Programs, methods, information processing devices, systems

Abstract

One challenge is that we haven't been able to create consumer interview questions for users. [Solution] A program to be executed by a computer comprising a processor and a memory unit, wherein the processor performs a first utterance acquisition step of acquiring first utterance content from a user, and a first creation step of creating a first prompt by including the user's first utterance content acquired in the first utterance acquisition step in a first instruction for creating an interview question to obtain information from the user from one or more perspectives.

Description

Technical Field

[0001] The present disclosure relates to a program, a method, an information processing apparatus, and a system.

Background Art

[0002] Techniques for analyzing interests and concerns in users' consumption behaviors are known. Patent Document 1 discloses a questionnaire reception method.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that consumer interview questions for users cannot be created yet. Therefore, the present disclosure has been made to solve the above problems, and an object thereof is to provide a technique for creating consumer interview questions for users.

Means for Solving the Problems

[0005] A program for causing a computer including a processor and a storage unit to execute, the processor executing a first speech acquisition step of acquiring first speech content from a user, and a first creation step of creating a first prompt by including the first speech content of the user acquired in the first speech acquisition step in a first instruction for creating an interview question for obtaining information from the user on one or more viewpoints.

Effects of the Invention

[0006] According to this disclosure, consumer interview questions can be created for users. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the functional configuration of System 1. [Figure 2] This block diagram shows the functional configuration of Server 10. [Figure 3] This is a block diagram showing the functional configuration of user terminal 20. [Figure 4] This is a block diagram showing the functional configuration of the administrator terminal 30. [Figure 5] This diagram shows the data structure of user table 1012. [Figure 6] This diagram shows the data structure of project table 1013. [Figure 7] This diagram shows the data structure of question table 1014. [Figure 8] This diagram shows the data structure of answer table 1015. [Figure 9] This diagram shows the data structure of interview table 1016. [Figure 10] This diagram shows the data structure of the instruction statement storage unit 1021. [Figure 11] This diagram shows the data structure of the analysis perspective table 1031. [Figure 12] This figure shows the data structure of the analysis perspective result table 1032. [Figure 13] This diagram shows the data structure of the analysis insight table 1033. [Figure 14] This is a flowchart showing the process of creating a project plan. [Figure 15] This is a flowchart showing the operation of the survey processing. [Figure 16] This is a flowchart showing the operation of the interview process. [Figure 17] This is a flowchart showing the operation of the consistency check process. [Figure 18]It is a flowchart showing the operation of the viewpoint analysis process. [Figure 19] It is a flowchart showing the operation of the insight analysis process. [Figure 20] It is a first screen example showing the operation of the viewpoint analysis process. [Figure 21] It is a second screen example showing the operation of the viewpoint analysis process. [Figure 22] It is a screen example showing the operation of the insight analysis process. [Figure 23] It is a block diagram showing the basic hardware configuration of the computer 90.

Modes for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for describing the embodiments, common components are denoted by the same reference numerals, and repeated descriptions are omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure. Also, each figure is a schematic diagram and is not necessarily drawn precisely.

[0009] <Configuration of System 1> The system 1 in the present disclosure is an information processing system that collects survey information of users. Specifically, it is an information processing system that collects survey information such as the user's interests and concerns regarding purchases through questionnaires, interviews, etc. Specifically, the information processing system according to the present disclosure relates to an information processing service that realizes consumer questionnaires, consumer interviews, etc., which collect consumer survey information such as the interests and concerns of users regarding their consumption behavior related to the survey target, using an artificial intelligence system. In the present disclosure, the information such as the user's interests and concerns regarding purchases collected through questionnaires, interviews, etc. is called survey information (consumer survey information). The system 1 includes an information processing device of the server 10, the user terminal 20, the administrator terminal 30, and the generation AI 50, which are connected via the network N. Figure 1 is a block diagram showing the functional configuration of System 1. Figure 2 is a block diagram showing the functional configuration of server 10. Figure 3 is a block diagram showing the functional configuration of the user terminal 20. Figure 4 is a block diagram showing the functional configuration of the administrator terminal 30.

[0010] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the server 10, user terminal 20, administrator terminal 30, and generation AI 50, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0011] <Server 10 Configuration> Server 10 is an information processing system that collects user survey information. Specifically, it is an information processing device that provides information processing services to collect user survey information such as their purchasing interests through surveys such as questionnaires and interviews. The server 10 includes a storage unit 101 and a control unit 104.

[0012] <Configuration of the storage unit 101 of server 10> The storage unit 101 of the server 10 includes an application program 1011, a user table 1012, a planning table 1013, a question table 1014, an answer table 1015, an interview table 1016, an instruction storage unit 1021, an analysis perspective table 1031, an analysis perspective result table 1032, and an analysis insight table 1033.

[0013] The application program 1011 is a program that causes the control unit 104 of the server 10 to function as individual functional units. Application program 1011 includes applications such as a web browser application.

[0014] User Table 1012 is a table that stores and manages information about member users (hereinafter referred to as "users") who use the service. When a user registers to use the service, their information is stored in a new record in User Table 1012. This allows the user to use the services related to this disclosure. Note that user information may also be stored in User Table 1012 through an input operation by an administrator. Furthermore, in the survey processing, interview processing, etc. described later, when a user opens a URL related to the survey processing page, interview page, etc. by operating the input device 206 of the user terminal 20, the user's information may also be stored in User Table 1012. User table 1012 is a table with User ID as the primary key, and has columns for User ID, User Name, and User Data. Figure 5 shows the data structure of user table 1012.

[0015] The User ID is an item that stores user identification information to identify a user. User identification information is an item that is set to a unique value for each user. The username field is used to store the user's real name. However, the username can also be a nickname or any other string of characters. User data includes unique information about individual users, as well as attribute information related to the user's characteristics and background. User-specific information includes user-specific information such as date of birth (age) and gender. User attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language.

[0016] Project Table 1013 is a table for storing and managing information (project information) related to consumer surveys and consumer interview projects. Project table 1013 is a table with Project ID as the primary key and containing columns for Project ID, Project Name, Target Audience, Project Content, Perspective, and Prompt A. Figure 6 shows the data structure of the planning table 1013.

[0017] The Project ID is an item that stores project identification information to identify a project. Each project has a unique value assigned to it. The project name is an item that stores the name of the project. The project name can be set to any string of characters. The "Target" field stores the user IDs of the users being investigated. The "Target" field stores one or more user IDs. The "Project Details" section is for remembering the content of the project. A "perspective" is an item used to remember the research perspectives of a consumer survey or consumer interview. Specifically, it remembers the perspectives related to the interests and concerns of users you want to investigate regarding a product or service. In addition to the text information describing the perspective, a perspective may also include image information related to the perspective. It may also include string information such as a URL linking to an image. For example, the viewpoint stores information such as strings and images, as shown below. Please ask about the manufacturer of the motorcycle you are using. Where do you use your motorcycle? Please elaborate on the situations in which you typically use this. Prompt A is an item that stores prompts (instructions) to get the AI ​​to conduct consumer interviews.

[0018] Question table 1014 is a table for storing and managing information related to questions (question information). Question table 1014 is a table with Question ID as the primary key and containing columns for Question ID, Project ID, and Question Content. Figure 7 shows the data structure of question table 1014.

[0019] The Question ID is an item that stores question identification information to identify a question. The question identification information is an item that has a unique value assigned to each piece of question information. The project ID is an item that stores project identification information to identify a project. The question content is an item to remember the content of the question.

[0020] Answer table 1015 is a table for storing and managing information related to the answers (answer information). The answer table 1015 is a table with the answer ID as the primary key and containing columns for answer ID, question ID, user ID, answer content, answer date and time, and judgment result. Figure 8 shows the data structure of the answer table 1015.

[0021] The response ID is an item that stores response identification information to identify a response. Each response has a unique value assigned to it. The Question ID is an item that stores question identification information to identify a question. The User ID is an item that stores user identification information used to identify a user. The "Answer Content" field stores the user's response to a question identified based on the question ID. The "Response Date and Time" field stores the date and time when a new record is added or updated in the response table. The judgment result is an item that stores the judgment result of whether the answer is appropriate or not. Specifically, the judgment result is an item that stores the judgment result (True, False) of whether the user's answer is false or not. The judgment result does not necessarily have to be a two-level value of "appropriate" or "inappropriate"; it may also be configured to store a numerical value indicating the degree of appropriateness or a string indicating a rank.

[0022] Interview table 1016 is a table for storing and managing information related to interviews (interview information). Interview table 1016 is a table with Interview ID as the primary key and containing columns for Interview ID, Project ID, User ID, Index, Interview Prompt, Interview Question, Speech Content, and Additional Data. Figure 9 shows the data structure of interview table 1016.

[0023] The Interview ID is an item that stores interview identification information to identify an interview. The interview identification information is an item with a unique value assigned to each interview. The project ID is an item that stores project identification information to identify a project. The User ID is an item that stores user identification information used to identify a user. The index is an item used to remember the order of the interviews. The interview prompt is an item that stores prompts (instructional statements) for generating interview questions to be output to the user. The interview question field is an item that stores the interview questions to be output to the user. The interview question field may include not only text information but also image information to be presented to the user. It may also include information such as URLs to the images. The "Speech Content" field stores the content of what the user says in response to interview questions. This includes audio data, video data, and image data received from the user, as well as text data transcribed from the audio data using text recognition technology. Furthermore, the system stores one or more utterances received from the user in response to one or more interview questions presented during the interview process. The supplemental data includes audio data, video data, and image data that record the user's responses to the interview. The supplemental data also includes information such as the content and date and time of input operations (such as temporary pauses) performed by the user during the interview.

[0024] The instruction statement storage unit 1021 is an item that stores instruction statements. Instruction statements are used when creating prompts to be input to the generating AI. Alternatively, the instruction statements may be input directly to the generating AI as prompts. The instruction statement storage unit 1021 is a table having columns for instruction statement A, instruction statement B, instruction statement C1, instruction statement C2, and instruction statement D. Figure 10 shows the data structure of the instruction statement storage unit 1021.

[0025] Instruction A is used to generate a prompt for conducting a consumer interview. Instruction B is used to generate prompts to verify the consistency between the user's responses and the content of their interview statements. Instruction C1 is used to generate a prompt for outputting perspectives from a question. Instruction C2 is used to generate a prompt for outputting a question from a given perspective. Instruction D is an instruction to output one or more perspectives included in a questionnaire or interview.

[0026] The analysis perspective table 1031 is a table for storing and managing information related to analysis perspectives (analysis perspective information). The analysis perspective table 1031 is a table with analysis perspective ID as the primary key, and has columns for analysis perspective ID, perspective name, perspective instruction, and analysis item. Figure 11 shows the data structure of the analysis perspective table 1031.

[0027] The analysis perspective ID is an item that stores analysis perspective identification information to identify an analysis perspective. Each analysis perspective identification information item has a unique value assigned to it. The "Perspective Name" field stores the name of the perspective. The perspective name can be set to any string. The "perspective instruction" field stores instructional texts used when creating prompts for analyzing consumer survey information, such as questionnaires and interviews, according to specific analytical perspectives. The analysis item is a field that stores information indicating the data source (analysis item) to be analyzed from among consumer survey information such as multiple questionnaires and interviews.

[0028] The analysis perspective result table 1032 is a table for storing and managing information related to the analysis perspective results (analysis perspective result information). The analysis perspective results table 1032 is a table that has columns for analysis perspective ID, user ID, perspective analysis prompt, and perspective analysis result. Figure 12 shows the data structure of the analysis perspective result table 1032.

[0029] The analysis perspective ID is an item that stores analysis perspective identification information for identifying an analysis perspective. The User ID is an item that stores user identification information used to identify a user. The perspective analysis prompt is an item that stores prompts that output one or more perspectives contained in consumer research information such as questionnaires and interviews of a given user. The viewpoint analysis results are an item that stores the output content that is generated in response to the input given to the viewpoint analysis prompt AI50.

[0030] The analytical insights table 1033 is a table for storing and managing information (analytical insights information) that delves deeper into analytical perspectives (analytical insights, insights) based on information spanning multiple analytical perspectives. The analysis insight table 1033 is a table whose primary key is the analysis insight ID, and which has columns for analysis insight ID, project ID, target perspective ID, insight instruction, and insight analysis result. Figure 13 shows the data structure of the analysis insight table 1033.

[0031] The Analysis Insight ID is an item that stores analysis insight identification information to identify an analysis insight. The analysis insight identification information is an item with a unique value assigned to each analysis insight. The project ID is an item that stores project identification information to identify a project. The target perspective ID is an item that stores one or more analysis perspective IDs that indicate the analysis perspective of the subject to be explored in depth. The insight instruction field stores instructions for outputting information (analytical insights, insights) that delves deeper into analytical perspectives across multiple analytical viewpoints. The insight analysis results section is a section that stores the output content generated in response to inputs such as insight instructions, consumer survey information including questionnaires and interviews, and perspective analysis results, which are then output to the generating AI50.

[0032] <Configuration of the control unit 104 of server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 realizes each functional unit by executing the application program 1011 stored in the storage unit 101.

[0033] The user registration control unit 1041 processes information of users who wish to use the services related to this disclosure and stores it in the user table 1012. Information stored in the user table 1012 is obtained when a user opens a web page operated by the service provider from any information processing terminal, enters information into a designated input form, and sends it to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, and user registration is completed. As a result, users stored in the user table 1012 can use the service. Prior to the registration of user information in the user table 1012 by the user registration control unit 1041, the service provider may perform a prescribed review and restrict whether or not the user can use the service. The user ID can be any string or number that can identify the user, and may be any string or number desired by the user, or the user registration control unit 1041 may automatically set any string or number.

[0034] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user of the service. The user terminal 20 may be, for example, a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer) or laptop PC. It may also be a wearable device such as an HMD (Head Mount Display) or a smartwatch. The user terminal 20 includes a storage unit 201, a control unit 204, an input device 206, and an output device 208.

[0035] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012.

[0036] User ID 2011 is the user's account ID. The user sends User ID 2011 from user terminal 20 to server 10. Server 10 identifies the user based on User ID 2011 and provides the services related to this disclosure to the user. User ID 2011 includes information such as a session ID that is temporarily assigned by server 10 to identify the user using user terminal 20.

[0037] The application program 2012 may be pre-stored in the memory unit 201, or it may be configured to be downloaded from a web server operated by the service provider via a communication interface. Application Program 2012 includes applications such as web browser applications. Application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0038] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 comprises an input control unit 2041 and an output control unit 2042. The control unit 204 realizes each functional unit by executing the application program 2012 stored in the memory unit 201.

[0039] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061, a microphone 2062, a position information sensor 2063, a motion sensor 2064, and a touch device 2065.

[0040] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082.

[0041] <Configuration of Administrator Terminal 30> The administrator terminal 30 is an information processing device operated by the administrator who manages the service. The administrator terminal 30 may be a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer) or laptop PC. It may also be a wearable device such as an HMD (Head Mount Display) or a smartwatch. The administrator terminal 30 includes a storage unit 301, a control unit 304, an input device 306, and an output device 308.

[0042] <Configuration of the storage unit 301 of the administrator terminal 30> The storage unit 301 of the administrator terminal 30 contains user ID 3011 and application program 3012.

[0043] User ID 3011 is the user's account ID. The user sends User ID 3011 from the administrator terminal 30 to the server 10. The server 10 identifies the user based on User ID 3011 and provides the services related to this disclosure to the user. User ID 3011 includes information such as a session ID that is temporarily assigned by the server 10 to identify the user using the administrator terminal 30.

[0044] The application program 3012 may be pre-stored in the memory unit 301, or it may be configured to be downloaded from a web server operated by the service provider via a communication interface. The application program 3012 includes an interpreted programming language such as JavaScript (registered trademark) that is executed on a web browser application stored in the administrator terminal 30.

[0045] <Configuration of the control unit 304 of the administrator terminal 30> The control unit 304 of the administrator terminal 30 comprises an input control unit 3041 and an output control unit 3042. The control unit 304 realizes each functional unit by executing the application program 3012 stored in the storage unit 301.

[0046] <Configuration of the input device 306 of the administrator terminal 30> The input device 306 of the administrator terminal 30 includes a camera 3061, a microphone 3062, a location information sensor 3063, a motion sensor 3064, and a keyboard 3065.

[0047] <Configuration of output device 308 of administrator terminal 30> The output device 308 of the administrator terminal 30 includes a display 3081 and a speaker 3082.

[0048] <Configuration of Generation AI50> Generative AI50 refers to large-scale artificial intelligence models used in the field of natural language processing (NLP). These models learn from large amounts of text data (web pages, books, articles, etc.) to understand patterns in human language and effectively perform natural language generation (NLG) tasks. Generative AI50 is used in many NLP tasks, such as generating responses to specific questions, automatically generating text, summarizing text, translation, and sentiment analysis. It can also be used in a variety of applications, including education, entertainment, customer service, and product development. Generative AI50 includes the following types. In this disclosure, large-scale language models that primarily output text information as output are described as a type of Generative AI50. OpenAI ChatGPT Anthropic Claude Google Gemini Stable Diffusion • Midjourney Furthermore, the generation AI50 may be implemented as part of the functions of server 10.

[0049] <System 1 operation> The following describes each process in System 1. Figure 14 is a flowchart showing the operation of the project planning process. Figure 15 is a flowchart showing the operation of the questionnaire processing. Figure 16 is a flowchart showing the operation of the interview process. Figure 17 is a flowchart showing the operation of the consistency check process. Figure 18 is a flowchart showing the operation of the viewpoint analysis process. Figure 19 is a flowchart showing the operation of the insight analysis process. Figure 20 is an example of the first screen showing the operation of the viewpoint analysis process. Figure 21 is an example of the second screen showing the operation of the viewpoint analysis process. Figure 22 shows an example screen illustrating the operation of the insight analysis process.

[0050] <Project creation process> The project planning process involves creating plans (projects) for consumer surveys and consumer interviews.

[0051] <Overview of the project creation process> The project creation process is a series of steps that involve opening the project creation page, entering project information, entering questions, and then executing the input completion process based on the entered information.

[0052] <Details of the project creation process> The details of the project planning process are explained below.

[0053] <Open the project creation page> In step S101, the administrator of the information processing service, etc. related to this disclosure operates the input device 306 of the administrator terminal 30 to enter the URL of the page for executing the plan creation process (plan creation processing page) into a web browser, etc., and opens the plan creation processing page. The control unit 304 of the administrator terminal 30 sends a request to the server 10 to open the plan creation processing page. The control unit 104 of the server 10 generates the plan creation processing page based on the received request and sends it to the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays the received plan creation processing page on the display 3081 of the administrator terminal 30. The project creation processing page includes input fields for project name, target audience, project content, and perspectives. Each input field corresponds to a column in project table 1013. The project creation processing page also includes input fields for one or more questions.

[0054] <Entering project information> In step S102, the administrator enters input values ​​into the respective input fields for project name, target audience, project content, and perspective by operating the input device 306 of the administrator terminal 30.

[0055] <Enter your question> In step S103, the administrator enters input values ​​into the input field for the question content by operating the input device 306 of the administrator terminal 30.

[0056] <Input of project information (first embodiment)> The input value for the perspective may be configured to be entered based on the input value of the question content. Specifically, the control unit 104 of the server 10 creates a prompt by including the input value of the question content in instruction statement C1. The control unit 104 of the server 10 inserts the input value of the question content at the ${question content} part of the following instruction statement C1. <Instruction C1> The following are survey questions for consumers. Based on the content of these survey questions, please output the perspectives for your consumer research. #Questionnaire ${Question}

[0057] The control unit 104 of server 10 inputs the created prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the prompt input. The output content includes information about the viewpoint. The control unit 104 of server 10 receives the output content. The control unit 104 of server 10 sends the received output content to the administrator terminal 30. The control unit 304 of administrator terminal 30 inputs the received output content into the viewpoint input field.

[0058] <Input of project information (second embodiment)> The input values ​​for the question content may be configured to be entered based on the input values ​​for the perspective. Specifically, the control unit 104 of the server 10 creates a prompt by including the input values ​​for the perspective in instruction statement C2. The control unit 104 of the server 10 inserts the input values ​​for the perspective at the ${perspective} part of the following instruction statement C2. <Instruction C2> The following are the points we would like to investigate in our consumer survey. Based on these points, please output a bulleted list of questions for the consumer questionnaire. #Consumer research perspective ${view}

[0059] The control unit 104 of server 10 inputs the created prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the prompt input. The output content includes information about the question. The control unit 104 of server 10 receives the output content. The control unit 104 of server 10 sends the received output content to the administrator terminal 30. The control unit 304 of administrator terminal 30 inputs the received output content into the question content input field.

[0060] The control unit 304 of the administrator terminal 30 sends the input values ​​of the project name, target audience, project content, perspective, and question content entered in the input fields to the server 10.

[0061] <Input completion process> In step S104, the control unit 104 of the server 10 stores the received project name, target audience, project content, and perspective in the project name, target audience, project content, and perspective fields of the new record in the project table 1013, respectively. The control unit 104 of the server 10 also stores the project ID of the new record in the project table 1013 and one or more question contents in the project ID and question content fields of the new record in the question table 1014, respectively. The control unit 104 of server 10 stores a prompt (instruction statement) for having the AI ​​conduct a consumer interview in the item "Prompt A". The control unit 104 of server 10 creates Prompt A by inserting the value of the "Perspective" item into the ${Perspective} part of instruction statement A stored in the storage unit 101 of server 10. Prompt A may also be created during the interview processing described later by inserting the value of the "Perspective" item into the ${Perspective} part of instruction statement A. The control unit 104 of server 10 stores the created Prompt A in the item "Prompt A" of the planning table 1013.

[0062] <Instructive sentence A> Please create interview transcripts to gather information from users regarding the following consumer research perspectives. The transcripts should be written in conversational language. #Consumer research perspective ${view}

[0063] <Survey Processing> The survey process involves asking users one or more questions and receiving one or more answers for each of those questions.

[0064] <Overview of Questionnaire Processing> The survey processing involves a series of steps: the user opens a website with a response page on their user terminal 20, the website presents questions to the user, and the user submits answers to those questions.

[0065] <Details of the survey processing> The details of the survey processing are explained below. In this disclosure, a survey process for a specified user is disclosed as an example. The survey process is performed for each user whose user ID is included in the target audience section of the project created during the project creation process. For example, after the input completion process of the project creation process (step S104), a message such as an email containing the URL of the survey processing page may be sent to the user whose user ID is included in the target audience of the project. This allows the user to answer the survey by selecting the URL included in the message such as the email.

[0066] <Open answer page> In step S201, the user operates the input device 206 of the user terminal 20 to enter the URL of the page for executing the survey (survey processing page) into a web browser or the like, and opens the survey processing page. The control unit 204 of the user terminal 20 sends a request to the server 10 to open the survey processing page. The URL may include identification information such as a string to identify the project ID. The control unit 104 of server 10 identifies a predetermined project ID based on the string contained in the URL. Based on the project ID, the control unit 104 of server 10 searches the project ID item in the question table 1014 and retrieves the question content. Based on the retrieved question content, the control unit 104 of server 10 generates an questionnaire processing page that includes a question form that can accept input from the user for the answer to the question content. Based on the received request, the control unit 104 of server 10 generates the questionnaire processing page and sends it to the user terminal 20.

[0067] <Question form provided> In step S202, the control unit 204 of the user terminal 20 performs a form presentation step in which it presents the user with a question form relating to one or more perspectives. Specifically, the control unit 204 of the user terminal 20 displays the received survey processing page on the display 2081 of the user terminal 20.

[0068] <Replies accepted> In step S203, the processing unit 1043 of the server 10 executes a response acquisition step to acquire the answers entered by the user in response to the question form presented in the form presentation step. Specifically, the user inputs values ​​into the input fields for the answers to the questions included in the survey processing page by operating the input device 206 of the user terminal 20. One or more answers are associated with a question ID of the question content included in the question form. For example, for questions with question IDs A, B, and C, the user inputs answers A, B, and C. The control unit 204 of the user terminal 20 sends the user ID 2011, one or more question IDs, and one or more answer contents associated with the question IDs to the server 10. The control unit 104 of the server 10 receives and accepts the answer contents. The control unit 104 of the server 10 stores the received user ID, question ID, and answer contents in the user ID, question ID, and answer contents fields of the answer table 1015, respectively. As a result, the answer contents that the user has answered are stored in the answer table 1015, associated with one or more question contents.

[0069] <Interview Processing> The interview process involves conducting one or more interviews with the user and receiving one or more statements from those interviews.

[0070] <Overview of Interview Processing> The interview process involves a series of steps: the user opens a website with an interview page on the user terminal 20 to conduct consumer interviews; interview questions are created for the user; the interview questions are presented to the user; and utterances are received from the user. The presentation of interview questions to the user and the reception of utterances from the user are repeated until all one or more interviews are completed.

[0071] <Details of interview processing> The details of the interview process are described below. In this disclosure, an interview process for a specified user is disclosed as an example. The interview process is performed for each user whose user ID is included in the target user section of the project created in the project creation process. For example, after receiving responses to the questionnaire (step S203), a message such as an email containing the URL of the interview process page may be sent to the user whose user ID is included in the target user section of the project. This allows the user to respond to the interview (speak) by selecting the URL included in the message such as the email.

[0072] <Open interview page> In step S301, the user operates the input device 206 of the user terminal 20 to enter the URL of the page for executing the interview process (interview processing page) into a web browser or the like, and opens the interview processing page. The control unit 204 of the user terminal 20 sends a request to the server 10 to open the interview processing page. The URL may include identification information such as a string to identify the project ID. The control unit 104 of server 10 identifies a predetermined project ID based on the string contained in the URL. Based on the project ID, the control unit 104 of server 10 searches the project ID item in project table 1013 and obtains prompt A.

[0073] <Creating Interview Questions>

[0074] <Creating Interview Questions (Step 0)> In step S302, the processing unit 1043 of the server 10 performs a zero-creation step in which it creates a zero-prompt by including information on one or more perspectives in the instruction to create an interview question. Specifically, the control unit 104 of server 10 searches the project ID field in project table 1013 based on the acquired project ID and retrieves the perspective field. The control unit 104 of server 10 inserts the value of the perspective field into the ${perspective} field of instruction A to create prompt A (0th prompt). The control unit 104 of server 10 stores the created prompt A (0th prompt) in the prompt A field of the record identified based on the project ID in project table 1013. Furthermore, this disclosure also discloses an example of creation in the input completion process of step S104 of the plan creation process. Prompt A may be executed in the plan creation process or in the interview process.

[0075] The processing unit 1043 of server 10 executes a zero input step, which inputs a zero prompt to the artificial intelligence system. The processing unit 1043 of server 10 executes a zero output step, which obtains a zero output that is output in response to inputting a zero prompt to the artificial intelligence system. Specifically, the control unit 104 of the server 10 inputs the created prompt A by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of prompt A. The output content includes a string related to the consumer interview (the 0th interview question). If the perspective includes image information or string information such as a URL indicating an image, the processing unit 1043 of the server 10 outputs the first interview question which includes the image information or string information such as a URL indicating an image. The same applies to the first and second interview questions. In addition, the control unit 204 of the user terminal 20 may display the image information identified based on the image information or string information such as a URL in the interview question on the display 2081 of the user terminal 20 when presenting the interview content (step S303).

[0076] <Creating Interview Questions (First Creation Step)> In step S302, the processing unit 1043 of the server 10 executes a first creation step to create a first prompt by including the content of the user's first utterance obtained in the first utterance acquisition step in a first instruction for creating an interview question to obtain information from the user from one or more perspectives. The first creation step executes a step to create a first prompt by including the content of the first utterance in a first instruction based on the zeroth output obtained in the zeroth output step. Specifically, the control unit 104 of the server 10 creates a first prompt by inputting the value of prompt A in the ${prompt A} part of the first instruction statement and the value of the first utterance content obtained in the utterance acquisition step of step S304 (first utterance acquisition step) in the ${first utterance content} part. For example, a first prompt containing prompt A in the prompt where the role value is assistant, and a first prompt containing the first utterance content in the prompt where the role value is user may be created. <1st directive> Interview: ${Prompt A} Utterance content: ${First utterance content}

[0077] The processing unit 1043 of the server 10 performs a first input step, which involves inputting a first prompt to the artificial intelligence system. The processing unit 1043 of the server 10 then performs a first output step, which involves obtaining a first output that is output in response to inputting the first prompt to the artificial intelligence system. Specifically, the control unit 104 of the server 10 inputs the created first prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the first prompt. The output content includes a string of characters (first interview questions) related to a consumer interview to explore the user's interests and concerns from one or more perspectives, taking into account the first utterance content received by the user in the utterance acquisition step (first utterance acquisition step).

[0078] <Creating interview questions (Second creation step)> In step S302, the processing unit 1043 of the server 10 performs a second creation step in which it creates a second prompt by including a first utterance, an interview based on the first output, and a second utterance in a second instruction for creating an interview question to obtain information from the user from one or more perspectives. Specifically, the control unit 104 of the server 10 creates the second prompt by inputting the value of the first prompt in the ${first prompt} part of the second instruction statement and the value of the second utterance content obtained in the utterance acquisition step (second utterance acquisition step) of step S304 in the ${second utterance content} part. <Second directive> ${First prompt} Utterance content: ${Second utterance content}

[0079] Specifically, the second prompt is created based on Prompt A, the first utterance, the first interview question, and the second utterance, as follows. For example, a second prompt may be created that includes Prompt A in the Assistant's prompt, the first utterance in the User's prompt, the first interview question in the Assistant's prompt, and the second utterance in the User's prompt. <Second prompt> Interview: ${Prompt A} Utterance content: ${First utterance content} Interview: ${First Interview Question} Utterance content: ${Second utterance content}

[0080] The processing unit 1043 of server 10 executes a second input step, which involves inputting a second prompt to the artificial intelligence system. The processing unit 1043 of server 10 executes a second output step, which involves obtaining a second output that is output in response to inputting the second prompt to the artificial intelligence system. Specifically, the control unit 104 of the server 10 inputs the created second prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the second prompt. The output content includes a string of characters (second interview questions) relating to a consumer interview to further explore the user's interests and concerns from one or more perspectives, taking into account the first and second utterances made by the user received in the utterance acquisition steps (first utterance acquisition step and second utterance acquisition step).

[0081] <Creating Interview Questions (Step N)> In step S302, the processing unit 1043 of the server 10 performs the Nth creation step to create the Nth prompt by including summary information that summarizes at least a portion of the utterances from the first utterance to the (N-1)th utterance, and the Nth utterance, in the Nth instruction for creating an interview question to obtain information from the user from one or more perspectives. Specifically, the control unit 104 of the server 10 creates the Nth prompt by inputting the value of the N-1st prompt in the ${N-1st prompt} section of the Nth instruction statement, and the value of the Nth utterance content obtained in the utterance acquisition step S304 (Nth utterance acquisition step) in the ${Nth utterance content} section. <Nth directive> ${the (N-1)th prompt} Utterance content: ${Utterance content of the Nth}

[0082] Specifically, the Nth prompt is created based on Prompt A, the first utterance, the first interview question, the second utterance, ...the N-1th interview question, and the Nth utterance, as follows. For example, the Nth prompt may be created with the role value set to Assistant, containing an interview question that includes Prompt A, and the role value set to User, containing an utterance. <Nth prompt> Interview: ${Prompt A} Utterance content: ${First utterance content} Interview: ${First Interview Question} Utterance content: ${Second utterance content} ... Utterance content: ${Utterance content of the (N-1)} Interview: ${Interview Question No. N-1} Utterance content: ${Utterance content of the Nth}

[0083] The processing unit 1043 of server 10 executes an Nth input step, which inputs the Nth prompt to the artificial intelligence system. The processing unit 1043 of server 10 executes an Nth output step, which obtains the Nth output that is output in response to inputting the Nth prompt to the artificial intelligence system. Specifically, the control unit 104 of the server 10 inputs the created Nth prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the Nth prompt. The output content includes a string of characters (the Nth interview question) relating to a consumer interview to further explore the user's interests and concerns from one or more perspectives, taking into account the first utterance content, second utterance content, ... Nth utterance content received by the user in the utterance acquisition step (first utterance acquisition step, second utterance acquisition step... Nth utterance acquisition step).

[0084] The control unit 104 of the server 10 may replace the information contained in the Nth prompt with information that summarizes at least a portion of the utterances or interview questions included from the first utterance to the N-1th utterance. Specifically, the control unit 104 of the server 10 creates a summary creation prompt by inserting at least a portion of the utterances or interview questions included from the first utterance to the N-1th utterance into the ${Consumer Interview Content} section of the summary creation instruction shown below.

[0085] <Instructions for creating a summary> Please briefly summarize the following consumer interviews in approximately 500 characters. #ConsumerInterview ${Contents of consumer interviews}

[0086] <Summary creation prompt> Please briefly summarize the following consumer interviews in approximately 500 characters. #ConsumerInterview Utterance content: ${First utterance content} Interview: ${First Interview Question} Utterance content: ${Second utterance content} ... Utterance content: ${Utterance content of the (N-1)}

[0087] The control unit 104 of the server 10 receives the created summary creation prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the summary creation prompt. The output content includes a string (summary string) that summarizes at least a portion of the utterances or interview questions included from the first utterance to the N-1th utterance.

[0088] The control unit 104 of the server 10 creates the Nth prompt (modified version) by replacing at least a portion of the utterances or interview questions included in the first utterance of the Nth prompt to the N-1th utterance with a summary string.

[0089] <Nth prompt (variation)> Interview: ${Prompt A} ${summary string} Interview: ${Interview Question No. N-1} Utterance content: ${Utterance content of the Nth}

[0090] This helps to prevent prompts from becoming excessively long, even in lengthy interviews where there is a large amount of information from the user and their utterances. By summarizing parts of the utterances, it becomes possible to create more appropriate interview questions based on the user's key utterances that align with the interview perspective.

[0091] <Presenting interview questions (0th presentation step)> In step S303, the control unit 104 of the server 10 generates an interview processing page that can accept input from the user of spoken audio (spoken content) in response to the 0th interview question created in the 0th creation step (0th creation step). The control unit 104 of the server 10 generates the interview processing page and sends it to the user terminal 20. The control unit 104 of server 10 sends the first interview question created in the first interview question creation step to the user terminal 20. Alternatively, the control unit 104 of server 10 may convert the first interview question into speech and send it to the user terminal 20. The control unit 204 of the user terminal 20 outputs audio based on the received interview questions to the user via the speaker 2082 of the user terminal 20. The user can receive an audio presentation of the interview questions. In this disclosure, an audio interview is disclosed as an example, but it is also acceptable to present it using visual methods such as text, images, or videos.

[0092] <Presenting interview questions (first presentation step)> The control unit 104 of server 10 presents the first interview question created in the interview question creation step (first creation step) to the user. The presentation of the interview question is the same as the presentation of the interview question (0th presentation step), except that the interview question is the first interview question and not the 0th interview question, so the explanation is omitted. Furthermore, the explanation for the presentation of interview questions (second presentation step) and the presentation of interview questions (nth presentation step) is omitted, as they are the same as the presentation of interview questions (zero presentation step), except that the interview questions are the second and nth interview questions, respectively, instead of the zeroth interview question.

[0093] In step S303, the processing unit 1043 of the server 10 executes a shooting step in which the user is photographed during the interview period using the camera provided in the user terminal. Specifically, the control unit 204 of the user terminal 20 takes a picture of the user by controlling the camera 2061 of the user terminal 20 in response to the presentation of interview questions. The control unit 204 of the user terminal 20 may also acquire the user's voice by controlling the microphone 2062. In this disclosure, taking a picture includes acquiring the user's voice.

[0094] In step S303, the shooting step performs the step of shooting the user during the interview period, which includes the first period and the extended period. Specifically, the control unit 204 of the user terminal 20 records the user from the time the first interview question (the 0th interview question) is presented until the interview is completed. Specifically, even if the interview is interrupted (extended) as described later, the control unit 204 of the user terminal 20 may record the user's state regardless of the interruption period (extension period).

[0095] This allows us to record and remember the user's behavior during periods of deep thought in the interview. Without needing to capture the user's spoken content during the first period, we can record the user's behavior and use it as reference information for the interview.

[0096] In this disclosure, the interview process is disclosed as an example in which a user performs the first to the nth interview at once, but is not limited to this. For example, a user may close the interview page and end the interview in the middle of it. In this case, when the user reopens the interview page, they may be able to resume the interview from where they left off (first interview, second interview...nth interview). For example, the control unit 104 of the server 10 and the control unit 204 of the user terminal 20 may resume the interview by referring to the interview prompt, interview content, spoken content, and other flag information (not shown) indicating the completion of the interview stored in the interview table. In this case as well, the control unit 204 of the user terminal 20 resumes control to film the user during the interview period. In this case, the control unit 204 stores video data of the user filmed and stored according to the number of times the interview has been resumed. The control unit 204 of the user terminal 20 may combine the video data of the user filmed and stored after the resumed interview with the previously created video data of the user filmed and stored, and store the video data of the user filmed and stored after the resumed interview in a single file. Alternatively, the control unit 204 of the user terminal 20 may combine the multiple video data of the user filmed and stored into a single video data after determining the completion of the interview in step S305, which will be described later. Alternatively, the combination of video data may be performed by the control unit 104 of the server 10.

[0097] <Speech acquisition> In step S304, the processing unit 1043 of the server 10 performs a speech acquisition step to acquire the content of the user's speech in response to presenting the interview to the user. Specifically, the input device 206 (microphone 2062) of the user terminal 20 receives the user's utterances in response to the interview questions presented in step S303. For example, if the interview question is, "What manufacturer is your motorcycle?", and the user utters, "Yamazaki Heavy Industries," the microphone 2062 acquires and accepts the utterance. The control unit 204 of the user terminal 20 transmits the acquired utterance to the server 10. The control unit 104 of the server 10 receives and accepts the utterance from the user terminal 20. The control unit 104 of the server 10 stores the spoken audio in the "Speech Content" field of the target record in the interview table 1016. Alternatively, the control unit 104 of the server 10 may convert the audio data received from the user into a string using a known speech recognition function or the like, and store that string in the "Speech Content" field of the interview table 1016.

[0098] <Utterance Acquisition (First Utterance Acquisition Step)> In step S304, the processing unit 1043 of the server 10 executes a first utterance acquisition step to obtain the content of the first utterance from the user. Specifically, the control unit 104 of the server 10 acquires the utterance content (first utterance content) in response to the 0th interview question presented to the user during the interview question presentation step (0th presentation step), and stores it in the utterance content item of the interview table 1016.

[0099] <Utterance Acquisition (Second Utterance Acquisition Step)> In step S304, the processing unit 1043 of the server 10 performs a second utterance acquisition step to acquire the content of a second utterance from the user, in response to presenting the user with an interview based on the first output. Specifically, the control unit 104 of the server 10 acquires the utterance content (second utterance content) in response to the first interview question presented to the user during the interview question presentation (first presentation step), and stores it in the utterance content item of the interview table 1016.

[0100] <Utterance Acquisition (Step 1 of acquiring the Nth utterance)> In step S304, the processing unit 1043 of the server 10 executes a step to acquire the content of the Nth utterance from the user. Specifically, the control unit 104 of the server 10 acquires the content of the utterance (the Nth utterance) in response to the N-1st interview question presented to the user during the interview question presentation step (the N-1st presentation step), and stores it in the utterance content item of the interview table 1016.

[0101] <Speech acquisition (first embodiment)> In step S304, the speech acquisition step performs the step of acquiring the user's speech content during the first period after presenting the interview to the user. Specifically, the control unit 204 of the user terminal 20 presents interview questions to the user and then executes control to acquire the user's utterances during a predetermined period (first period), such as 10 seconds, 20 seconds, 30 seconds, or 1 minute. Specifically, after presenting interview questions to the user and the first period has elapsed, the control unit 204 of the user terminal 20 terminates the utterance acquisition step and stores the user's utterances in the utterance content item of the interview table 1016.

[0102] <Speech acquisition (second embodiment)> In step S304, the processing unit 1043 of the server 10 executes an extension step in which it receives an input operation from the user to extend the first period. The speech acquisition step executes a step of acquiring the user's speech content during the first period and the predetermined extension period, excluding the user's speech content during the predetermined extension period. Specifically, the interview processing page may include a "speech interruption button." The user selects the "speech interruption button" by operating the input device 206 of the user terminal 20. When the control unit 204 of the user terminal 20 detects the selection of the speech interruption button, it stops acquiring the content of the user's speech. The control unit 204 of the user terminal 20 resumes acquiring the content of the user's speech after a predetermined period has elapsed since the user selected the speech interruption button. Alternatively, the acquisition of the content of the user's speech may be resumed in response to input operations by the input device 206 of the user terminal 20 on a "speech resume button" or similar included in the interview processing page. As a result, the period during which the user can speak in response to interview questions (the first period) is extended by a predetermined period depending on the interruption period.

[0103] <Speech acquisition (third embodiment)> In step S304, the speech acquisition step executes the step of acquiring the user's speech content in response to the input operation received from the user. Specifically, the control unit 204 of the user terminal 20 terminates the speech acquisition step in response to an input operation by the input device 206 of the user terminal 20, such as the "end speech button" included in the interview processing page, and stores the user's speech content in the speech content item of the interview table 1016.

[0104] <Speech acquisition (Fourth embodiment)> In step S304, the processing unit 1043 of the server 10 receives an input operation from the user to redo the interview, and executes a retry step in which it repeats the speech acquisition step according to the input operation. Specifically, the control unit 204 of the user terminal 20 can restart the presentation of interview questions in step S303 or the acquisition of spoken content in step S304 from the beginning in response to an input operation by the input device 206 of the user terminal 20 to the "retry button" or the like included in the interview processing page. This allows users to re-answer if they were unable to provide an appropriate response, reducing user stress during interviews.

[0105] <Interview Completion Determination> In step S305, the control unit 104 of the server 10 determines whether the interview is complete or not. The completion of the interview may also be determined by the following method. • In the interview question creation step S302, if, in response to the input of a prompt for creating interview questions to the artificial intelligence system 50, the artificial intelligence system 50 outputs information indicating that there are no additional interviews to be conducted, - If one or more utterances obtained in the utterance acquisition step S304 during the interview processing meet predetermined conditions. For example, if the output obtained by inputting a prompt generated by including a viewpoint and utterances in the instruction to determine the completion of the interview to the artificial intelligence system 50 includes information indicating that the interview has been completed. • If the duration of the user's spoken audio exceeds a specified period. • If the user inputs an action indicating that they wish to end the interview,

[0106] In step S305, if the control unit 104 of the server 10 determines that the interview is not complete, it returns to step S302.

[0107] If the control unit 104 of the server 10 determines that the interview is not complete after acquiring the content of the first utterance in the speech acquisition step (first utterance acquisition step) in step S304, it executes the interview question creation step (first creation step) in step S302. Similarly, if it determines that the interview is not complete after acquiring the content of the second utterance and the Nth utterance in the speech acquisition step (second utterance acquisition step) and speech acquisition step (nth utterance acquisition step), it executes the interview question creation step (second creation step) and the interview question creation step (nth creation step) in step S302.

[0108] In step S305, if the control unit 104 of the server 10 determines that the interview is complete, it sends information to the user terminal 20 indicating that the interview is complete. Upon receiving this information, the control unit 204 of the user terminal 20 displays the information indicating that the interview is complete on the user terminal 20's display 2081 or the like. This completes the interview process.

[0109] <Integrity verification process> The consistency verification process determines whether the response results from a questionnaire and the utterances from an interview conducted by a designated user are consistent.

[0110] <Overview of the consistency verification process> The consistency verification process involves acquiring project information, identifying users (target individuals) who are the subject of consumer survey information collection for that project, acquiring questionnaire responses from those users, acquiring interview questions and statements from those users, and determining the consistency between the questionnaire responses and the interview statements. This allows for the verification of the consistency of the content of consumer survey information.

[0111] <Details of the consistency verification process> The details of the consistency check process are described below.

[0112] <Acquire project information> In step S401, a plan ID is obtained to identify the predetermined plan information related to the consistency check process. The consistency verification process may identify the specified project ID for which the survey and interview processes have been completed for all users related to the target group for the specified project. The consistency verification process may also identify and obtain the specified project ID in response to user input operations related to the administrator.

[0113] <Identifying Target Individuals> In step S402, the control unit 104 of the server 10 searches the project ID item in the project table 1013 based on a predetermined project ID obtained in step S401, and retrieves and identifies one or more user IDs stored in the target person item.

[0114] <Get questions and answers> In step S403, the control unit 104 of the server 10 searches the user ID field in the answer table 1015 based on the one or more user IDs obtained in step S402, and obtains the question ID and answer content. Based on the obtained question ID, the control unit 104 of the server 10 searches the question ID field in the question table 1014, and obtains the question content. As a result, the control unit 104 of the server 10 acquires the questions asked to users and the content of the user's responses in the survey processing for users who are the target of a predetermined project.

[0115] <Interview speech acquisition> In step S404, the control unit 104 of the server 10 searches the user ID field in the interview table 1016 based on the one or more user IDs obtained in step S402, and obtains the interview questions and spoken content. As a result, the control unit 104 of the server 10 acquires interview questions for the user and the content of the user's speech during the interview process with the target person of the predetermined project.

[0116] <Consistency judgment> In step S405, the processing unit 1043 of the server 10 executes a comparison creation step to create a comparison prompt by including the answer content obtained in the answer acquisition step and at least a portion of the user's utterance in the instruction to compare the answer content to the question form with the user's utterance in the interview. The comparison creation step involves creating a comparison prompt by including the answers to the question form and at least a portion of the user's utterances in an instruction to determine whether the answers to the question form and the user's utterances in the interview are consistent. Specifically, the control unit 104 of the server 10 creates a comparison prompt by inserting the acquired values ​​of question content, answer content, interview question, and utterance content into the respective sections of instruction statement B stored in the storage unit 101 of the server 10, namely ${question content}, ${answer content}, ${interview question}, and ${utterance content}. If there are multiple questions, answers, interview questions, and utterances, the control unit 104 inserts each of the questions, answers, interview questions, and utterances contained within them into the sections named question content1, answer content1, interview question1, utterance content1, question content2, answer content2, interview question2, utterance content2, etc., to create a comparison prompt. The comparison prompt is created for each user by including the user-specific question content, answer content, interview questions, and utterance content in instruction text B.

[0117] <Instruction text B> The following are survey and interview results from specific users regarding specific perspectives. Compare the survey results with the interview results and determine whether the content of the user's responses and the content of the user's statements are consistent. #Survey Results ## Question 1 ${Question 1} ##Answer content 1 ${Answer content 1} ## Question 2 ${Question 2} ##Answer content 2 ${Answer content 2} ... #Interview results ## Interview Question 1 ${Interview Question 1} ## Speech content 1 ${Speech content 1} ## Interview Question 2 ${Interview Question 2} ## Speech Content 2 ${Speech content 2} ...

[0118] The comparison creation step involves creating comparison prompts by including the answers and at least a portion of the user's utterances in the instructions for determining whether the user's utterances to the interview are consistent for each of the one or more question perspectives in the question form. Specifically, the control unit 104 of the server 10 may generate a prompt to output a judgment result for each of the question contents (for each of the answer contents) based on the instruction statement B (modified version) stored in the storage unit 101 of the server 10. This allows for a comparison of the consistency between user information collected for one or more question perspectives in the question form and user information collected through interviews. This allows for a more detailed verification of the consistency of consumer survey information collected from users.

[0119] <Instruction B (Variation)> The following are survey and interview results from specific users regarding specific perspectives. Compare the survey results with the interview results, and determine whether the content of each response in the survey is consistent with the user's statements. #Survey Results ## Question 1 ${Question 1} ##Answer content 1 ${Answer content 1} ## Question 2 ${Question 2} ##Answer content 2 ${Answer content 2} ... #Interview results ## Interview Question 1 ${Interview Question 1} ## Speech content 1 ${Speech content 1} ## Interview Question 2 ${Interview Question 2} ## Speech Content 2 ${Speech content 2} ...

[0120] In step S506, the control unit 104 of the server 10 inputs the created comparison prompt by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the comparison prompt. The output content includes information indicating the result of the determination of consistency between the answers to the questionnaire questions and the spoken content of the interview. The control unit 104 of the server 10 stores the judgment result value included in the output content in the judgment result item of the answer table 1015. In this disclosure, as an example, the output content for instruction B (modified version) (the judgment result for each of the one or more question contents and answer contents) is stored in the judgment result item of the answer table 1015, but the invention is not limited to this. For example, in instruction B, information indicating the consistency judgment result is output to the user. In this case, the information identifying the user to be judged may be stored in the "Target Person" field of the planning table 1013 in association with the information identifying the user to be judged.

[0121] <Perspective Analysis Processing> Perspective analysis is a process that analyzes user consumer survey information collected through methods such as questionnaires and interviews, according to one or more specific perspectives (analysis perspectives).

[0122] <Overview of viewpoint analysis processing> The perspective analysis process is a series of operations that accepts input of analysis perspectives, input of analysis items, input of users (subjects) related to the analysis target, acquires survey information related to the accepted users, generates prompts based on the input information and survey information, and obtains and presents the perspective analysis results output by inputting the prompts to the generation AI50.

[0123] <Details of the perspective analysis process> The details of the perspective analysis process are described below.

[0124] <Input of analysis perspective> In step S501, the administrator operates the input device 306 of the administrator terminal 30 to enter the URL of the page for executing the viewpoint analysis process (viewpoint analysis processing page D1) into a web browser or the like, and opens the viewpoint analysis processing page. The control unit 304 of the administrator terminal 30 sends a request to the server 10 to open the viewpoint analysis processing page. The control unit 104 of the server 10 generates the viewpoint analysis processing page based on the received request and sends it to the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays the received viewpoint analysis processing page D1 on the display 3081 of the administrator terminal 30. The administrator sends the project ID for the viewpoint analysis process to the server 10 by operating the input device 306 of the administrator terminal 30. The URL may also include a string to identify the project ID for the viewpoint analysis process. Figure 20 shows an example of the first screen of page D1 in the viewpoint analysis process. Page D1 includes input fields for viewpoint name D11, viewpoint instruction D12, and analysis item D13. Each item corresponds to an item in the analysis viewpoint table 1031.

[0125] In step S501, the processing unit 1043 of the server 10 performs an instruction acquisition step to obtain a first instruction to output one or more viewpoints regarding the survey information. The processing unit 1043 of the server 10 performs a second instruction acquisition step to obtain a second instruction to output one or more viewpoints. Specifically, the administrator inputs an instruction into the perspective instruction D12 by operating the input device 306 of the administrator terminal 30. For example, instructions such as "If you were to use an animal as an example" or "Preferential behavior of animals" are entered. The control unit 304 of the administrator terminal 30 sends the instruction entered into the perspective instruction D12 to the server 10. The control unit 104 of the server 10 receives and accepts the instruction.

[0126] In step S501, the instruction acquisition step performs the step of acquiring a first instruction for each of the multiple users, which outputs one or more perspectives on the survey information. Specifically, the analysis process based on the perspective instruction statement D12 is performed on one or more users included in the target person item of the project information, which is identified by searching for the project ID in the project table 1013 based on the project ID related to the perspective analysis process.

[0127] <Analysis item submission> In step S502, the processing unit 1043 of the server 10 performs a survey presentation step in which it presents information indicating one or more survey pieces to the user in a selectable manner. The processing unit 1043 of the server 10 executes a survey selection step in which it receives a selection from the user of information indicating a predetermined survey information from among the information indicating one or more survey information presented in the survey presentation step. Specifically, the administrator selects the survey information to be analyzed from one or more survey information (data sources) included in analysis item D13 by operating the input device 306 of the administrator terminal 30. For example, the survey information can be selected from the content of responses in questionnaire processing, the content of utterances in interview processing, etc.

[0128] The processing unit 1043 of the server 10 performs an output presentation step that presents the user with selectable information indicating one or more output contents. The processing unit 1043 of the server 10 executes an output selection step in which it receives from the user the selection of information indicating a predetermined output content from the information indicating one or more output contents presented in the output presentation step. Specifically, in addition to the content of responses in the questionnaire and the content of speech in the interview, it is also possible to select the viewpoint analysis results output for each user in the viewpoint analysis process as analysis items. For example, the content of responses in a survey or utterances in an interview with a specific user can be used as the basis for selecting the perspective analysis results output by perspective analysis processing, based on specific viewpoints such as "If you were to compare them to an animal" or "Preferences for favorite animals," as analysis items. This allows for further analysis of the results output from survey information collected from users through questionnaires, interviews, etc., from one or more perspectives. Further in-depth analysis can be performed on the results obtained from the survey information, based on specific perspectives.

[0129] <Analysis User Registration> In step S503, the control unit 104 of the server 10 searches the project ID column in the project table 1013 based on the project ID received in step S501, and retrieves the target person. The control unit 104 of the server 10 retrieves and identifies one or more user IDs included in the target person column. In addition, the administrator may manually select or exclude one or more users to be subject to viewpoint analysis processing by operating the input device 306 of the administrator terminal 30.

[0130] <Acquisition of survey information> In step S504, the processing unit 1043 of the server 10 executes a research acquisition step to acquire research information about the user. The research acquisition step executes a step to acquire research information corresponding to information indicating predetermined research information selected in the research selection step. Specifically, the control unit 104 of the server 10 acquires survey information (data source) according to the analysis items acquired in step S502 for each user who is the target of the viewpoint analysis process received in step S503. If the analysis items are the responses in the questionnaire processing, the control unit 104 of the server 10 searches the question table 1014 for the project ID and obtains the question ID and question content. Based on the question ID and user ID, the control unit 104 of the server 10 searches the response table 1015 for the question ID and user ID and obtains the response content items. If the analysis item is the content of the utterance during the interview process, the control unit 104 of the server 10 searches the interview table 1016 for the project ID and user ID, and retrieves the interview question and utterance content items. If the analysis item is the viewpoint analysis result of viewpoint analysis processing, the control unit 104 of the server 10 searches the user ID item in the analysis viewpoint result table 1032 based on the user ID and retrieves the viewpoint analysis result item.

[0131] The survey acquisition step involves performing the steps of acquiring multiple survey data points about multiple users. Specifically, the control unit 104 of the server 10 acquires multiple pieces of survey information for each of the multiple users received in step S503.

[0132] <Prompt generation> In step S505, the processing unit 1043 of the server 10 executes a creation step to create a prompt by including the investigation information obtained in the investigation acquisition step with the first instruction obtained in the instruction acquisition step. specifically,

[0133] In step S505, the creation step performs the step of creating a prompt by including in the first instruction one or more viewpoints and investigation information corresponding to information indicating predetermined investigation information. The processing unit 1043 of the server 10 executes a second creation step in which it creates a prompt by including output content in the second instruction acquired in the second instruction acquisition step. The second creation step executes a step in which it creates a prompt by including output content corresponding to information indicating predetermined output content in the second instruction. Specifically, the control unit 104 of the server 10 creates prompt D by inserting the viewpoint instruction into the ${viewpoint instruction} section of the instruction D stored in the storage unit 101 of the server 10, and the investigation information acquired in step S504 into the ${investigation information} section. Alternatively, prompt D may be created by inserting the investigation information into the ${investigation information} section of the viewpoint instruction.

[0134] <Instructive text D> ${Perspective Indicator} ${Survey Information}

[0135] <Prompt generation (first embodiment)> In step S505, the creation step performs the step of creating multiple prompts, each corresponding to a different user, by including each of the multiple pieces of survey information obtained in the survey acquisition step in the first instruction. Specifically, prompt D is created individually and independently for each of the multiple users identified in step S503. Output quality can be improved by using different prompts for each user.

[0136] <Prompt generation (second embodiment)> In step S505, the creation step performs the step of creating a prompt by including the first instruction obtained in the instruction acquisition step with multiple pieces of investigation information obtained in the investigation acquisition step. Specifically, the control unit 104 of the server 10 creates prompt D by inserting the viewpoint instruction at the ${viewpoint instruction} location and the investigation information acquired in step S504 at the ${investigation information 1}, ${investigation information 2}, ${investigation information 3}, etc. locations of the instruction D (modified version) stored in the storage unit 101 of the server 10, for each user to be analyzed. For example, investigation information 1, investigation information 2, and investigation information 3 are the investigation information of user 1, user 2, and user 3, who are the users to be analyzed in the viewpoint analysis process (investigation information relating to the analysis items identified in step S502). By including multiple pieces of research information in a prompt, the number of prompt tokens, processing cycles, and processing costs can be reduced. <Instruction D (Variation)> Please output the processing results for each of the following items: Survey Information 1, Survey Information 2, and Survey Information 3, following the instructions below. ${Perspective Indicator} #Investigation Information 1 ${Investigation Information 1} #Investigation Information 2 ${Survey Information 2} #Investigation Information 3 ${Investigation Information 3}

[0137] <Obtaining results from perspective analysis> In step S506, the processing unit 1043 of the server 10 performs an input step in which it inputs a prompt to the artificial intelligence system. It then performs an output acquisition step in which it acquires the output content that is output in response to the input of the prompt to the artificial intelligence system. The output acquisition step performs a step of acquiring output content corresponding to information indicating predetermined output content selected in the output selection step. Specifically, the control unit 104 of the server 10 inputs the created prompt D by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of prompt D. The output content includes processing results in line with the analysis perspectives accepted in step S501 for the survey information acquired in step S504.

[0138] The control unit 104 of the server 10 stores the user ID of the user subject to the viewpoint analysis process, the prompt D created for that user, and the output content from the artificial intelligence system 50 in the user ID, viewpoint analysis prompt, and viewpoint analysis result items of the viewpoint analysis result table 1032.

[0139] The control unit 104 of server 10 transmits the analysis perspective result information stored in the analysis perspective result table 1032 to the administrator terminal 30. The control unit 304 of administrator terminal 30 displays a page (analysis perspective result page D2) for displaying the received analysis perspective result information on the administrator terminal 30's display 3081. Figure 21 is an example of the second screen showing the operation of the viewpoint analysis process. The viewpoint analysis results page D2 displays the viewpoint analysis results D211, D221, D231 for viewpoint A and the viewpoint analysis results D212, D222, D232 for viewpoint B for each user D21, D22, D23, etc., in association with each user. This allows for the analysis of survey information collected from users through questionnaires, interviews, etc., from one or more perspectives.

[0140] <Insight Analysis Processing> Insight analysis processing is a process that delves deeper into the analytical perspective by examining one or more perspective analysis results output by perspective analysis processing.

[0141] <Overview of insight analysis processing> The insight analysis process is a series of operations that accepts an insight instruction as input, accepts an analysis perspective to be analyzed, generates a prompt based on the insight instruction and the input analysis perspective, and obtains and presents the insight analysis results output by inputting the prompt to the generation AI50.

[0142] <Details of insight analysis processing> The following details the insight analysis process.

[0143] <Analysis item submission> In step S601, the processing unit 1043 of the server 10 executes a third output acquisition step in which it acquires multiple output contents for each of the multiple users that are output in response to inputting a prompt into the artificial intelligence system. The processing unit 1043 of the server 10 performs a third output presentation step in which it presents to the user with information indicating one or more output contents in a selectable manner. The processing unit 1043 of the server 10 executes a third output selection step in which it receives from the user the selection of information indicating a predetermined output content from the information indicating one or more output content presented in the third output presentation step. The third output acquisition step involves acquiring multiple output contents for multiple users, corresponding to the information indicating the predetermined output contents selected in the third output selection step. Specifically, the administrator operates the input device 306 of the administrator terminal 30 to select one or more checkboxes for the viewpoint analysis results D211, D221, D231, and viewpoint analysis results D212, D222, D232, etc., output by the viewpoint analysis process on the viewpoint analysis results page D2, from the checkboxes D201, D202, etc., which correspond to the viewpoint analysis results that are the target of the insight analysis process. The administrator selects one or more viewpoint analysis results output by the viewpoint analysis process as targets for insight analysis processing by operating the input device 306 of the administrator terminal 30.

[0144] <Insight Instructions Input Acceptance> In step S602, the processing unit 1043 of the server 10 performs a third instruction acquisition step to acquire a third instruction that outputs one or more viewpoints. Specifically, the administrator selects the "Insight Analysis Button" included in the analysis perspective results page D2 by operating the input device 306 of the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays a screen (Insight Analysis screen D3) on the display 3081 of the administrator terminal 30 for further exploring the analysis perspective, spanning one or more perspective analysis results output by the perspective analysis process. Figure 22 shows an example screen illustrating the operation of the insight analysis process. The insight analysis screen D3 includes an insight instruction input field D31. The insight analysis screen D3 also includes insight instruction D311, insight analysis result D312, insight instruction D321, insight analysis result D322, insight instruction D331, insight analysis result D332, and so on. The administrator operates the input device 306 of the administrator terminal 30 to input an instruction (insight instruction) into the insight instruction input field D31 to further explore the viewpoint analysis results selected in step S601, which applies to multiple users. For example, insight instructions might include questions like, "Please list the three best candidates," "Which candidate has the highest technical skills?", or "Which candidate has the best teamwork skills?".

[0145] <Prompt generation> In step S603, the processing unit 1043 of the server 10 executes a third creation step in which it creates a third prompt by including the multiple output contents for multiple users obtained in the third output acquisition step in the third instruction acquisition step. The third creation step involves creating a third prompt by including in the third instruction multiple output contents for multiple users, corresponding to information indicating predetermined output contents. Specifically, the control unit 104 of the server 10 creates prompt E by including one or more viewpoint analysis results obtained in step S601 in the insight instruction statement received in step S602. The viewpoint analysis results include viewpoint analysis results output by viewpoint analysis processing for multiple users. <Prompt E> ${insight directive} ${Perspective Analysis Results}

[0146] <Obtain insight analysis results> In step S604, the control unit 104 of the server 10 inputs the created prompt E by sending it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of prompt E. The output content includes analysis results that delve deeper into the analysis viewpoint, spanning one or more viewpoint analysis results output by the viewpoint analysis process. The control unit 104 of the server 10 stores the project ID of the project to be analyzed in the perspective analysis process, the analysis perspective ID related to the analysis item selected in step S601, the insight instruction received in step S602, and the output content of the artificial intelligence system 50 in the project ID, target perspective ID, insight instruction, and insight analysis result fields of the analysis insight table 1033, respectively.

[0147] The analytical insight information stored in the analytical insight table 1033 is sent to the administrator terminal 30 and displayed on the administrator terminal 30's display 3081 as insight instruction D311, insight analysis result D312, insight instruction D321, insight analysis result D322, insight instruction D331, insight analysis result D332, etc., on the insight analysis screen D3.

[0148] <Basic Computer Hardware Configuration> Figure 23 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 comprises at least a processor 901, main memory 902, auxiliary memory 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0149] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0150] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0151] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0152] The communication IF991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards. The network is composed of various mobile communication systems such as the Internet, LAN, wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks (e.g., Wi-Fi (registered trademark)) that can be connected to the Internet by a predetermined access point, etc. When connecting wirelessly, communication protocols such as Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. are included. When connecting by wire, the network also includes those directly connected by a USB (Universal Serial Bus) cable, etc.

[0153] Note that all or part of each hardware configuration can be distributed and provided to a plurality of computers 90, and the computers 90 can be virtually realized by connecting them to each other via a network. Thus, the computer 90 is a concept that includes not only a single housing and the computer 90 housed in a case, but also a virtualized computer system.

[0154] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of the computer 90 (Figure 23) will be described. The computer includes at least functional units of a control unit, a storage unit, and a communication unit.

[0155] Note that the functional units included in the computer 90 can also be realized by distributing all or part of each functional unit to a plurality of computers 90 interconnected by a network. The computer 90 is a concept that includes not only a single computer 90, but also a virtualized computer system.

[0156] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing according to the programs. The control unit can realize functional units that perform various information processes according to the type of program. Thereby, the computer is realized as an information processing device that performs information processing.

[0157] The functions realized by the components described in this specification may be implemented in circuitry or processing circuitry including a general-purpose processor, a special-purpose processor, an integrated circuit, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), a conventional circuit, and / or a combination thereof, programmed to realize the described functions. The processor includes transistors and other circuits and is regarded as circuitry or processing circuitry. The processor may be a programmed processor that executes a program stored in a memory. In this specification, circuitry, unit, and means are hardware programmed to realize the described functions or hardware that executes them. The hardware may be any hardware disclosed in this specification or any hardware known as being programmed or executing to realize the described functions. When the hardware is a processor regarded as being of the circuitry type, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or the processor.

[0158] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0159] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0160] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0161] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0162] <Note> The details described in each of the above embodiments are noted below.

[0163] (Note 1) A program to be executed by a computer having a processor and a memory unit, wherein the processor performs a first utterance acquisition step (S304) of acquiring first utterance content from a user, and a first creation step (S302) of creating a first prompt by including the user's first utterance content acquired in the first utterance acquisition step in a first instruction for creating an interview question to obtain information from the user from one or more perspectives. This allows for the creation of interview questions that are suitable for gathering in-depth information from one or more perspectives based on the initial utterance obtained from the user.

[0164] (Note 2) The first instruction is the program described in Appendix 1, which is an instruction to create interview questions to obtain information from one or more perspectives regarding the user's interests and concerns about the product or service. This allows for the creation of interview questions that are suitable for gathering in-depth information on one or more aspects of a user's interests and concerns in their consumer behavior.

[0165] (Note 3) The program as described in Appendix 1, wherein the processor performs a first input step (S302) of inputting a first prompt to an artificial intelligence system; a first output step (S302) of obtaining a first output that is output in response to inputting the first prompt to the artificial intelligence system; a second utterance acquisition step (S304) of obtaining a second utterance from a user in response to presenting an interview based on the first output to the user; and a second creation step (S302) of creating a second prompt by including the first utterance, the interview based on the first output, and the second utterance in a second instruction for creating an interview question to obtain information from the user from one or more perspectives. This allows for the creation of further interview questions to delve deeper into the user's utterances, based on the second utterances obtained from the user in response to interview questions designed to gather information from one or more perspectives.

[0166] (Note 4) The program as described in Appendix 1, wherein the processor performs a zero creation step (S302) of creating a zero prompt by including information on one or more perspectives in an instruction to create an interview question; a zero input step (S302) of inputting the zero prompt to an artificial intelligence system; and a zero output step (S302) of obtaining a zero output that is output in response to inputting the zero prompt to the artificial intelligence system, and the first creation step (S302) is a step of creating a first prompt by including the content of a first utterance in a first instruction based on the zero output obtained in the zero output step. This allows you to create interview questions to gather information from one or more perspectives from the user.

[0167] (Note 5) The program described in Appendix 1, wherein the processor performs an Nth utterance acquisition step (S304) in which it acquires the content of the Nth utterance from the user, and an Nth creation step (S302) in which it creates an Nth prompt by including summary information that summarizes at least a portion of the utterances from the first utterance to the N-th (N-1)th utterance, and the Nth utterance, in the Nth instruction for creating an interview question to obtain information from the user from one or more perspectives. This makes it possible to suppress the length of prompts, even in long interviews where there is a large amount of information about the user and the user's utterances. By summarizing parts of the utterances, it becomes possible to create more appropriate interview questions based on the user's key utterances that align with the interview perspective.

[0168] (Note 6) The program described in Appendix 1, wherein the processor performs a form presentation step (S202) in which it presents a question form to the user on one or more perspectives; an answer acquisition step (S203) in which it acquires the answers entered by the user to the question form presented in the form presentation step; and a comparison creation step (S405) in which it creates a comparison prompt by including the answers acquired in the answer acquisition step and at least a portion of the user's utterances in an instruction to compare the answers to the question form with the user's utterances in an interview. This allows for a comparison of the consistency between user information collected through questionnaires and user information collected through interviews. This will allow us to further improve the quality of consumer research results for users.

[0169] (Note 7) The comparison creation step (S405) is a step of creating a comparison prompt by including the response content and at least a part of the user's utterance content in an instruction to determine whether the response to the questionnaire form and the user's utterance content in the interview are consistent, which is the program described in Supplementary Note 6. Thereby, it is possible to compare the consistency between the information of the user collected by the questionnaire form and the information of the user collected by the interview. Thereby, it is possible to further improve the quality of the consumer survey results for the user.

[0170] (Supplementary Note 8) The comparison creation step (S405) is a step of creating a comparison prompt by including the response content and at least a part of the user's utterance content in an instruction to determine whether the user's utterance content in the interview is consistent for each of one or more question perspectives in the questionnaire form, which is the program described in Supplementary Note 7. Thereby, it is possible to compare the consistency between the information of the user collected for each of one or more question perspectives in the questionnaire form and the information of the user collected by the interview. It is possible to more carefully confirm the consistency of the consumer survey information collected from the user.

[0171] (Supplementary Note 9) One or more perspectives in the first instruction are for verifying whether the response content of the user to one or more question perspectives included in the questionnaire form is a fact, and are perspectives different from the one or more question perspectives included in the questionnaire form, which is the program described in Supplementary Note 6. Thereby, regarding the information on one or more question perspectives collected via the questionnaire form, by comparing it with the information collected by the interview, it is possible to determine from a multi-faceted perspective that the information collected via the questionnaire form is correct (does not contain falsehoods).

[0172] (Supplementary Note 10) The program as described in Appendix 1, wherein the processor performs an utterance acquisition step (S304) to acquire utterances from the user in response to presenting an interview to the user, and the utterance acquisition step (S304) is a step to acquire the user's utterances during the first period after presenting the interview to the user. This allows for regular interviews with users at predetermined intervals, enabling the acquisition of their spoken content.

[0173] (Note 11) The program as described in Appendix 10, wherein the processor performs an extension step (S304) in which it receives an input operation from the user to extend the first period, and the speech acquisition step (S304) is a step of acquiring the user's speech content during the first period and the predetermined extension period, excluding the user's speech content during the predetermined extension period. This allows users to extend the response period to consider their answers to interview questions (allowing them to think for longer), thus reducing user stress during interviews. Furthermore, by not capturing the user's utterances while they are thinking for an extended period, the quality of the interview can be improved.

[0174] (Note 12) The program as described in Appendix 11, wherein the processor performs a shooting step (S303) of photographing the user during the interview period using a camera provided on the user terminal, and the shooting step (S303) is a step of photographing the user during the interview period, including the first period and the extended period. This allows us to record and remember the user's behavior during periods of deep thought in the interview. Without needing to capture the user's spoken content during the first period, we can record the user's behavior and use it as reference information for the interview.

[0175] (Note 13) The program described in Appendix 10, wherein the processor receives an input operation from the user to redo the interview, and executes a retry step (S304) in which the speech acquisition step is executed again in response to the input operation. This allows users to re-answer if they were unable to provide an appropriate response, reducing user stress during interviews.

[0176] (Note 14) The speech acquisition step (S304) is a step in the program described in Appendix 10, in which the content of the user's speech is acquired in response to an input operation received from the user. This allows users to answer interview questions based on their own input, reducing user stress during interviews.

[0177] (Note 15) A method to be performed on an information processing apparatus comprising a processor and a memory unit, wherein the processor performs all steps performed in the invention according to any of the appendices 1 to 14. This allows for the creation of interview questions that delve deeper into one or more perspectives of information from the user, based on the initial utterance obtained from the user.

[0178] (Note 16) An information processing apparatus comprising a processor and a memory unit, wherein the processor performs all steps performed in any of the inventions described in Appendix 1 to Appendix 14. This allows for the creation of interview questions that delve deeper into one or more perspectives of information from the user, based on the initial utterance obtained from the user.

[0179] (Note 17) A system comprising means for performing all steps performed in any of the inventions described in Appendix 1 to Appendix 14. This allows for the creation of interview questions that delve deeper into one or more perspectives of information from the user, based on the initial utterance obtained from the user. [Explanation of symbols]

[0180] 1 System, 10 Servers, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminals, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 30 Administrator Terminals, 301 Memory Unit, 304 Control Unit, 306 Input Device, 308 Output Device, 50 Generating AI, 501 Memory Unit, 504 Control Unit, 506 Input Device, 508 Output Device

Claims

1. A program to be executed by a computer having a processor and a memory unit, The aforementioned processor, The first utterance acquisition step obtains the content of the first utterance from the user, A first creation step involves creating a first prompt by including the content of the first utterance of the user obtained in the first utterance acquisition step in a first instruction for creating interview questions to obtain information from the user from one or more perspectives, A program that executes this task.

2. The first instruction is to create interview questions to obtain information from one or more perspectives regarding the user's interests and concerns about the product or service. The program according to claim 1.

3. The aforementioned processor, A first input step involves inputting the first prompt into the artificial intelligence system, A first output step of obtaining a first output that is output in response to inputting the first prompt to the artificial intelligence system, A second utterance acquisition step is performed to obtain the content of a second utterance from the user in response to presenting the user with an interview based on the first output, A second creation step involves creating a second prompt by including the first utterance, the interview based on the first output, and the second utterance in a second instruction for creating interview questions to obtain information from the user from one or more perspectives. Execute The program according to claim 1.

4. The aforementioned processor, The instructions for creating interview questions include a first-step creation step of creating a first-step prompt by including information on one or more perspectives, The first input step involves inputting the aforementioned first prompt into the artificial intelligence system, A first output step of obtaining the first output that is output in response to inputting the first prompt to the artificial intelligence system, Execute, The first creation step is a step of creating the first prompt by including the first utterance content in the first instruction based on the first output obtained in the first output step. The program according to claim 1.

5. The aforementioned processor, The Nth utterance acquisition step obtains the content of the Nth utterance from the user, The Nth creation step creates an Nth prompt by including summary information that summarizes at least a portion of the utterances from the first utterance to the (N-1)th utterance, and the Nth utterance, in the Nth instruction for creating an interview question to obtain information from the user from one or more perspectives. Execute The program according to claim 1.

6. The aforementioned processor, A form presentation step that presents the user with a question form regarding one or more perspectives, The response acquisition step involves acquiring the content of the answers entered by the user in the question form presented in the form presentation step, A comparison creation step creates a comparison prompt by including the response content obtained in the response acquisition step and at least a portion of the user's utterance in an instruction to compare the response content to the question form with the user's utterance in the interview. Execute The program according to claim 1.

7. The comparison creation step is a step of creating the comparison prompt by including the answer content and at least a portion of the user's utterance in an instruction to determine whether the answer to the question form and the user's utterance in the interview are consistent. The program according to claim 6.

8. The comparison creation step is a step of creating the comparison prompt by including the answer content and at least a portion of the user's utterances in the instruction to determine whether the user's utterances in the interview are consistent for each of the one or more question perspectives in the question form. The program according to claim 7.

9. The one or more viewpoints in the first instruction are for verifying whether the user's answers to the one or more question viewpoints included in the question form are factual or not, and are viewpoints different from the one or more question viewpoints included in the question form. The program according to claim 6.

10. The aforementioned processor, A speech acquisition step in which the content of the utterance is obtained from the user in response to presenting the interview to the user, Execute, The utterance acquisition step is a step of acquiring the content of the user's utterances during the first period, after presenting the interview to the user. The program according to claim 1.

11. The aforementioned processor, An extension step in which the user provides input to extend the first period, Execute, The utterance acquisition step is a step of acquiring the user's utterances during the first period and the predetermined extension period, excluding the user's utterances during the predetermined extension period. The program according to claim 10.

12. The aforementioned processor, The user's device has a camera that is used to take pictures of the user during the interview, and Execute, The aforementioned shooting step is a step of photographing the user during the interview period, which includes the first period and the extended period. The program according to claim 11.

13. The aforementioned processor, A retry step which receives an input operation from the user to redo the interview and executes the speech acquisition step again in response to the input operation, Execute The program according to claim 10.

14. The utterance acquisition step is a step of acquiring the content of the user's utterance in response to an input operation received from the user. The program according to claim 10.

15. A method to be performed on an information processing apparatus comprising a processor and a storage unit, wherein the processor performs all steps performed in the invention according to any one of claims 1 to 14.

16. An information processing apparatus comprising a processor and a storage unit, wherein the processor performs all steps performed in the invention according to any one of claims 1 to 14.

17. A system comprising means for performing all steps performed in the invention according to any one of claims 1 to 14.

Images