Program, method, information processing device, and system

Abstract

There is an issue in that the survey information collected from users cannot be analyzed. [Solution] A program to be executed on a computer having a processor and a memory unit, the program executing a survey acquisition step in which the processor acquires survey information regarding a user, an instruction acquisition step in which the processor acquires a first instruction to output one or more perspectives regarding the survey information, and a creation step in which the processor creates a prompt by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step.

Description

[Technical field]

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

[0002] Techniques for analyzing the interests and concerns of a user in terms of consumption behavior are known. Patent Document 1 discloses a method for accepting questionnaires. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2003-308415 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is an issue in that the survey information collected from users cannot be analyzed. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to analyze survey information collected from users. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, the program executing a survey acquisition step in which the processor acquires survey information regarding a user, an instruction acquisition step in which a first instruction is acquired to output one or more perspectives regarding the survey information, and a creation step in which a prompt is created by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step. Effect of the Invention

[0006] According to the present disclosure, survey information collected from users can be analyzed. [Brief description of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Diagram 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Diagram 3] 2 is a block diagram showing the functional configuration of a user terminal 20. FIG. [Figure 4] 2 is a block diagram showing a functional configuration of an administrator terminal 30. FIG. [Diagram 5] FIG. 13 is a diagram showing the data structure of a user table 1012. [Figure 6] FIG. 13 is a diagram showing the data structure of a project table 1013. [Figure 7] FIG. 13 is a diagram showing the data structure of a question table 1014. [Figure 8] FIG. 13 is a diagram showing the data structure of a response table 1015. [Figure 9] FIG. 13 is a diagram showing the data structure of an interview table 1016. [Figure 10] 13 is a diagram showing the data structure of an instruction statement storage unit 1021. FIG. [Figure 11] FIG. 13 is a diagram showing the data structure of an analysis viewpoint table 1031. [Figure 12] 13 is a diagram showing the data structure of an analysis viewpoint result table 1032. FIG. [Figure 13] FIG. 13 is a diagram showing the data structure of an analysis insight table 1033. [Figure 14] 13 is a flowchart showing the operation of a plan creating process. [Figure 15] 13 is a flowchart showing the operation of a questionnaire process. [Figure 16] 13 is a flowchart showing the operation of an interview process. [Figure 17] 13 is a flowchart showing an operation of a consistency checking process. [Figure 18] 13 is a flowchart showing the operation of a viewpoint analysis process. [Figure 19]13 is a flowchart showing the operation of an insight analysis process. [Figure 20] 13 is a first screen example showing the operation of the viewpoint analysis process. [Figure 21] 13 is a second screen example showing the operation of the viewpoint analysis process. [Figure 22] 13 is a screen example showing the operation of the insight analysis process. [Diagram 23] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In all the drawings explaining the embodiment, the same reference numerals are given to common components, and repeated explanations are omitted. Note that the following embodiment does not unduly limit the contents of the present disclosure described in the claims. In addition, not all of the components shown in the embodiment are essential components of the present disclosure. In addition, each figure is a schematic diagram and is not necessarily illustrated strictly.

[0009] <System 1 Configuration> 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 a user's purchasing interests through questionnaires, interviews, etc. Specifically, the information processing system in the present disclosure relates to an information processing service that uses an artificial intelligence system to realize consumer questionnaires, consumer interviews, etc. that collect consumer survey information such as interests and concerns regarding the consumption behavior of a user who is the subject of the survey. In this disclosure, information such as a user's purchasing interests collected through questionnaires, interviews, etc. is referred to as survey information (consumer survey information). The system 1 includes an information processing device including a server 10, a user terminal 20, an administrator terminal 30, and a generating AI 50, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG. FIG. 4 is a block diagram showing the functional configuration of the administrator terminal 30. As shown in FIG.

[0010] Each information processing device is composed of a computer equipped with a calculation device and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, the administrator terminal 30, and the generation AI 50, the description that overlaps with the basic hardware configuration and the basic functional configuration of the computer described later will be omitted.

[0011] <Server 10 Configuration> The server 10 is an information processing system that collects survey information of users. Specifically, the server 10 is an information processing device that provides an information processing service that collects survey information such as users' 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 the server 10> The memory unit 101 of the server 10 includes an application program 1011, a user table 1012, a plan table 1013, a question table 1014, an answer table 1015, an interview table 1016, a directive memory unit 1021, an analysis viewpoint table 1031, an analysis viewpoint result table 1032, and an analysis insight table 1033.

[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.

[0014] The user table 1012 is a table that stores and manages information on member users (hereinafter, users) who use the service. When a user registers to use the service, the user's information is stored in a new record in the user table 1012. This allows the user to use the service according to the present disclosure. The user information may be registered in the user table 1012 by an input operation by an administrator. In addition, in a survey process, an interview process, etc. described below, when a user operates the input device 206 of the user terminal 20 to open a URL related to a survey processing page, an interview page, etc., the user's information may be registered by storing it in the user table 1012. The user table 1012 is a table having columns of user ID, user name, and user data, with the user ID as the primary key. FIG. 5 is a diagram showing the data structure of the user table 1012. As shown in FIG.

[0015] The user ID is an item for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name. The user data includes information specific to each individual user and attribute information relating to the characteristics and background of the user. The user's unique information includes information unique to the user, such as the user's date of birth (age), sex, and the like. The user's 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] The project table 1013 is a table for storing and managing information (project information) relating to projects of consumer questionnaires and consumer interviews. The project table 1013 is a table having the project ID as a primary key and columns of the project ID, project name, target person, project content, viewpoint, and prompt A. FIG. 6 is a diagram showing the data structure of the project table 1013. As shown in FIG.

[0017] The project ID is an item for storing project identification information for identifying a project. The project identification information is an item for which a unique value is set for each piece of project information. The project name is an item for storing the name of the project. Any character string can be set as the project name. The subject is an item for storing the user ID of the user who is the subject of the survey. The subject stores one or more user IDs. The plan content is an item for storing the content of the plan. The viewpoint is an item for storing a research viewpoint of a consumer questionnaire or a consumer interview. Specifically, a viewpoint related to the interests and concerns of a user who wishes to research a product or service is stored. The viewpoint may include image information related to the viewpoint in addition to a sentence (text information) describing the viewpoint. It may also include character string information such as a URL indicating an image. For example, the viewpoint stores information such as character strings and images as follows. Ask the manufacturer of the bike they use. Where do you use your bike? -Dig deeper into the scenes you use every day. Prompt A is an item that stores a prompt (instruction sentence) to have the AI ​​conduct a consumer interview.

[0018] The question table 1014 is a table for storing and managing information relating to questions (question information). The question table 1014 is a table having a question ID as a primary key, and columns of a question ID, a project ID, and a question content. FIG. 7 is a diagram showing the data structure of the question table 1014. As shown in FIG.

[0019] The question ID is an item for storing question identification information for identifying a question. The question identification information is an item for which a unique value is set for each piece of question information. The project ID is an item for storing project identification information for identifying a project. The question content is an item for storing the question content.

[0020] The answer table 1015 is a table for storing and managing information related to answers (answer information). The answer table 1015 is a table having an answer ID as a primary key, and columns of an answer ID, a question ID, a user ID, an answer content, an answer date and time, and a judgment result. FIG. 8 is a diagram showing the data structure of the answer table 1015. As shown in FIG.

[0021] The answer ID is an item for storing answer identification information for identifying an answer. The answer identification information is an item for which a unique value is set for each piece of answer information. The question ID is an item for storing question identification information for identifying a question. The user ID is an item for storing user identification information for identifying a user. The answer content is an item for storing the user's answer to the question content identified based on the question ID. The answer date and time is an item for storing the storage date and time when a new record is stored or updated in the answer table. The judgment result is an item that stores the judgment result of whether the answer content is appropriate or not. Specifically, the judgment result is an item that stores the judgment result (True, False) of whether the answer content by the user is a lie or not. The judgment result does not necessarily have to be a two-level value of "appropriate" or "inappropriate", and may be configured to store a number indicating the degree of appropriateness or a character string indicating a rank.

[0022] The interview table 1016 is a table for storing and managing information relating to interviews (interview information). The interview table 1016 is a table having an interview ID as a primary key, and columns of an interview ID, a project ID, a user ID, an index, an interview prompt, an interview question, a speech content, and additional data. FIG. 9 is a diagram showing the data structure of the interview table 1016.

[0023] The interview ID is an item for storing interview identification information for identifying an interview. The interview identification information is an item for which a unique value is set for each interview information. The project ID is an item for storing project identification information for identifying a project. The user ID is an item for storing user identification information for identifying a user. The index is an item that stores the order of the interviews. The interview prompt is an item for storing a prompt (instruction sentence) for generating an interview question to be output to the user. The interview question is an item for storing an interview question to be output to the user. The interview question may include not only text information but also image information to be presented to the user. It may also include information such as a URL indicating an image. The speech content is an item for storing the speech content received from the user in response to the interview questions. The speech content includes voice data, recorded data, image data, and text data obtained by transcribing the voice data using text recognition technology. The speech content stores one or more speech contents received from the user in response to one or more interview question presentations executed in the interview process. The additional data includes voice data, recorded data, image data, etc., that store the manner in which the user responds to the interview. The additional data includes information such as the content of input operations (such as pausing) performed by the user during the interview, and the date and time.

[0024] The instruction statement storage unit 1021 is an item for storing instruction statements. Instruction statements are used when creating a prompt to be input to the generation AI. Also, the instruction statement may be input directly to the generation AI as a prompt. The instruction statement storage unit 1021 is a table having columns of instruction statement A, instruction statement B, instruction statement C1, instruction statement C2, and instruction statement D. FIG. 10 is a diagram showing the data structure of the instruction statement storage unit 1021. As shown in FIG.

[0025] Instruction A is a instruction used to generate a prompt for conducting a consumer interview. Instruction B is an instruction used to generate a prompt for checking the consistency of the user's answers and the contents of the utterances in the interview. The instruction C1 is an instruction used to generate a prompt for outputting a viewpoint from a question. Instruction C2 is an instruction used to generate a prompt for outputting a question from a viewpoint. Instruction D is an instruction to output one or more viewpoints contained in the questionnaire or interview.

[0026] The analysis viewpoint table 1031 is a table for storing and managing information related to the analysis viewpoint (analysis viewpoint information). The analysis viewpoint table 1031 is a table having an analysis viewpoint ID as a primary key and columns of an analysis viewpoint ID, a viewpoint name, a viewpoint directive, and an analysis item. FIG. 11 is a diagram showing the data structure of the analysis viewpoint table 1031. As shown in FIG.

[0027] The analysis viewpoint ID is an item for storing analysis viewpoint identification information for identifying an analysis viewpoint. The analysis viewpoint identification information is an item in which a unique value is set for each analysis viewpoint information. The viewpoint name is an item for storing the name of the viewpoint. Any character string can be set as the viewpoint name. The viewpoint instruction sentence is an item for storing an instruction sentence used when creating a prompt for analyzing consumer survey information such as questionnaires and interviews in accordance with an analytical viewpoint. The analysis item is an item that stores information indicating a data source (analysis item) to be analyzed from consumer survey information such as a plurality of questionnaires and interviews.

[0028] The analysis viewpoint result table 1032 is a table for storing and managing information related to the analysis viewpoint result (analysis viewpoint result information). The analysis viewpoint result table 1032 is a table having columns of analysis viewpoint ID, user ID, viewpoint analysis prompt, and viewpoint analysis result. FIG. 12 is a diagram showing the data structure of the analysis viewpoint result table 1032. As shown in FIG.

[0029] The analysis viewpoint ID is an item for storing analysis viewpoint identification information for identifying an analysis viewpoint. The user ID is an item for storing user identification information for identifying a user. The viewpoint analysis prompt is an item for storing a prompt that outputs one or more viewpoints contained in consumer survey information such as a questionnaire or interview of a specific user. The viewpoint analysis result is an item for storing output contents that are output in response to inputting a viewpoint analysis prompt to the generation AI 50.

[0030] The analytical insight table 1033 is a table for storing and managing information (analytical insight information) relating to information (analytical insight, insight) that is obtained by digging into an analytical perspective based on information across a plurality of analytical perspectives. The analytical insight table 1033 is a table having an analytical insight ID as a primary key, and columns of an analytical insight ID, a plan ID, a target viewpoint ID, an insight directive, and an insight analysis result. FIG. 13 is a diagram showing the data structure of the analytical insight table 1033.

[0031] The analytical insight ID is an item for storing analytical insight identification information for identifying an analytical insight. The analytical insight identification information is an item in which a unique value is set for each analytical insight. The project ID is an item for storing project identification information for identifying a project. The target viewpoint ID is an item for storing one or more analysis viewpoint IDs indicating the analysis viewpoint of the target to be dug up. The insight instruction statement is an item for storing an instruction statement for outputting information (analysis insight) that digs deeper into an analysis perspective across multiple analysis perspectives. The insight analysis result is an item that stores the output contents that are output in response to inputting insight instructions, consumer survey information such as questionnaires and interviews, viewpoint analysis results, etc. to the generation AI 50.

[0032] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0033] The user registration control unit 1041 performs processing to store, in the user table 1012, information on users who wish to use the service according to the present disclosure. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a specific input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers user information in the user table 1012, the service provider may carry out a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or an arbitrary character string or number may be automatically set by the user registration control unit 1041.

[0034] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. 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] The user ID 2011 is an account ID of the user. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user who is using the user terminal 20.

[0037] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript™ 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 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[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 an administrator who manages a service. The administrator terminal 30 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary PC (Personal Computer), or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type terminal. 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 includes a user ID 3011 and an application program 3012 .

[0043] The user ID 3011 is the user's account ID. The user transmits the user ID 3011 from the administrator terminal 30 to the server 10. The server 10 identifies the user based on the user ID 3011 and provides the user with the service according to the present disclosure. The user ID 3011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user using the administrator terminal 30.

[0044] The application program 3012 may be prestored in the storage unit 301, or may be downloaded from a web server operated by a service provider via a communication IF. The application program 3012 includes an interpreter-type 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 includes an input control unit 3041 and an output control unit 3042. The control unit 304 executes an application program 3012 stored in the storage unit 301, thereby realizing each functional unit.

[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 position information sensor 3063 , a motion sensor 3064 , and a keyboard 3065 .

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

[0048] <Configuration of generated 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 perform natural language generation (NLG) tasks effectively. The generation AI 50 is used in many NLP tasks, such as generating responses to specific questions, automatically generating sentences, summarizing text, translation, and sentiment analysis. It can also be used for a variety of purposes, such as education, entertainment, customer service, and product development. The generation AI 50 includes the following types. In this disclosure, a large-scale language model that mainly outputs text information as output information will be described as a type of generation AI 50. OpenAI ChatGPT ·Anthropic Claude Google Gemini Stable Diffusion Midjourney The generation AI 50 may be realized as a part of the functions of the server 10.

[0049] <System 1 Operation> Each process of the system 1 will be described below. FIG. 14 is a flowchart showing the operation of the plan creating process. FIG. 15 is a flowchart showing the operation of the questionnaire process. FIG. 16 is a flowchart showing the operation of the interview process. FIG. 17 is a flowchart showing the operation of the consistency checking process. FIG. 18 is a flowchart showing the operation of the viewpoint analysis process. FIG. 19 is a flowchart showing the operation of the insight analysis process. FIG. 20 is a first screen example showing the operation of the viewpoint analysis process. FIG. 21 is a second example of a screen showing the operation of the viewpoint analysis process. FIG. 22 is an example of a screen showing the operation of the insight analysis process.

[0050] <Plan creation process> The plan creation process is a process for creating a plan (project) for a consumer questionnaire and consumer interview.

[0051] <Outline of the planning process> The plan creation process is a series of processes that open a plan creation page, input plan information, input questions, and execute an input completion process based on the input information.

[0052] <Details of the plan creation process> The plan creation process will be described in detail below.

[0053] <Open the plan creation page> In step S101, an administrator associated with an employee of an information processing service or the like according to the present disclosure operates the input device 306 of the administrator terminal 30 to input the URL of a page for executing a plan creation process (plan creation processing page) into a web browser or the like, and open the plan creation processing page. The control unit 304 of the administrator terminal 30 transmits a request to the server 10 to open the plan creation processing page. The control unit 104 of the server 10 generates a plan creation processing page based on the received request, and transmits 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 plan creation processing page includes input fields for inputting the plan name, target person, plan content, and viewpoint. Each input item corresponds to each column of the plan table 1013. The plan creation processing page includes input fields for one or more questions.

[0054] <Enter project information> In step S102, the administrator operates the input device 306 of the administrator terminal 30 to input values ​​into each of the input items, namely, the project name, the target person, the project content, and the viewpoint.

[0055] <Enter your question> In step S103, the administrator operates the input device 306 of the administrator terminal 30 to input an input value in the input field for the question content.

[0056] <Input of project information (first embodiment)> The input value of the viewpoint may be configured to be input 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 the instruction C1. The control unit 104 of the server 10 inserts the input value of the question content into the ${question content} portion of the instruction C1 below. <Instruction C1> Below are some questions for consumers. Please output your consumer research perspective based on the content of these questions. #QuestionSurvey ${Question}

[0057] The control unit 104 of the 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 input of the prompt. The output content includes information regarding the viewpoint. The control unit 104 of the server 10 receives the output content. The control unit 104 of the server 10 transmits the received output content to the administrator terminal 30. The control unit 304 of the administrator terminal 30 inputs the received output content into an input field for the viewpoint.

[0058] <Input of project information (second embodiment)> The input value of the question content may be configured to be input based on the input value of the viewpoint. Specifically, the control unit 104 of the server 10 creates a prompt by including the input value of the viewpoint in the instruction C2. The control unit 104 of the server 10 inserts the input value of the viewpoint in the ${viewpoint} portion of the following instruction C2. <Instruction C2> Below are the perspectives you would like to investigate in your consumer survey. Based on these perspectives, please output the questions you would like to ask consumers in bullet points. #Consumer research perspective ${perspective}

[0059] The control unit 104 of the 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 input of the prompt. The output content includes information regarding the question content. The control unit 104 of the server 10 receives the output content. The control unit 104 of the server 10 transmits the received output content to the administrator terminal 30. The control unit 304 of the administrator terminal 30 inputs the received output content into the input field for the question content.

[0060] The control unit 304 of the manager terminal 30 transmits to the server 10 the input values ​​entered in the input fields, such as the project name, the target person, the project content, the viewpoint, and the question content.

[0061] <Input completion process> In step S104, the control unit 104 of the server 10 stores the received project name, target person, project content, and viewpoint in the project name, target person, project content, and viewpoint items of a new record in the project table 1013. The control unit 104 of the server 10 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 items of a new record in the question table 1014, respectively. The control unit 104 of the server 10 stores a prompt (instruction statement) for causing the AI ​​to conduct a consumer interview in the prompt A item. The control unit 104 of the server 10 creates prompt A by inserting the value of the viewpoint item into the ${viewpoint} portion of instruction statement A stored in the memory unit 101 of the server 10. Note that prompt A may also be created by inserting the value of the viewpoint item into the ${viewpoint} portion of instruction statement A during the interview process described below. The control unit 104 of the server 10 stores the created prompt A in the prompt A item of the plan table 1013.

[0062] <Instructive text A> Please create interview texts to gather information from users about the following consumer research aspects. Please write the interview texts in a colloquial style. #Consumer research perspective ${perspective}

[0063] <Survey processing> The questionnaire process is a process of asking the user one or more questions and receiving one or more answers to each of the one or more questions.

[0064] <Outline of survey processing> The questionnaire process is a series of processes in which a user opens a website related to an answer page on user terminal 20, questions are presented to the user, and answers to the questions are received from the user.

[0065] <Survey processing details> The questionnaire process will be described in detail below. In the present disclosure, a questionnaire process for a specific user is disclosed as an example, and the questionnaire process is executed for each plan created in the plan creation process for users associated with one or more user IDs included in the target person item for that plan. For example, after the input completion process (step S104) of the plan creation process, a message such as an email including a URL for a questionnaire processing page may be sent to users associated with one or more user IDs included in the target person for that plan. This may allow the user to answer the questionnaire by selecting a URL included in the message such as an email.

[0066] <Open answer page> In step S201, the user operates the input device 206 of the user terminal 20 to input the URL of a page for executing a survey process (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 transmits a request to open the survey processing page to the server 10. The URL may include identification information such as a character string for specifying the project ID. The control unit 104 of the server 10 identifies a specific project ID based on a character string included in the URL, etc. The control unit 104 of the server 10 searches the project ID item in the question table 1014 based on the project ID and acquires the question content. The control unit 104 of the server 10 generates a survey processing page including a question form that can accept input of an answer to the question content from the user based on the acquired question content. The control unit 104 of the server 10 generates the survey processing page based on the received request and transmits it to the user terminal 20.

[0067] <Question form presentation> In step S202, the control unit 204 of the user terminal 20 executes a form presenting step of presenting a question form regarding one or more viewpoints to the user. 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] <Reply> In step S203, the processing unit 1043 of the server 10 executes an answer acquisition step of acquiring the answer content input by the user to the question form presented in the form presentation step. Specifically, the user operates the input device 206 of the user terminal 20 to input values ​​in input fields for answer contents to a question form included in the survey processing page. One or more answer contents are associated with the question IDs of the question contents included in the question form. For example, the user inputs answer contents A, B, and C to the question contents related to the question IDs of question contents A, B, and C. The control unit 204 of the user terminal 20 transmits 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 content in the user ID, question ID, and answer content items of the answer table 1015, respectively. As a result, the answer contents answered by the user are stored in the answer table 1015 in association with one or more question contents.

[0069] <Interview Processing> The interview process is a process of conducting one or more interviews with a user and accepting one or more utterances in response to the one or more interviews.

[0070] <Outline of interview process> The interview process is a series of processes in which a user opens a website related to an interview page for conducting a consumer interview on the user terminal 20, creates interview questions for the user, presents the interview questions to the user, and accepts utterances from the user. Presentation of interview questions to the user and acceptance of utterances from the user are repeated until one or all of the interviews are completed.

[0071] <Interview Processing Details> The details of the interview process are described below. In this disclosure, an interview process for a specific user is disclosed as an example, but the interview process is executed for each plan created in the plan creation process for users associated with one or more user IDs included in the target person item for that plan. For example, after accepting responses to the questionnaire process (step S203), a message such as an email including a URL for an interview processing page may be sent to users associated with one or more user IDs included in the target person for that plan. This allows the user to respond (speak) to the interview by selecting a URL included in the message such as an email.

[0072] <Open interview page> In step S301, the user operates the input device 206 of the user terminal 20 to input the URL of a page for performing interview processing (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 transmits a request to open the interview processing page to the server 10. The URL may include identification information such as a character string for specifying the project ID. The control unit 104 of the server 10 identifies a specific project ID based on a character string included in the URL, etc. The control unit 104 of the server 10 searches the project ID item of the project table 1013 based on the project ID, and acquires prompt A.

[0073] <Creating interview questions>

[0074] <Creating interview questions (step 0)> In step S302, the processing unit 1043 of the server 10 executes a 0th creation step of creating a 0th prompt by including information on one or more viewpoints in an instruction for creating an interview question. Specifically, the control unit 104 of the server 10 searches the plan ID item in the plan table 1013 based on the acquired plan ID and acquires the perspective item. The control unit 104 of the server 10 creates prompt A (0th prompt) by inserting the value of the perspective item into the ${perspective} item of the instruction statement A. The control unit 104 of the server 10 stores the created prompt A (0th prompt) in the prompt A item of the record identified based on the plan ID in the plan table 1013. In addition, in the present disclosure, an example in which the prompt is created in the input completion process in step S104 of the plan creation process has also been disclosed. Prompt A may be executed in the plan creation process or in the interview process.

[0075] The processing unit 1043 of the server 10 executes a 0th input step of inputting the 0th prompt to the artificial intelligence system. The processing unit 1043 of the server 10 executes a 0th output step of obtaining a 0th output that is output in response to inputting the 0th prompt to the artificial intelligence system. Specifically, the control unit 104 of the server 10 inputs the created prompt A by transmitting 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 character string related to the consumer interview (the 0th interview question). When the viewpoint includes image information, character string information such as a URL indicating an image, the processing unit 1043 of the server 10 outputs the 0th interview question including the image information, character string information such as a URL indicating an image, etc. The same applies to the first interview question and the second interview question. Furthermore, the control unit 204 of the user terminal 20 may display and present image information specified based on the image information, character string information such as a URL, etc., in the interview question on the display 2081 of the user terminal 20 when presenting the interview question (step S303).

[0076] <Creating interview questions (first step)> In step S302, the processing unit 1043 of the server 10 executes a first creation step of creating a first prompt by including the first utterance content of the user acquired in the first utterance acquisition step in a first instruction for creating an interview question for obtaining information from one or more perspectives from the user. The first creation step executes a step of creating a first prompt by including the first utterance content in a first instruction based on the 0th output acquired in the 0th output step. Specifically, the control unit 104 of the server 10 creates the first prompt by inputting the value of prompt A into ${prompt A} of the first instruction sentence, and the value of the first utterance content acquired in the utterance acquisition of step S304 (first utterance acquisition step) into ${first utterance content}. Note that, for example, a first prompt may be created in which the role value is prompt A for the assistant prompt, and the role value is prompt including the first utterance content for the user prompt. <1st directive> Interview:${Prompt A} Utterance content: ${First utterance content}

[0077] The first instructions are instructions to create interview questions to obtain information from one or more perspectives regarding the user's product or service interests and concerns, and the one or more perspectives in the first instructions are for verifying whether the user's answers to the one or more question perspectives included in the question form are factual or not, and are perspectives different from the one or more question perspectives included in the question form.In this way, by comparing the information regarding the one or more question perspectives collected via the question form with information collected by interview, it can be determined from multiple perspectives that the information collected via the question form is correct (does not contain any falsehoods).

[0078] The processing unit 1043 of the server 10 executes a first input step of inputting a first prompt to the artificial intelligence system. The processing unit 1043 of the server 10 executes a first output step of 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 transmitting 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 character string (first interview question) related to a consumer interview for digging deeper into the user's interests and concerns about one or more perspectives, taking into consideration the first utterance content by the user accepted in the utterance acquisition (first utterance acquisition step).

[0079] <Creating interview questions (second creation step)> In step S302, the processing unit 1043 of the server 10 executes a second creation step of creating a second prompt by including the first utterance content, an interview based on the first output, and the second utterance content in a second instruction for creating an interview question for obtaining information from one or more perspectives from the user. Specifically, the control unit 104 of the server 10 creates the second prompt by inputting the value of the first prompt into the ${first prompt} part of the second instruction sentence, and the value of the second utterance content acquired in the utterance acquisition in step S304 (second utterance acquisition step) into the ${second utterance content} part. <Second directive> ${first prompt} Utterance content: ${Second utterance content}

[0080] Specifically, the second prompt is created based on prompt A, the first utterance content, the first interview question, and the second utterance content as follows: Note that, for example, a second prompt may be created that includes prompt A in a prompt with a role value of assistant, the first utterance content in a prompt with a role value of user, the first interview question in a prompt with a role value of assistant, and the second utterance content in a prompt with a role value of user. <2nd prompt> Interview:${Prompt A} Utterance content: ${First utterance content} Interview:${First Interview Question} Utterance content: ${Second utterance content}

[0081] The processing unit 1043 of the server 10 executes a second input step of inputting a second prompt to the artificial intelligence system. The processing unit 1043 of the server 10 executes a second output step of 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 transmitting 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 character string (second interview question) related to a consumer interview for further digging deeper into the user's interests and concerns about one or more perspectives, taking into consideration the first utterance content and the second utterance content by the user accepted in the utterance acquisition (first utterance acquisition step, second utterance acquisition step).

[0082] <Creating interview questions (Nth creation step)> In step S302, the processing unit 1043 of the server 10 executes an Nth creation step of creating an Nth prompt by including summary information summarizing at least a portion of the utterance contents from the 1st utterance content to the N-1st utterance content and the Nth utterance content in the Nth instruction for creating an interview question to obtain information from one or more perspectives from the user. Specifically, the control unit 104 of the server 10 creates the Nth prompt by inputting the value of the N-1st prompt into the ${N-1st prompt} portion of the Nth instruction sentence, and the value of the Nth utterance content acquired in the utterance acquisition of step S304 (Nth utterance acquisition step) into the ${Nth utterance content} portion. <Nth directive> ${prompt N-1} Utterance content: ${Utterance content N}

[0083] Specifically, the Nth prompt is created based on prompt A, the first utterance content, the first interview question, the second utterance content, ... the N-1th interview question, and the Nth utterance content as follows: Note that, for example, it is possible to create an interview question with a role value of assistant including prompt A, and an Nth prompt with a role value of user including utterance content. <Nth prompt> Interview:${Prompt A} Utterance content: ${First utterance content} Interview:${First Interview Question} Utterance content: ${Second utterance content} ... Utterance content: ${Utterance content N-1} Interview:${N-1 Interview Question} Utterance content: ${Utterance content N}

[0084] The processing unit 1043 of the server 10 executes an Nth input step of inputting the Nth prompt to the artificial intelligence system. The processing unit 1043 of the server 10 executes an Nth output step of obtaining an Nth output to be 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 transmitting 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 character string (Nth interview question) related to a consumer interview for further digging deeper into the user's interests and concerns about one or more perspectives, taking into consideration the first utterance content, the second utterance content, through the 1Nth utterance content by the user received in the utterance acquisition (first utterance acquisition step, second utterance acquisition step, through the Nth utterance acquisition step).

[0085] The control unit 104 of the server 10 may replace the information included in the Nth prompt with information summarizing at least a part of the utterance contents or interview questions included in the 1st utterance content to the N-1th utterance content. Specifically, the control unit 104 of the server 10 creates a summary creation prompt by inserting at least a portion of the utterance content or interview question contained in the first utterance content to the N-1st utterance content into the ${consumer interview content} portion of the summary creation instruction sentence shown below.

[0086] <Summary Instructions> Please provide a brief summary of the consumer interviews included below in approximately 500 words. #Consumer Interview ${Contents of consumer interviews}

[0087] <Summary prompt> Please provide a brief summary of the consumer interviews included below in approximately 500 words. #Consumer Interview Utterance content: ${First utterance content} Interview:${First Interview Question} Utterance content: ${Second utterance content} ... Utterance content: ${Utterance content N-1}

[0088] The control unit 104 of the server 10 inputs the created summarization prompt by transmitting it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output content in response to the input of the summarization prompt. The output content includes a character string (summary character string) that summarizes at least a part of the utterance contents or interview questions included in the 1st utterance content to the N-1th utterance content.

[0089] The control unit 104 of the server 10 creates the Nth prompt (variant example) by replacing at least a portion of the utterance content or interview question contained in the 1st utterance content to the N-1th utterance content of the Nth prompt with a summary string.

[0090] <Nth prompt (variation)> Interview:${Prompt A} ${summary string} Interview:${N-1 Interview Question} Utterance content: ${Utterance content N}

[0091] This makes it possible to prevent the prompts from becoming too long even in the case of a long interview, when the interview with the user and the user's utterances are numerous. By summarizing a part of the utterances, more suitable interview questions can be created based on the important utterances by the user that are in line with the interview viewpoint.

[0092] <Interview question presentation (0th presentation step)> In step S303, the control unit 104 of the server 10 generates an interview processing page capable of accepting input of a speech (speech content) from the user in response to the 0th interview question created in the interview question creation (0th creation step). The control unit 104 of the server 10 generates the interview processing page and transmits it to the user terminal 20. The control unit 104 of the server 10 transmits the 0th interview question created in the interview question creation (0th creation step) to the user terminal 20. Note that the control unit 104 of the server 10 may convert the 0th interview question into voice and transmit it to the user terminal 20. The control unit 204 of the user terminal 20 outputs audio based on the received interview question to the user via the speaker 2082 of the user terminal 20. The user can receive audio presentation of the interview question. In this disclosure, an audio interview is disclosed as an example, but the information may be presented in a visual manner such as a character string, an image, or a video.

[0093] <Presenting interview questions (first presentation step)> The control unit 104 of the server 10 presents the first interview question created in the interview question creation (first creation step) to the user. The presentation of the interview question is similar to the interview question presentation (0th presentation step) except that the interview question is the first interview question instead of the 0th interview question, and therefore a description thereof will be omitted. In addition, the interview question presentation (second presentation step) and the interview question presentation (Nth presentation step) are similar to the interview question presentation (zeroth presentation step) except that the interview questions are not the zeroth interview questions but the second interview questions and the Nth interview questions, respectively, and therefore will not be explained here.

[0094] In step S303, the processing unit 1043 of the server 10 executes a photographing step of photographing the user during the interview period with a camera provided in the user terminal. Specifically, the control unit 204 of the user terminal 20 photographs the user by controlling the camera 2061 of the user terminal 20 in response to the presentation of an interview question. The control unit 204 of the user terminal 20 may capture the voice of the user by controlling the microphone 2062. In the present disclosure, capturing an image also includes capturing the voice of the user.

[0095] In step S303, a photographing step is performed to photograph the user during an interview period including the first period and an extension period. Specifically, the control unit 204 of the user terminal 20 captures an image of the user from the presentation of the first interview question (the 0th interview question) to the completion of the interview. Specifically, even if the interview is interrupted (extended) as described below, the control unit 204 of the user terminal 20 may capture an image of the user's state regardless of the interruption period (extension period).

[0096] This allows the user's behavior during long periods of thought during the interview to be captured and stored. The user's behavior can be stored without acquiring the contents of the user's speech during the first period, and can be stored as reference information for the interview.

[0097] In the present disclosure, an example of the interview process in which the user executes the first interview to the Nth interview at once has been disclosed as an example, but the present invention is not limited to this. For example, the user may close the interview page in the middle of the interview to end the interview. In this case, when the user opens the interview page again, the interview (the first interview, the second interview, the Nth interview) may be resumed from the middle. For example, the control unit 104 of the server 10 or the control unit 204 of the user terminal 20 may resume the interview by referring to the interview prompt, interview question, spoken content, and other flag information (not shown) indicating the completion of the interview stored in the interview table. In this case, the control unit 204 of the user terminal 20 also resumes control of photographing the user during the interview period. In this case, the user stores video data that has been photographed and stored of the user's appearance in accordance with the number of times the interview is resumed. The control unit 204 of the user terminal 20 may combine the already created video data that has been photographed and stored of the user's appearance, and store the video data that has been photographed and stored of the user's appearance after the resume in one file. In addition, the control unit 204 of the user terminal 20 may combine the multiple video data that have been photographed and stored of the user's appearance into one video data after determining the completion of the interview in step S305 described later. In addition, the combination of video data may be executed by the control unit 104 of the server 10.

[0098] <Acquisition of speech> In step S304, the processing unit 1043 of the server 10 executes an utterance acquisition step of acquiring utterance contents from the user in response to presenting the interview to the user. Specifically, the input device 206 (microphone 2062) of the user terminal 20 accepts the contents of the user's speech in response to the interview question presented in step S303. For example, if the interview question is "What is the manufacturer of the motorcycle you are using?" and the user utters "Yamazaki Heavy Industries," the speech is acquired and accepted via the microphone 2062. The control unit 204 of the user terminal 20 transmits the acquired speech to the server 10. The control unit 104 of the server 10 receives and accepts the speech from the user terminal 20. The control unit 104 of the server 10 stores the uttered voice in the item of the utterance content of the target record in the interview table 1016. The control unit 104 of the server 10 may convert the voice data received from the user into a character string using a known voice recognition function or the like, and store the character string in the item of the utterance content of the interview table 1016.

[0099] <Utterance acquisition (first utterance acquisition step)> In step S304, the processing unit 1043 of the server 10 executes a first utterance acquisition step of acquiring the contents of a 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 in the interview question presentation (0th presentation step), and stores it in the utterance content item of the interview table 1016.

[0100] <Utterance acquisition (second utterance acquisition step)> In step S304, the processing unit 1043 of the server 10 executes a second utterance acquisition step of acquiring second utterance content from the user in response to presenting the interview based on the first output to the user. 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 in the interview question presentation (first presentation step), and stores it in the item of the utterance content in the interview table 1016.

[0101] <Utterance acquisition (Nth utterance acquisition step)> In step S304, the processing unit 1043 of the server 10 executes an N-th utterance acquisition step of acquiring the N-th utterance content from the user. Specifically, the control unit 104 of the server 10 acquires the utterance content (Nth utterance content) in response to the N-1st interview question presented to the user in the interview question presentation (N-1st presentation step), and stores it in the utterance content item of the interview table 1016.

[0102] <Utterance Acquisition (First Embodiment)> In step S304, the speech acquisition step executes a step of acquiring the contents of the user's speech in a first period after presenting the interview to the user. Specifically, the control unit 204 of the user terminal 20 executes control to acquire the contents of the user's utterance for a predetermined period (first period) such as 10 seconds, 20 seconds, 30 seconds, 1 minute, etc. Specifically, after presenting the interview questions to the user, the control unit 204 of the user terminal 20 ends the utterance acquisition step after the first period has elapsed, and stores the contents of the user's utterance in the item of utterance contents in the interview table 1016.

[0103] <Utterance Acquisition (Second Embodiment)> In step S304, the processing unit 1043 of the server 10 executes an extension step of accepting an input operation for extending the first period from the user. The utterance acquisition step executes a step of acquiring the user's utterance contents during the first period and the predetermined extension period, excluding the user's utterance contents during the predetermined extension period. Specifically, the interview processing page may include a "stop speech button." The user selects the "stop speech 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 stop speech button, it stops acquiring the contents of the speech from the user. The control unit 204 of the user terminal 20 resumes acquiring the contents of the speech from the user a predetermined period of time after the user selects the stop speech button. Note that acquisition of the contents of the speech from the user may be resumed in response to the reception of an input operation by the input device 206 of the user terminal 20 on the "resume speech button" or the like included in the interview processing page. As a result, the period (first period) during which the user can speak in response to the interview question is extended by a predetermined period according to the interruption period.

[0104] <Utterance Acquisition (Third Embodiment)> In step S304, the utterance acquiring step executes a step of acquiring the contents of the user's utterance in response to an input operation accepted from the user. Specifically, the control unit 204 of the user terminal 20 terminates the speech acquisition step in response to receiving an input operation by the input device 206 of the user terminal 20 on an “end speech button” or the like included in the interview processing page, and stores the content of the user's utterance in the “speech content” item of the interview table 1016.

[0105] <Utterance Acquisition (Fourth Embodiment)> In step S304, the processing unit 1043 of the server 10 accepts an input operation for redoing the interview from the user, and executes a retry step of executing the utterance acquisition step again in response to the input operation. Specifically, the control unit 204 of the user terminal 20 can restart presenting the interview question in step S303 or acquiring the spoken content in step S304 from the beginning in response to reception of an input operation by the input device 206 of the user terminal 20 on a "retry button" or the like included in the interview processing page. This allows the user to retry the answer if he / she was unable to give an appropriate answer, thereby reducing the stress of the user during the interview.

[0106] <Interview Completion Judgment> In step S305, the control unit 104 of the server 10 determines whether the interview is completed or not. The end of the interview may be determined by the following method. In the interview question generation step S302, when a prompt for generating interview questions is input to the artificial intelligence system 50, the artificial intelligence system 50 outputs information indicating that there are no additional interviews to be conducted, When one or more utterance contents acquired in the utterance acquisition step S304 during the interview process satisfy a predetermined condition. For example, when the output obtained by inputting a prompt generated by including a viewpoint and an utterance content in an instruction for determining the completion of the interview to the artificial intelligence system 50 includes information indicating that the interview is completed. When the duration of the user's speech exceeds a specified period. When the user inputs an instruction to end the interview,

[0107] If the control unit 104 of the server 10 determines in step S305 that the interview is not completed, the process returns to step S302.

[0108] If the control unit 104 of the server 10 determines that the interview is not complete after acquiring the first utterance content in the utterance acquisition (first utterance acquisition step) of step S304, it executes the interview question creation (first creation step) of step S302. Similarly, if the control unit 104 determines that the interview is not complete after acquiring the second utterance content and the Nth utterance content in the utterance acquisition (second utterance acquisition step) and the utterance acquisition (Nth utterance acquisition step), it executes the interview question creation (second creation step) and the interview question creation (Nth creation step) of step S302.

[0109] In step S305, if the control unit 104 of the server 10 determines that the interview is completed, it transmits information indicating that the interview is completed to the user terminal 20. Upon receiving the information, the control unit 204 of the user terminal 20 displays and presents the information indicating that the interview is completed on the display 2081 or the like of the user terminal 20. This ends the interview process.

[0110] <Consistency check process> The consistency checking process is a process for determining whether or not the answers given by a predetermined user in the questionnaire process and the spoken content in the interview process are consistent with each other, based on the answers given by the predetermined user in the questionnaire process and the spoken content in the interview process.

[0111] <Outline of consistency check process> The consistency check process is a series of processes that acquire project information, identify users (subjects) who are the targets of consumer survey information collection for the project, acquire survey question and answer responses for the users, acquire interview questions and speech content for the users, and determine the consistency between the survey question and answer responses and the interview speech content. This makes it possible to check the consistency of the content of the consumer survey information.

[0112] <Details of the consistency check process> The consistency checking process will be described in detail below.

[0113] <Get project information> In step S401, a project ID for identifying predetermined project information related to the consistency checking process is acquired. The consistency check process may identify a predetermined project ID for which questionnaire processing and interview processing have been completed for all users related to the target of a predetermined project. The consistency check process may identify and acquire a predetermined project ID in response to an input operation by a user related to the administrator.

[0114] <Target identification> In step S402, the control unit 104 of the server 10 searches the project ID item in the project table 1013 based on the specified project ID acquired in step S401, and acquires and identifies one or more user IDs stored in the target person item.

[0115] <Get questions and answers> In step S403, the control unit 104 of the server 10 searches the user ID item in the answer table 1015 based on the one or more user IDs acquired in step S402, and acquires the question ID and the answer content. The control unit 104 of the server 10 searches the question ID item in the question table 1014 based on the acquired question ID, and acquires the question content. As a result, the control unit 104 of the server 10 acquires questions to the user in the questionnaire process for users who are the targets of a specific project, and the contents of the answers from the user.

[0116] <Interview utterance acquisition> In step S404, the control unit 104 of the server 10 searches the user ID item in the interview table 1016 based on one or more user IDs acquired in step S402, and acquires the interview questions and speech contents. As a result, the control unit 104 of the server 10 acquires interview questions for the user in the interview process for the user who is a subject of a predetermined project, and the contents of the speech from the user.

[0117] <Consistency judgment> In step S405, the processing unit 1043 of the server 10 executes a comparison creation step of creating a comparison prompt by including the answer content acquired in the answer acquisition step and at least a part of the user's utterance in an instruction to compare the answer content to the question form with the user's utterance in the interview. The comparison creation step includes a step of creating a comparison prompt by including the answer content and at least a portion of the user's speech content in instructions for determining whether the answer to the questionnaire form and the user's speech content in the interview are consistent. Specifically, the control unit 104 of the server 10 creates a comparison prompt by inserting the acquired values ​​of the question content, answer content, interview question, and utterance content into the ${question content}, ${answer content}, ${interview question}, and ${utterance content} portions of instruction sentence B stored in the storage unit 101 of the server 10. When there are multiple questions, answers, interview questions, and utterance contents, the comparison prompt is created by inserting the question content, answer content, interview question, and utterance content included in the question content, answer content, interview question, and utterance content into the following portions: question content 1, answer content 1, interview question 1, utterance content 1, question content 2, answer content 2, interview question 2, utterance content 2, ... The comparison prompt is created for each user by including the question content, answer content, interview question, and utterance content for each user in the instruction sentence B.

[0118] <Instruction text B> Below are the survey and interview results of specific users on specific points of view. Compare the survey results with the interview results and determine whether the answers given by the users are consistent with the content of their 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} ##Utterance content 1 ${Utterance content 1} Interview Question 2 ${Interview Question 2} ##Utterance content 2 ${Utterance content 2} ...

[0119] The comparison creation step includes a step of creating a comparison prompt by including the answer content and at least a part of the user's utterance content in an instruction for determining whether the user's utterance content in the interview is consistent with respect to one or more question perspectives in the question form. Specifically, the control unit 104 of the server 10 may generate a prompt that outputs a judgment result for each question content (for each answer content) based on instruction text B (variant example) stored in the memory unit 101 of the server 10. This makes it possible to compare the consistency between the user information collected from one or more question perspectives in the question form and the information collected from the user through an interview. The consistency of consumer survey information collected from users can be checked in more detail.

[0120] <Instruction B (variation)> Below are the survey and interview results of specific users on specific points of view. Compare the survey results with the interview results, and for each answer in the survey results, determine whether the content is consistent with the user's utterances. #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} ##Utterance content 1 ${Utterance content 1} Interview Question 2 ${Interview Question 2} ##Utterance content 2 ${Utterance content 2} ...

[0121] In step S506, the control unit 104 of the server 10 inputs the created comparison prompt by transmitting 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 determination result of the consistency between the answers to the questionnaire questions and the content of the interview utterances. The control unit 104 of the server 10 stores the value of the judgment result included in the output content in the judgment result item of the answer table 1015. In the present disclosure, as an example, the output content (the judgment result for each of one or a plurality of question contents and answer contents) for the instruction statement B (variation example) is configured to be stored in the judgment result item of the answer table 1015, but this is not limited to the above. For example, in instruction statement B, information indicating the consistency judgment result is output to the user, and in that case, the information may be stored in the target item of project table 1013 in association with information identifying the user to be judged.

[0122] <Point of view analysis processing> The viewpoint analysis process is a process of analyzing consumer survey information of users collected by questionnaire processing, interview processing, etc., along one or more specific viewpoints (analysis viewpoints).

[0123] <Outline of viewpoint analysis process> The viewpoint analysis process is a series of processes that accepts input of an analysis viewpoint, accepts input of analysis items, accepts input of a user (subject) related to the analysis target, acquires survey information related to the accepted user, generates a prompt based on the input information and the survey information, acquires and presents the viewpoint analysis results that are output by inputting the prompt to the prompt generation AI 50.

[0124] <Details of viewpoint analysis process> The viewpoint analysis process will be described in detail below.

[0125] <Analysis viewpoint input> In step S501, the administrator operates the input device 306 of the administrator terminal 30 to input the URL of a page for executing viewpoint analysis processing (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 transmits a request to open the viewpoint analysis processing page to the server 10. The control unit 104 of the server 10 generates a viewpoint analysis processing page based on the received request, and transmits 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 operates the input device 306 of the administrator terminal 30 to transmit the project ID related to the viewpoint analysis processing to the server 10. Note that the URL may include a character string for identifying the project ID related to the viewpoint analysis processing. 20 is an example of a first screen of a viewpoint analysis processing page D1 in viewpoint analysis processing. The viewpoint analysis processing page D1 includes input fields for a viewpoint name D11, a viewpoint directive D12, and an analysis item D13. Each item corresponds to each item in the analysis viewpoint table 1031.

[0126] In step S501, the processing unit 1043 of the server 10 executes an instruction acquisition step of acquiring a first instruction to output one or more perspectives related to the investigation information. The processing unit 1043 of the server 10 executes a second instruction acquisition step of acquiring a second instruction to output one or more perspectives. Specifically, the administrator operates the input device 306 of the administrator terminal 30 to input a directive into the viewpoint directive D12. For example, directives such as "If we compare it to animals," "What are the tendencies of favorite animals," etc. are input. The control unit 304 of the administrator terminal 30 transmits the directive input into the viewpoint directive D12 to the server 10. The control unit 104 of the server 10 acquires and accepts the directive.

[0127] In step S501, the instruction obtaining step executes a step of obtaining a first instruction to output one or more perspectives related to survey information for each of a plurality of users. Specifically, an analysis process based on the viewpoint directive D12 is executed on one or more users included in the target item of the plan information identified by searching the plan ID in the plan table 1013 based on the plan ID related to the viewpoint analysis process.

[0128] <Analysis item reception> In step S502, the processing unit 1043 of the server 10 executes a survey presentation step of presenting information indicating one or more pieces of survey information to the user in a selectable manner. The processing unit 1043 of the server 10 executes a survey selection step of accepting, from the user, a selection of information indicating predetermined survey information from the information indicating one or more pieces of survey information presented in the survey presentation step. Specifically, the administrator selects survey information to be analyzed from one or more survey information (data sources) included in the analysis item D13 by operating the input device 306 of the administrator terminal 30. For example, the survey information can be selected from the contents of answers in a questionnaire process, the contents of utterances in an interview process, etc.

[0129] The processing unit 1043 of the server 10 executes an output presenting step of presenting information indicating one or more output contents to the user in a selectable manner. The processing unit 1043 of the server 10 executes an output selection step of accepting, from the user, a 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 answer contents in the questionnaire process and the spoken contents in the interview process, the viewpoint analysis results output for each user in the viewpoint analysis process can also be selected as analysis items. For example, the answers given to a particular user in a questionnaire process, the contents of speech given in an interview process, etc. can be targeted, and the viewpoint analysis results output by the viewpoint analysis process along a particular viewpoint, such as "If we compare it to an animal," or "Favorite animal tendencies," can be selected as analysis items. This allows the analysis results output in response to survey information collected from users through questionnaire surveys, interview surveys, and the like to be further analyzed from one or more perspectives. The analysis results obtained from the survey information can be further analyzed in depth from a specific perspective.

[0130] <Analysis user reception> In step S503, the control unit 104 of the server 10 searches the item of the project ID in the project table 1013 based on the project ID accepted in step S501, and acquires the target person. The control unit 104 of the server 10 acquires and identifies one or more user IDs included in the item of the target person. Alternatively, the administrator may operate the input device 306 of the administrator terminal 30 to manually select one or more users to be the targets of the viewpoint analysis process, or to exclude them from the selection targets.

[0131] <Acquisition of survey information> In step S504, the processing unit 1043 of the server 10 executes a survey acquisition step of acquiring survey information related to the user. The survey acquisition step executes a step of acquiring survey information corresponding to the information indicating the predetermined survey information selected in the survey 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 accepted in step S503. When the analysis item is the content of an answer in a questionnaire process, the control unit 104 of the server 10 searches the item of the project ID in the question table 1014 based on the project ID, and acquires the question ID and the question content. The control unit 104 of the server 10 searches the items of the question ID and the user ID in the answer table 1015 based on the question ID and the user ID, and acquires the item of the answer content. When the analysis item is the content of the utterance in the interview process, the control unit 104 of the server 10 searches the items of the project ID and user ID in the interview table 1016 based on the project ID and user ID, and acquires the items of the interview question and the content of the utterance. When the analysis item is a viewpoint analysis result of a viewpoint analysis process, the control unit 104 of the server 10 searches the item of the user ID in the analysis viewpoint result table 1032 based on the user ID, and acquires the item of the viewpoint analysis result.

[0132] The survey acquisition step includes a step of acquiring a plurality of survey information regarding a plurality of users. Specifically, the control unit 104 of the server 10 acquires a plurality of pieces of survey information for each of the plurality of users accepted in step S503.

[0133] <Prompt Generation> In step S505, the processing unit 1043 of the server 10 executes a creating step of creating a prompt by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step. specifically,

[0134] In step S505, the creating step executes a step of creating a prompt by including, in the first instruction, one or more viewpoints and survey information corresponding to the information indicating the predetermined survey information. The processing unit 1043 of the server 10 executes a second creation step of creating a prompt by including output content in the second instruction acquired in the second instruction acquisition step. The second creation step executes a step of creating a prompt by including output content corresponding to information indicating the predetermined output content in the second instruction. Specifically, the control unit 104 of the server 10 creates the prompt D by inserting the viewpoint directive into the ${viewpoint directive} position of the directive D stored in the storage unit 101 of the server 10, and the survey information acquired in step S504 into the ${survey information} position. Note that the prompt D may also be created by inserting survey information into the ${survey information} position of the viewpoint directive.

[0135] <Instructive text D> ${viewpoint directive} ${investigation information}

[0136] <Prompt Generation (First Embodiment)> In step S505, the creating step executes a step of creating a plurality of prompts corresponding to the plurality of users, by including, in the first instruction, each of the plurality of pieces of survey information acquired in the survey acquisition step. Specifically, prompt D is created individually and independently for each of the multiple users identified in step S503. Separate prompts for each user can improve output quality.

[0137] <Prompt Generation (Second Embodiment)> In step S505, the creating step executes a step of creating a prompt by including the first instruction acquired in the instruction acquiring step and the plurality of pieces of survey information acquired in the survey acquiring step. Specifically, the control unit 104 of the server 10 creates a prompt D by inserting a viewpoint directive into the ${viewpoint directive} portion of the directive D (variant example) stored in the memory unit 101 of the server 10, and inserting the survey information acquired in step S504 for each analysis target user into the ${survey information 1}, ${survey information 2}, ${survey information 3}, ... portions. For example, survey information 1, survey information 2, and survey information 3 are the survey information (survey information related to the analysis items identified in step S502) of user 1, user 2, and user 3, who are the users to be analyzed in the viewpoint analysis process. By including multiple pieces of survey information together in a prompt, the number of tokens in the prompt, the number of processes, and the processing cost can be reduced. <Instruction D (variation)> Follow the instructions below to output the processing results for each of survey information 1, survey information 2, and survey information 3. ${viewpoint directive} #Survey information 1 ${Investigation information 1} #Survey information 2 ${Investigation information 2} #Survey information 3 ${Investigation information 3}

[0138] <Obtaining viewpoint analysis results> In step S506, the processing unit 1043 of the server 10 executes an input step of inputting a prompt to the artificial intelligence system, and an output acquisition step of acquiring output content to be output in response to inputting the prompt to the artificial intelligence system. The output acquisition step executes a step of acquiring output content corresponding to information indicating the predetermined output content selected in the output selection step. Specifically, the control unit 104 of the server 10 inputs the created prompt D by transmitting it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output contents in response to the input of the prompt D. The output contents include a processing result according to the analysis viewpoint accepted in step S501 for the survey information acquired in step S504.

[0139] The control unit 104 of the server 10 stores the user ID of the user who is the target of the viewpoint analysis processing, the prompt D created for that user, and the output contents from the artificial intelligence system 50 in the analysis viewpoint result table 1032 in the fields of user ID, viewpoint analysis prompt, and viewpoint analysis result.

[0140] The control unit 104 of the server 10 transmits the analysis viewpoint result information stored in the analysis viewpoint result table 1032 to the manager terminal 30. The control unit 304 of the manager terminal 30 displays a page (analysis viewpoint result page D2) for displaying the received analysis viewpoint result information on the display 3081 of the manager terminal 30. 21 is a second screen example showing the operation of the viewpoint analysis process. The analysis viewpoint result page D2 displays viewpoint analysis results D211, D221, D231 related to the viewpoint directive sentence of viewpoint A and viewpoint analysis results D212, D222, D232 related to the viewpoint directive sentence of viewpoint B in association with each user D21, D22, D23, . . . This allows the survey information collected from users through questionnaire surveys, interview surveys, etc. to be analyzed from one or more perspectives.

[0141] <Insight analysis processing> The insight analysis process is a process for digging deeper into the analysis viewpoint across one or more viewpoint analysis results output by the viewpoint analysis process.

[0142] <Overview of insight analysis processing> The insight analysis process is a series of processes that accepts input of an insight instruction statement, accepts input of an analysis perspective to be analyzed in the insight analysis process, generates a prompt based on the insight instruction statement and the analysis perspective that has been accepted as input, and obtains and presents the insight analysis results that are output by inputting the prompt to generation AI 50.

[0143] <Details of insight analysis processing> The insight analysis process will be described in detail below.

[0144] <Analysis item reception> In step S601, the processing unit 1043 of the server 10 executes a third output acquisition step of acquiring a plurality of output contents for a plurality of users that are output in response to inputting a prompt to the artificial intelligence system. The processing unit 1043 of the server 10 executes a third output presenting step of presenting information indicating one or more output contents to the user in a selectable manner. The processing unit 1043 of the server 10 executes a third output selection step of accepting, from the user, a selection of information indicating a predetermined output content from the information indicating one or more output contents presented in the third output presentation step. The third output acquisition step executes a step of acquiring a plurality of output contents for a plurality of users according to the information indicating the predetermined output content selected in the third output selection step. Specifically, the administrator operates the input device 306 of the administrator terminal 30 to select the check boxes D201, D202, etc., which select each of the perspective analysis results D211, D221, D231 and the perspective analysis results D212, D222, D232, etc. output by the perspective analysis process on the analysis perspective result page D2, of one or more check boxes that are related to the processing target of the insight analysis processing. The administrator operates the input device 306 of the administrator terminal 30 to select one or more viewpoint analysis results output by the viewpoint analysis processing as targets for the insight analysis processing.

[0145] <Accepting insight instruction input> In step S602, the processing unit 1043 of the server 10 executes a third instruction acquisition step of acquiring a third instruction to output one or more viewpoints. Specifically, the administrator selects an "insight analysis button" included in the analysis viewpoint result page D2 by operating the input device 306 of the administrator terminal 30. The control unit 304 of the administrator terminal 30 displays on the display 3081 of the administrator terminal 30 a screen (insight analysis screen D3) for digging deeper into the analysis viewpoint across one or more viewpoint analysis results output by the viewpoint analysis process. 22 is a screen example showing the operation of the insight analysis process. The insight analysis screen D3 includes an insight instruction statement input field D31. The insight analysis screen D3 includes an insight instruction statement D311, an insight analysis result D312, an insight instruction statement D321, an insight analysis result D322, an insight instruction statement D331, an insight analysis result D332, . . . The administrator operates the input device 306 of the administrator terminal 30 to input an instruction statement (insight instruction statement) for further digging into the viewpoint analysis results selected in step S601 for multiple users into the insight instruction statement input field D31. For example, insight prompts could be, “Name the three best candidates?”, “Which candidate has the best technical skills?”, “Name the candidate with the best teamwork skills?”, etc.

[0146] <Prompt Generation> In step S603, the processing unit 1043 of the server 10 executes a third creation step of creating a third prompt by including the third instruction acquired in the third instruction acquisition step and the multiple output contents for the multiple users acquired in the third output acquisition step. The third creating step includes a step of creating a third prompt by including, in the third instruction, a plurality of output contents for a plurality of users according to information indicating predetermined output contents. Specifically, the control unit 104 of the server 10 creates a prompt E by including one or more viewpoint analysis results acquired in step S601 in the insight instruction sentence accepted in step S602. The viewpoint analysis results include viewpoint analysis results output by the viewpoint analysis process for multiple users. <prompt E> ${insight directive} ${Perspective analysis result}

[0147] <Obtain insight analysis results> In step S604, the control unit 104 of the server 10 inputs the created prompt E by transmitting it to the artificial intelligence system 50. The artificial intelligence system 50 outputs output contents in response to the input of the prompt E. The output contents include an analysis result that delves deeper into the analysis viewpoint across 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 object of analysis in the perspective analysis process, the analysis perspective ID related to the analysis item selected in step S601, the insight instruction statement received in step S602, and the output contents of the artificial intelligence system 50 in the project ID, target perspective ID, insight instruction statement, and insight analysis result items of the analysis insight table 1033, respectively.

[0148] The analysis insight information stored in the analysis insight table 1033 is transmitted to the administrator terminal 30 and displayed on the display 3081 of the administrator terminal 30 as an insight instruction statement D311, an insight analysis result D312, an insight instruction statement D321, an insight analysis result D322, an insight instruction statement D331, an insight analysis result D332, etc. on the insight analysis screen D3.

[0149] <Basic computer hardware configuration> 23 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.

[0150] The processor 901 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0151] The main memory device 902 is for temporarily storing programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0152] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0153] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can connect to the Internet via a specified access point (e.g., Wi-Fi (registered trademark)), etc. In the case of wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of wired connection, the network also includes a network that is directly connected by a USB (Universal Serial Bus) cable or the like.

[0154] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration among multiple computers 90 and connecting them together via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0155] <Basic functional configuration of computer 90> A description will now be given of the functional configuration of a computer realized by the basic hardware configuration (FIG. 23) of a computer 90. The computer comprises at least the functional units of a control unit, a storage unit, and a communication unit.

[0156] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 connected to each other via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0157] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding the programs in the main storage device 902, and executing processes according to the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0158] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general purpose processors, application specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the functions described. Processors include transistors and other circuits and are considered to be circuitry or processing circuitry. A processor may be a programmed processor that executes a program stored in a memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed in this specification or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0159] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with a program. Furthermore, the control unit can cause the processor 901 to execute processes of adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0160] The term database refers to a relational database, which is used to manage sets of data called masters and tables in a tabular format structurally defined by rows and columns, by associating them with each other. In a database, a table is called a table or master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Usually, a column that serves as a primary key for uniquely identifying a record is set in each table and each master, but setting a primary key in a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in a specific table or master stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0161] In addition, the database and master in this disclosure may include any data structure (such as a list, a dictionary, an associative array, or an object) in which information is structurally defined. The data structure also includes data that can be considered as a data structure by combining data with a function, class, method, or the like written in any programming language.

[0162] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0163] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0164] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program executing a survey acquisition step (S504) in which the processor acquires survey information related to a user, an instruction acquisition step (S501) in which a first instruction is acquired to output one or more perspectives related to the survey information, and a creation step (S505) in which a prompt is created by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step. This allows the survey information collected from users through questionnaire surveys, interview surveys, etc. to be analyzed from one or more perspectives.

[0165] (Appendix 2) 2. The program of claim 1, wherein the survey information is survey information collected from one or more users regarding the users' product or service interests and concerns. This allows consumer survey information regarding a user's product or service interests and concerns to be analyzed along one or more dimensions.

[0166] (Appendix 3) 2. The program according to claim 1, wherein the survey information includes at least one of the following: answers entered by the user in a question form; and speech spoken by the user in an interview. This makes it possible to analyze the answers given by users to question forms and the contents of their speech in interviews from one or more perspectives.

[0167] (Appendix 4) A program as described in Appendix 1, wherein a processor executes a survey presentation step (S502) of presenting information indicating one or more pieces of survey information to a user in a selectable manner, and a survey selection step (S502) of accepting from the user a selection of information indicating specified survey information from the information indicating the one or more pieces of survey information presented in the survey presentation step, wherein a survey acquisition step (S504) is a step of acquiring survey information corresponding to the information indicating the specified survey information selected in the survey selection step, and a creation step (S505) is a step of creating a prompt by including one or more perspectives and survey information corresponding to the information indicating the specified survey information in a first instruction. This makes it possible to select only the survey information appropriate for the viewpoint analysis from among the survey information collected from the user through the questionnaire, interview, etc. By not including unnecessary information in the prompt, the output quality can be improved.

[0168] (Appendix 5) The program described in Appendix 1, in which a processor executes an input step (S506) of inputting a prompt to an artificial intelligence system, an output acquisition step (S506) of acquiring output content to be output in response to inputting the prompt to the artificial intelligence system, and a second instruction acquisition step (S501) of acquiring second instructions to output one or more perspectives, and a second creation step (S505) of creating a prompt by including the output content in the second instruction acquired in the second instruction acquisition step. This allows the analysis results output in response to survey information collected from users through questionnaire surveys, interview surveys, and the like to be further analyzed from one or more perspectives. The analysis results obtained from the survey information can be further analyzed in depth from a specific perspective.

[0169] (Appendix 6) The program described in Appendix 5, wherein the processor executes an output presentation step (S502) of presenting to a user information indicating one or more selectable output contents, and an output selection step (S502) of accepting from the user a selection of information indicating a predetermined output content from the information indicating the one or more output contents presented in the output presentation step, wherein an output acquisition step (S506) is a step of acquiring output content corresponding to the information indicating the predetermined output content selected in the output selection step, and a second creation step (S505) is a step of creating a prompt by including, in a second instruction, output content corresponding to the information indicating the predetermined output content. This makes it possible to select only the appropriate output contents according to the viewpoint analysis from among the output contents output from the artificial intelligence system. By not including unnecessary information in the prompt, the output quality can be improved.

[0170] (Appendix 7) The program described in Appendix 1, wherein the survey acquisition step (S504) is a step of acquiring multiple pieces of survey information regarding multiple users, and the creation step (S505) is a step of creating multiple prompts corresponding to each of the multiple users by including each of the multiple pieces of survey information acquired in the survey acquisition step in the first instruction. This allows the survey information collected from multiple users to be analyzed from one or more perspectives for each of the survey information of each user. Separate prompts for each user can improve output quality.

[0171] (Appendix 8) The program described in Appendix 1, wherein the survey acquisition step (S504) is a step of acquiring multiple survey information related to multiple users, the instruction acquisition step (S501) is a step of acquiring a first instruction for outputting one or multiple perspectives regarding the survey information for each of the multiple users, and the creation step (S505) is a step of creating a prompt by including the multiple survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step. This allows the survey information collected from multiple users to be analyzed from one or more perspectives for each of the survey information of each user. By including multiple pieces of survey information together in a prompt, the number of tokens in the prompt, the number of processes, and the processing cost can be reduced.

[0172] (Appendix 9) The survey acquisition step (S504) is a step of acquiring multiple survey information regarding multiple users, and the processor executes an input step (S506) of inputting a prompt into the artificial intelligence system, a third output acquisition step (S601) of acquiring multiple output contents for multiple users that are output in response to inputting the prompt into the artificial intelligence system, a third instruction acquisition step (S602) of acquiring third instructions to output one or more perspectives, and a third creation step (S603) of creating a third prompt by including the multiple output contents for multiple users acquired in the third output acquisition step in the third instruction acquired in the third instruction acquisition step. This allows analysis results output for survey information of a plurality of users to be analyzed across the plurality of users. Further in-depth analysis can be performed on the analysis results from one or more perspectives.

[0173] (Appendix 10) The program described in Appendix 9, wherein the processor executes a third output presentation step (S601) of presenting to a user information indicating one or more output contents in a selectable manner, and a third output selection step (S601) of accepting from the user a selection of information indicating a predetermined output content from the information indicating the one or more output contents presented in the third output presentation step, wherein the third output acquisition step (S601) is a step of acquiring multiple output contents for multiple users according to the information indicating the predetermined output content selected in the third output selection step, and the third creation step (S603) is a step of creating a third prompt by including, in a third instruction, multiple output contents for multiple users according to the information indicating the predetermined output content. This makes it possible to select only the appropriate output contents according to the viewpoint analysis from among the output contents output from the artificial intelligence system.By not including unnecessary information in the prompt, it is possible to improve the output quality of in-depth analysis of analysis results along one or more viewpoints.

[0174] (Appendix 11) A method executed by an information processing device having a processor and a memory unit, wherein the processor executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10. This allows the survey information collected from users through questionnaire surveys, interview surveys, etc. to be analyzed from one or more perspectives.

[0175] (Appendix 12) An information processing device comprising a processor and a memory unit, wherein the processor executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10. This allows the survey information collected from users through questionnaire surveys, interview surveys, etc. to be analyzed from one or more perspectives.

[0176] (Appendix 13) A system comprising means for performing all the steps performed in any one of claims 1 to 10. This allows the survey information collected from users through questionnaire surveys, interview surveys, etc. to be analyzed from one or more perspectives. [Explanation of symbols]

[0177] 1 system, 10 server, 101 memory unit, 104 control unit, 106 input device, 108 output device, 20 user terminal, 201 memory unit, 204 control unit, 206 input device, 208 output device, 30 administrator terminal, 301 memory unit, 304 control unit, 306 input device, 308 output device, 50 generation 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 storage unit, The processor, A survey acquisition step of acquiring survey information regarding the user; An instruction acquisition step of acquiring a first instruction to output one or more perspectives related to the survey information; a creating step of creating a first prompt by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step; inputting the first prompt into a large scale language model; a first output acquisition step of acquiring a first output content, the first output content including one or more perspectives related to the survey information, the first output content being output in response to inputting the first prompt into the large-scale language model; a second instruction acquisition step of acquiring a second instruction to output one or more viewpoints; a second creation step of creating a second prompt by including the first output content in the second instruction; inputting the second prompt into a large scale language model; acquiring a second output content, the second output content including one or more perspectives on the first output content, output in response to inputting the second prompt into the large-scale language model; A program that executes.

2. A program to be executed by a computer having a processor and a storage unit, The processor, A survey acquisition step of acquiring survey information regarding a plurality of users; An instruction acquisition step of acquiring a first instruction to output one or more perspectives related to the survey information; a creating step of creating a first prompt by including the survey information acquired in the survey acquisition step in the first instruction acquired in the instruction acquisition step; inputting the first prompt into a large scale language model; a first output acquisition step of acquiring, for each of the plurality of users, first output content including one or more perspectives related to the survey information, the first output content being output in response to inputting the first prompt into the large-scale language model; a third instruction acquisition step of acquiring a third instruction to output one or more viewpoints; a third generation step of generating a third prompt by including the first output content in the third instruction; inputting the third prompt into a large scale language model; a third output acquisition step of acquiring third output content, the third output content including one or more perspectives regarding the first output content of the plurality of users, the third output content being output in response to inputting the third prompt into the large-scale language model; A program that executes.

3. A program to be executed by a computer having a processor and a storage unit, The processor, A survey presentation step of presenting information indicating one or more survey information to a user in a selectable manner; a survey selection step of accepting, from the user, a selection of information indicating a predetermined survey information from the information indicating one or more pieces of survey information presented in the survey presentation step; a survey acquisition step of acquiring survey information related to the user according to information indicating the predetermined survey information selected in the survey selection step; An instruction acquisition step of acquiring a first instruction to output one or more perspectives related to the survey information; a creating step of creating a first prompt by including the one or more viewpoints and survey information corresponding to the information indicating the predetermined survey information in the first instruction acquired in the instruction acquisition step; inputting the first prompt into a large scale language model; acquiring a first output content, the first output content including one or more perspectives related to the predetermined survey information, in response to inputting the first prompt into the large-scale language model; Execute The survey information is survey information collected from one or more users regarding their product or service interests and concerns. program.

4. The survey information is survey information collected from one or more users regarding their product or service interests and concerns. The program according to any one of claims 1 to 3.

5. The survey information is The answers entered by the user in the question form, The contents of the user's speech in the interview, At least one of the following is included: The program according to any one of claims 1 to 3.

6. The processor, an output presenting step of presenting information indicating one or more output contents to the user in a selectable manner; an output selection step of accepting, from the user, a selection of information indicating a predetermined output content from information indicating one or more output contents presented in the output presentation step; Run the first output acquisition step is a step of acquiring output content corresponding to information indicating the predetermined output content selected in the output selection step, The second generation step is a step of generating a prompt by including, in the second instruction, output content corresponding to the information indicating the predetermined output content. The program according to claim 1.

7. The survey acquisition step is a step of acquiring a plurality of survey information related to a plurality of users, The creating step is a step of creating a plurality of prompts corresponding to each of the plurality of users by including, in the first instruction, each of the plurality of pieces of survey information acquired in the survey acquisition step. The program according to claim 1.

8. The survey acquisition step is a step of acquiring a plurality of survey information related to a plurality of users, The instruction acquisition step is a step of acquiring the first instruction to output one or more perspectives related to the survey information for each of a plurality of users, The creating step is a step of creating a prompt by including the first instruction acquired in the instruction acquiring step and the plurality of pieces of survey information acquired in the survey acquiring step. The program according to any one of claims 1 to 3.

9. The processor, a third output presenting step of presenting information indicating one or more output contents to the user in a selectable manner; a third output selection step of accepting, from the user, a selection of information indicating a predetermined output content from the information indicating the one or more output contents presented in the third output presentation step; Run the third output acquisition step is a step of acquiring a plurality of output contents for each of the plurality of users according to information indicating the predetermined output content selected in the third output selection step; the third generation step is a step of generating the third prompt by including, in the third instruction, a plurality of output contents for each of the plurality of users according to the information indicating the predetermined output contents; The program according to claim 2.

10. A method executed by an information processing device including a processor and a storage unit, the processor executing all of the steps executed in the invention according to any one of claims 1 to 3.

11. 4. An information processing device comprising a processor and a storage unit, the processor executing all the steps executed in the invention according to any one of claims 1 to 3.

12. A system comprising means for performing all the steps performed in any one of claims 1 to 3.

Images