unit 433 acquires the person identifier of the i-th proposer.

[0378] (Step S2504) The ranking unit 433 acquires a rank paired with the person identifier from the human resources management unit 411. This rank is the original rank.

[0379] (Step S2505) The ranking unit 433 acquires information used to determine whether to rank up. Such information includes, for example, the score acquired by the score acquisition unit 139, the evaluation information acquired by the evaluation unit 432, and whether the idea of ​​the proposer was included in the ideas selected by the idea selection unit 137.

[0380] (Step S2506) The ranking unit 433 judges whether or not one or more pieces of information acquired in step S2505 match the rank-up condition. If the rank-up condition is matched, the process proceeds to step S2507, and if not, the process proceeds to step S2509.

[0381] (Step S2507) Ranking unit 433 increments the original rank acquired in step S2504 by 1 to acquire a new rank.

[0382] (Step S2508) The ranking unit 433 stores the new rank acquired in step S2507 in the human resources management unit 411 in combination with the person identifier of the proposer.

[0383] (Step S2509) The ranking unit 433 increments the counter i by 1. The process returns to step S2502.

[0384] In the flowchart of FIG. 25, it is preferable not to perform processing to increase the rank of a proposer who is already in the highest rank.

[0385] Next, an example of the offer process in step S2106 will be described with reference to the flowchart in FIG.

[0386] (Step S2601) The candidate determining means 4311 acquires a theme.

[0387] (Step S2602) The candidate determining means 4311 assigns 1 to a counter i.

[0388] (Step S2603) The candidate determination means 4311 judges whether or not personnel information of the i-th candidate exists in the personnel management unit 411. If personnel information of the i-th candidate exists, the process proceeds to step S2604, and if not, the process returns to the upper level process.

[0389] (Step S2604) The candidate determining means 4311 acquires the personnel information of the i-th candidate.

[0390] (Step S2605) The candidate determining means 4311 judges whether or not the human resources information satisfies the offer conditions. If the offer conditions are satisfied, the process proceeds to step S2606, and if not, the process proceeds to step S2609.

[0391] (Step S2606) The candidate determining means 4311 acquires the person identifier and notification destination information contained in the human resources information of the i-th candidate.

[0392] (Step S2607) The offer means 4312 acquires offer information having a theme.

[0393] (Step S2608) The offer means 4312 transmits the offer information to the notification destination specified by the notification destination information.

[0394] (Step S2609) The candidate determining means 4311 increments the counter i by 1. The process returns to step S2603.

[0395] Next, an example of the operation of the terminal device 2 will be described with reference to the flowchart of FIG.

[0396] (Step S2701) The terminal reception unit 22 judges whether or not an idea creation request has been received. If an idea creation request has been received, the process proceeds to step S2702, and if not, the process proceeds to step S2703.

[0397] (Step S2702) The device processing unit 23 acquires the user identifier from the device storage unit 21, and associates the user identifier with the idea creation request accepted in step S2701. The device transmission unit 24 transmits the idea creation request paired with the user identifier to the idea creation support device 4. Return to step S2701. The user identifier may be the same type of information as the person identifier.

[0398] (Step S2703) The terminal receiving unit 25 judges whether or not offer information has been received from the creation support device 4. If offer information has been received, the process proceeds to step S2704, and if offer information has not been received, the process proceeds to step S2705.

[0399] (Step S2704) The terminal processing unit 23 uses the received offer information to configure offer information to be output. The terminal output unit 26 outputs the offer information. Return to step S2701.

[0400] (Step S2705) The terminal acceptance unit 22 judges whether or not permission information for the offer has been accepted. If permission information has been accepted, the process proceeds to step S2706, and if not, the process proceeds to step S2709.

[0401] (Step S2706) The device processing unit 23 acquires the theme identifier and the person identifier from the terminal storage unit 21. The terminal transmitting unit 24 transmits the accepted permission information to the creation support device 4, with the theme identifier and the person identifier as a pair.

[0402] (Step S2707) The terminal receiving unit 25 judges whether or not information has been received from the creation support device 4. If information has been received, the process proceeds to step S2708, and if information has not been received, the process returns to step S2707. Note that the information here includes information indicating whether or not the candidate has become a proposer.

[0403] (Step S2708) The device processing unit 23 composes information to be output using the information received in step S2707. The terminal output unit 26 outputs the information. The process returns to step S2701.

[0404] (Step S2709) The terminal receiving unit 25 judges whether or not information has been received from the creation support device 4. If information has been received, the process proceeds to step S2710, and if information has not been received, the process proceeds to step S2711. The information here is, for example, the idea proposed by the generating AI, the ideas proposed by other proposers, evaluation information, and rank.

[0405] (Step S2710) The device processing unit 23 composes information to be output using the information received in step S2709. The terminal output unit 26 outputs the information. The process returns to step S2701.

[0406] (Step S2711) The terminal reception unit 22 judges whether or not an idea has been received from the proposer. If an idea has been received, the process proceeds to step S2712, and if not, the process returns to step S2701.

[0407] (Step S2712) The device processing unit 23 acquires the theme identifier and the person identifier from the terminal storage unit 21. The terminal transmitting unit 24 transmits the idea accepted in step S2711, together with the theme identifier and the person identifier, to the creation support device 4. Return to step S2701.

[0408] In the flowchart of FIG. 27, the process ends when the power is turned off or an interrupt for ending the process occurs.

[0409] A specific example of the operation of the information system B in this embodiment will be described below.

[0410] 13 is stored in the transition management unit 111 of the creation support device 4. Also, the prompt management table shown in FIG.

[0411] Furthermore, it is assumed that the talent management unit 411 of the creation support device 4 stores a talent management table shown in FIG. 28. The talent management table is a table for managing talent information. The talent management table manages one or more records having an "ID" and "talent information". The "talent information" has a "person identifier", "notification destination information", "theme information", "account information", "points", and "rank". The "theme information" has a "field" and "keywords". The "field" is the field in which the candidate excels. The "keywords" are keywords that indicate the candidate's specialized skills.

[0412] 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 generation AI, and offers the following: <Theme> Solution using AI and a camera <Deadline information> July 31, 2024 <Budget> 100,000 yen <Offer conditions> Rank> = 3 <Agent><Name> Mr. A <Agent name> AI engineer <Role> To promote the use of AI in ideas and products by utilizing AI-related technologies and improve problem-solving capabilities. <Persona> ['Has deep knowledge and experience in AI technologies such as machine learning, deep learning, and natural language processing', 'Skilled in preprocessing of datasets, training and evaluation of models, and deployment of AI solutions', 'Conscious of working on development that takes into account the ethical aspects and social impact of AI']< / エージェント> " is input to the terminal device 2.

[0413] In addition, "<Deadline information> July 31, 2024" in the idea creation request indicates the deadline by which user U obtains an idea. "<Budget> 100,000 yen" indicates the budget that user U can bear. Note that the budget "100,000 yen" is the amount that can hire one proposer. Also, "<Offer condition> Rank> = 3" indicates that the offer condition for the proposer is "Rank 3 or higher."

[0414] Next, the terminal reception unit 22 of the terminal device 2 receives the idea creation request. Next, the terminal transmission unit 24 of the terminal device 2 transmits the idea creation request to the creation support device 1 in combination with the user identifier “U01” of the user U of the terminal device 2.

[0415] Next, the reception unit 12 of the creation support device 1 receives the idea creation request from the terminal device 2 of the user U. Then, the creation support device 1 determines a proposer as follows, creates an idea with the generation AI and the proposer, and provides the created idea to the user U, by the operation described using the flowchart in FIG.

[0416] That is, first, the processing unit 43 generates a unique theme identifier "T01". Next, the processing unit 43 accumulates requested theme information having the theme identifier "T01" and information included in the idea creation request. Such requested theme information is "<Theme identifier> T01 <Theme> Solution using AI and camera <Deadline information> July 31, 2024 <Budget> 100,000 yen <Offer condition> Rank> = 3 <Agent><Name> Mr. A <Agent name> AI engineer <Role> To promote the use of AI in ideas and products by utilizing AI-related technologies and improve problem-solving capabilities. <Persona> ['Has deep knowledge and experience in AI technologies such as machine learning, deep learning, and natural language processing', 'Skilled in pre-processing of datasets, training and evaluation of models, and deployment of AI solutions', 'Conscious of working on development that takes into account the ethical aspects and social impacts of AI']< / エージェント> "

[0417] Next, the recruitment processing unit 431 performs the offer process as follows. That is, the candidate determination means 4311 of the recruitment processing unit 431 detects a record having theme information corresponding to "<theme> solution using AI and a camera" and having a rank that satisfies "<offer condition> rank> = 3" from the human resources management table of FIG. 28, and acquires one or more person identifiers. As a result, it is assumed that the candidate determination means 4311 acquires person identifiers "P01" and "P03". Note that the theme information corresponding to "<theme> solution using AI and a camera" is here assumed to have a field that matches the field "information" of <theme> and includes any keyword of the technical terms "AI" and "camera" included in <theme>. In addition, the method of determining the field of "<theme> solution using AI and a camera" does not matter. Such a method is a publicly known technology.

[0418] Next, the candidate determining means 4311 acquires the notification destination information "P01@x.com" and "08076543210" of the person identifiers "P01" and "P03".

[0419] Next, the offer means 4312 acquires the theme "Solution using AI and camera". In addition, the offer means 4312 determines the start time of the idea creation meeting to be "July 24, 2024, 10:00" from "<Deadline information> July 31, 2024". The start time of the meeting is determined based on <Deadline information>, and here, for example, it is 10:00 one week before the deadline indicated by the deadline information. Next, the offer means 4312 configures screen information that is offer information such as "The idea creation meeting on the theme "Solution using AI and camera" will start at the following time. We would like you, who have a deep knowledge of this theme, to participate in this idea creation meeting. <Date and time> July 24, 2024, 10:00~ If you are able to participate, please instruct the following "Accept" button." Next, the offer means 4312 transmits the offer information to the notification destination specified by the notification destination information.

[0420] Next, the above offer information is transmitted to each of the terminal devices 2 of the candidates identified by "P01" and "P03".

[0421] First, a screen based on the above offer information is output to the terminal device 2 of the candidate 1 identified by "P01" and the terminal device 2 of the candidate 3 identified by "P03".

[0422] Next, suppose that the candidate 1 looks at the screen of the terminal device 2 and presses the "Agree" button. Then, the terminal reception unit 22 of the terminal device 2 accepts the permission information. Next, the terminal processing unit 23 acquires the theme identifier "T01" and the person identifier "P01" from the terminal storage unit 21. The terminal transmission unit 24 transmits the accepted permission information (for example, "1") to the creation support device 4, pairing the theme identifier "T01" with the person identifier "P01".

[0423] Next, the reception unit 12 of the creation support device 4 receives the permission information from the terminal device 2 of the candidate 1, with the theme identifier "T01" and the person identifier "P01" paired together.

[0424] Next, the proposer determination means 4313 determines that the person identified by the person identifier contained in the permission information satisfies the hiring condition. Note that the hiring condition here is the number of people to be hired according to the budget, and in this case, the maximum number of people to be hired for a budget of "100,000 yen" is "one person." In other words, here, only the person who first transmits permission information becomes the proposer. The proposer determination means 4313 acquires the person identifier "P01" and stores the person identifier in a pair with the theme identifier "T01."

[0425] Next, the proposer determination means 4313 acquires notification destination information paired with the person identifier "P01", and transmits information to the notification destination specified by the notification destination information that the person has become a proposer who will create an idea.

[0426] Next, the terminal device 2 of the candidate 1 identified by the person identifier "P01" receives and outputs information that he or she has become the proposer who will create an idea.

[0427] Next, the candidate 3 looks at the screen of the terminal device 2 and presses the "Agree" button. Then, the terminal reception unit 22 of the terminal device 2 accepts the permission information. Next, the terminal processing unit 23 acquires the theme identifier "T01" and the person identifier "P03" from the terminal storage unit 21. The terminal transmission unit 24 transmits the accepted permission information (for example, "1") to the creation support device 4, pairing the theme identifier "T01" with the person identifier "P03".

[0428] Next, the reception unit 12 of the creation support device 4 receives the permission information from the terminal device 2 of the candidate 3, with the theme identifier "T01" and the person identifier "P03" paired together.

[0429] Next, the proposer determination means 4313 determines that the person identified by the received person identifier "P03" does not satisfy the hiring conditions. Since the candidate 3 identified by the person identifier "P03" sent the permission information second, the proposer determination means 4313 determines that the candidate does not satisfy the hiring conditions.

[0430] Next, the proposer determination means 4313 acquires notification destination information paired with the person identifier "P03", and transmits information to the notification destination specified by the notification destination information that the person did not become a proposer who creates an idea.

[0431] Next, the terminal device 2 of the candidate 3 identified by the person identifier "P01" receives and outputs information to the effect that the candidate did not become a proposer who creates an idea.

[0432] In this manner, the proposer (here, Proposer 1) who will participate in the idea creation meeting has been decided.

[0433] Next, at 10:00 on July 24, 2024, an idea creation meeting is started. Then, an idea creation meeting is held between the generation AI and the proposer 1 of "P01". The idea creation meeting is as described in the specific example of the first embodiment. Note that, for the idea creation meeting here, the input of the idea of ​​the user U in the specific example of the first embodiment is replaced with the input of the idea of ​​the proposer 1.

[0434] In this specific example, the evaluation unit 432 acquires evaluation information of the idea put forward by the proposer 1. 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 1.

[0435] The terminal device 2 of the user U and the terminal device 2 of the proposer 1 receive and output evaluation information on the idea put forward by the proposer 1.

[0436] Furthermore, the ranking unit 433 updates the rank of the proposer 1 identified by the person identifier "P01" from "4" to "5", for example, through the above-mentioned process.

[0437] Furthermore, the reward processing unit 434 performs the process described above to determine the amount of reward for the proposer 1 identified by the person identifier "P01" and to give a reward equivalent to the determined amount of reward.

[0438] As described above, according to this embodiment, it is possible to support the generation AI and humans working together to create ideas on a single theme.

[0439] Furthermore, according to this embodiment, an appropriate idea can be selected from among ideas that are generated together by the generation AI and a person on a single theme.

[0440] Furthermore, according to this embodiment, a reward can be given to the person who proposes the idea.

[0441] Furthermore, according to this embodiment, people who fit the theme can be offered the opportunity to participate in idea generation.

[0442] Furthermore, according to this embodiment, the ideas put forward by the proposers can be evaluated.

[0443] Furthermore, according to this embodiment, candidates who submit ideas can be ranked.

[0444] In this embodiment, the creation support device 4 does not have to include, for example, the agent determination unit 130, the control unit 132, the moderator judgment unit 133, the viewpoint acquisition unit 134, the idea criticism unit 136, the idea selection unit 137, the analysis unit 138, etc. The creation support device 4 may be a device that includes, for example, the prompt management unit 112, the attribute value storage unit 113, the recruitment processing unit 431, the character setting unit 131, the idea acquisition unit 135, and the idea output unit 142.

[0445] Furthermore, the software for realizing the creation support device 4 in this embodiment is the following program. That is, this program is a program for making a computer that can access a prompt management unit in which 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 generation AI in one or more phases including the idea generation phase are stored, and an attribute value storage unit in which one or more idea attribute values, which are attribute values ​​related to the idea to be created and include a theme for which the idea is to be generated, are stored, as a solicitation processing unit that performs a solicitation process for soliciting people who will provide ideas for the theme and determines a proposer who is a person who will provide an idea for the theme, a character setting unit that obtains one or more setting prompts using the setting prompt template and provides the one or more setting prompts to the generation AI, an idea acquisition unit that obtains a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, and provides the prompt to the one or more agents of the generation AI to obtain an idea, an idea reception unit that receives ideas from the proposers determined by the solicitation processing unit, and an idea output unit that outputs the ideas obtained by the idea acquisition unit and the ideas obtained by the idea reception unit.

[0446] FIG. 29 is a block diagram of a computer system 300 that executes the programs described in this specification to realize the creation support device 1, the creation support device 4, and the like according to the various embodiments described above.

[0447] In FIG. 29, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0448] 29, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0449] A program for causing computer system 300 to execute the functions of creation support device 4 and the like of the above-mentioned embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and further transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 at the time of execution. The program may be loaded directly from CD-ROM 3101 or the network.

[0450] The program does not necessarily include an operating system (OS) or a third party program that causes the computer 301 to execute the functions of the creation support device 4 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain a desired result. How the computer system 300 operates is well known, and a detailed description will be omitted.

[0451] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmitting step (processing that is performed only by hardware).

[0452] The program may be executed by a single computer or a plurality of computers, that is, centralized processing or distributed processing may be performed.

[0453] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0454] Furthermore, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0455] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0456] As described above, the creation support device 4 according to the present invention has an effect of being able to support a generation AI and a person in creating ideas on a theme together, and is useful as a server or the like. [Explanation of symbols]

[0457] A,B Information Systems 1, 4 Creation support device 2 Terminal Equipment 3 Generation AI device 11, 41 Storage area 12 Reception 13, 43 Processing section 14, 44 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal Processing Section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Section 111 Transition Management Department 112 Prompt Management Department 113 Attribute value storage section 114 Current Management Department 121 Attribute value reception unit 122 Idea Reception Department 130 Agent Determination Unit 131 Person setting section 132 Control section 133 Chairperson Judgment Department 134 Perspective Acquisition Department 135 Idea Acquisition Department 136 Idea Critique Department 137 Idea Selection Department 138 Analysis Department 139 Score Acquisition Section 141 Answer output section 142 Idea Output Section 143 Score Output Section 144 Error output section 411 Human Resources Management Department 431 Recruitment Department 432 Evaluation Department 433 Rankings 434 Reward Processing Unit 441 Evaluation Output Unit 442 Rank Output Unit 4311 Candidate Selection Method 4312 Offer means 4313 Proposer determining means

Claims

1. a prompt management unit in which 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 generation AI in one or more phases including an idea generation phase are stored; an attribute value storage unit in which one or more idea attribute values, which are attribute values ​​related to an idea to be created and include a theme for which an idea is to be generated, are stored; a solicitation processing unit that performs a solicitation process for soliciting people who submit ideas for the theme and determines a proposer who submits ideas for the theme; a person setting unit that obtains one or more setting prompts using the setting prompt template and provides each of 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 provides the prompt to each of the one or more agents of the generation AI to acquire an idea; an idea receiving unit that receives ideas from the proposers determined by the solicitation processing unit; a creation support device comprising: an idea output unit that outputs the ideas acquired by the idea acquisition unit and the ideas acquired by the idea reception unit.

2. The prompt management unit includes: The setting prompt template and a phase prompt template for configuring a prompt to be given to the generation AI in each of two or more phases including the idea generation phase and the idea selection phase are stored; An idea selection unit acquires a prompt using the phase prompt template corresponding to the idea selection phase, the idea acquired by the idea acquisition unit, and the idea accepted by the idea acceptance unit, and provides the prompt to the generation AI, and acquires one or more ideas selected based on the idea acquired by the idea acquisition unit and the idea accepted by the idea acceptance unit, The idea output unit includes: A creation support device as described in claim 1, which outputs the one or more ideas acquired by the idea selection unit in addition to the ideas acquired by the idea acquisition unit and the ideas acquired by the idea reception unit, or instead of the ideas acquired by the idea acquisition unit and the ideas acquired by the idea reception unit.

3. 2. The creation support device according to claim 1, further comprising a reward processing unit for performing a reward process for giving a reward to the proposer.

4. Further comprising an attribute value receiving unit for receiving a theme, The recruitment processing unit: a candidate determination means for referencing a human resources management section in which two or more pieces of human resources information each having theme information related to a theme and a person identifier for identifying a person are stored, and acquiring one or more person identifiers for identifying a candidate who is a person corresponding to the theme; an offering means for offering each of the one or more candidates acquired by the candidate determination means to submit an idea related to the theme; A creation support device as described in any one of claims 1 to 3, further comprising a proposer determination means for receiving consent information from one or more of the one or more candidates, and determining a proposer who is a candidate corresponding to the consent information and who is a candidate who can submit an idea.

5. an evaluation unit that acquires evaluation information indicating an evaluation of the idea accepted by the idea accepting unit; The creation support device according to claim 1 , further comprising an evaluation output unit that outputs the evaluation information.

6. a ranking unit that acquires a rank of the proposer who submitted the idea by using the evaluation information acquired by the evaluation unit; 6. The creation support device according to claim 5, further comprising a rank output unit for outputting the rank.

7. A creation support method implemented by a prompt management unit that stores 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 a generation AI in one or more phases including an idea generation phase, an attribute value storage unit that stores one or more idea attribute values ​​which are attribute values ​​related to ideas to be created and include a theme for which the ideas are to be generated, a collection processing unit, a character setting unit, an idea acquisition unit, an idea reception unit, and an idea output unit, a solicitation processing step in which the solicitation processing unit performs a solicitation process for soliciting people who submit ideas regarding the theme and determines a proposer who submits ideas regarding the theme; a person setting step of the person setting unit obtaining one or more setting prompts using the setting prompt template and providing each of the one or more setting prompts to the generation AI; an idea acquisition step in which the idea acquisition unit acquires a prompt using the phase prompt template corresponding to the idea generation phase and the one or more idea attribute values, and provides the prompt to each of the one or more agents of the generation AI to acquire an idea; an idea receiving step in which the idea receiving unit receives ideas from the proposers determined by the solicitation processing unit; The creation support method includes an idea output step in which the idea output unit outputs the ideas acquired by the idea acquisition unit and the ideas acquired by the idea reception unit.

8. a prompt management unit that stores 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 a generation AI in one or more phases including an idea generation phase; and an attribute value storage unit that stores one or more idea attribute values ​​that are attribute values ​​related to ideas to be created and include a theme for which the idea is to be generated; a solicitation processing unit that performs a solicitation process for soliciting people who submit ideas for the theme and determines a proposer who submits ideas for the theme; a person setting unit that obtains one or more setting prompts using the setting prompt template and provides each of 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 provides the prompt to each of the one or more agents of the generation AI to acquire an idea; an idea receiving unit that receives ideas from the proposers determined by the solicitation processing unit; a program for causing the program to function as an idea output unit that outputs the ideas acquired by the idea acquisition unit and the ideas acquired by the idea reception unit;

Images