Programs, information processing devices, methods, and systems

Abstract

Extract useful information from interviewees to improve the quality of the article. [Solution] A program for operating a computer comprising a processor and memory. The program causes the processor to input a basic prompt to the generating AI, which includes instructions for the generating AI to autonomously select a dialogue technique from a predefined set of dialogue techniques, taking into account the current phase of the dialogue, and analyze the context of the dialogue, including the dialogue history with the interviewee and the most recent query from the interviewee; to cause the generating AI to generate the next question using the dialogue technique selected using the basic prompt in response to a query from the interviewee, and to present the next question to the interviewee, repeating this series of dialogue processing until a predetermined termination condition is met; and, after the dialogue has ended, to cause the generating AI to generate an article from the dialogue history based on the basic prompt and to present it to the interviewee.

Description

Technical Field

[0004] , , , , , , ,

[0006] , , , ,

[0005] , , , , , ,

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

Background Art

[0002] Conventionally, the creation of an interview article generally involves a process in which a person in charge directly interacts with the interviewee and manually writes an article based on the information obtained.Interview guide systems that present a pre-defined list of questions and general-purpose chatbots that conduct general conversations exist to support this process.

[0003] In recent years, with the development of generative AI technology, more advanced dialogue systems have been proposed. For example, Patent Document 1 discloses a dialogue system in which generative AI plays the role of an interviewer and dynamically generates questions in response to the answers of the interviewee. This document also describes a technique for recognizing the emotions of the interviewee using an emotion engine and adjusting the tone and content of the questions based on those emotions.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the technique described in Patent Document 1, it is only possible to generate questions in response to answers, and it is difficult to structurally manage the entire interview and actively control the conversation to achieve the goal. For example, there is a problem that it is difficult to stabilize the quality of the interview, such as asking in-depth questions in a situation where a trust relationship should be built with the other party or changing the topic before comprehensively collecting information.

[0006] The purpose of this disclosure is to extract useful information from the interviewee and improve the quality of the article. [Means for solving the problem]

[0007] To solve the above problems, a program according to one aspect of the present disclosure is a program for operating a computer comprising a processor and memory, the program causing the processor to input a basic prompt to a generating AI, which includes instructions for the generating AI to autonomously select a dialogue technique from a predefined set of dialogue techniques, taking into account the current phase of the dialogue, and analyzing the context of the dialogue, including the dialogue history with the interviewee and the most recent query from the interviewee; the program causing the processor to input a basic prompt to the generating AI, which includes instructions for the generating AI to autonomously select a dialogue technique to apply from among a predefined set of dialogue techniques, in response to a query from the interviewee, and to repeat a series of dialogue processes, in which the generating AI generates the next question using the dialogue technique selected using the basic prompt, and presents the generated next question to the interviewee, until a predetermined termination condition is met; and, after the end of the dialogue, the program causing the generating AI to generate an article from the dialogue history based on the basic prompt, and presenting the generated article to the interviewee. [Effects of the Invention]

[0008] According to this disclosure, it is possible to extract useful information from interviewees and improve the quality of the article. [Brief explanation of the drawing]

[0009] [Figure 1] This block diagram shows the overall configuration of an interview article creation system according to one embodiment of this disclosure. [Figure 2] This is a block diagram showing a functional configuration example of the terminal device in this embodiment. [Figure 3] This is a block diagram showing an example of the functional configuration of the server in this embodiment. [Figure 4] This figure shows an example of the data structure of the dialogue technique table in this embodiment. [Figure 5]This flowchart shows an example of the interview article creation process in this embodiment. [Figure 6] This figure shows an example of a chatbot screen in this disclosure. [Figure 7] This figure shows an example of the article review screen in this disclosure. [Figure 8] This is a block diagram representing the basic hardware configuration of the computer used in the embodiments of this disclosure. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0011] Furthermore, in the following description, "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0012] Furthermore, at least one processor may be a broad-sense processor, such as a hardware circuit that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)).

[0013] In the following description, the expression such as "xxx table" may be used to describe information from which an output is obtained for an input. This information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, "xxx table" can be referred to as "xxx information".

[0014] In the following description, the configuration of each table is an example. One table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0015] In the following description, the "program" may be used as the subject to describe the process. Since the program is executed by a processor to perform a defined process while appropriately using a storage unit and / or an interface unit, etc., the subject of the process may be a processor (or a device such as a controller having the processor).

[0016] The program may be installed in a device such as a computer, or may be in, for example, a program distribution server or a computer-readable (e.g., non-temporary) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0017] In the following description, an identification number is used as identification information for various objects, but identification information of other types (e.g., an identifier including letters and symbols) may be adopted.

[0018] In the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type by distinction, identification numbers (or reference signs) of the elements may be used.

[0019] In the following description, the control lines and information lines indicate those considered necessary for the description, and not necessarily all the control lines and information lines on the product are shown. All components may be interconnected.

[0020] Each information processing device is composed of a computer having an arithmetic unit and a storage unit. 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 terminal device 10 and the server 20, descriptions overlapping with the basic hardware configuration of the computer and the basic functional configuration of the computer to be described later are omitted.

[0021] <1. Overview> System 1 provides a dialogue system for automating the creation of high-quality interview articles by utilizing generative AI technology. In this system, the interviewee conducts a dialogue with an anthropomorphic dialogue partner (AI interviewer) driven by generative AI. This system enables the generative AI to autonomously control the flow of the dialogue and the generation of response content based on a "basic prompt" that includes definitions related to the dialogue techniques possessed by professional interviewers. The server 20 mainly relays the queries input from the interviewee to the generative AI system and presents the responses (questions, comments, etc.) from the generative AI system to the interviewee. The dialogue progresses through a plurality of structured phases, and in this process, a plurality of dialogue techniques are autonomously selected and applied according to the situation. After the interview ends, a well-structured article is automatically generated based on the collected information, and through confirmation and correction by the interviewee, an interactive process leading to completion is realized. Large language models (LLMs), etc. can be used for the generative AI.

[0022] Here, the structured multiple phases refer to, for example, a framework for progressing the dialogue step by step according to the purpose or situation of the dialogue. For example, the phases in this embodiment include a "listening phase" to build trust with the interviewee and collect basic information, a "deep dive phase" to explore background information and motivations related to a specific topic, a "concretization phase" to concretize the information obtained, and a "development phase" to shift or organize the topic. In this way, by defining phases according to the purpose of the dialogue based on the instructions of the basic prompt, and going through them cyclically or sequentially, it becomes possible to collect comprehensive and high-quality information.

[0023] <2. Overall System Configuration> Figure 1 is a block diagram showing an example of the overall configuration of System 1. In this disclosure, System 1, which is used for providing an interview article creation service, will be explained using the example of how it is used by an interviewee.

[0024] As shown in Figure 1, this embodiment includes a system 1 comprising, for example, a terminal device 10, a server 20, and a generation AI system 30. In system 1, the terminal device 10, the server 20, and the generation AI system 30 are each connected to each other so as to be able to communicate via a network 80.

[0025] Figure 1 shows an example where System 1 includes one terminal device 10, for the sake of illustration simplification. However, in reality, System 1 may include multiple terminal devices 10 for use by multiple interviewees.

[0026] In Figure 1, System 1 is shown as an example that includes one Server 20, but for example, a collection of multiple devices may be considered as one Server 20. The way in which the multiple functions required to realize Server 20 are distributed to one or more hardware can be appropriately determined according to the processing capacity of each hardware and / or the specifications required for Server 20.

[0027] Figure 1 shows an example where System 1 includes one Generative AI System 30, but System 1 may include two or more Generative AI Systems 30. Also, Figure 1 shows an example where the Generative AI System 30 is independent of Server 20, but Server 20 may include the functions of the Generative AI System 30. In other words, Server 20 may store the LLM included in the Generative AI System 30.

[0028] The terminal device 10 is, for example, an information processing device operated by the interviewee. The terminal device 10 may be implemented as, for example, a mobile device such as a smartphone or tablet, or a stationary PC (Personal Computer), laptop PC, etc. The interviewee accesses the interview article creation service via a dedicated application or web browser installed on the terminal device 10 and interacts with the AI ​​interviewer.

[0029] The terminal device 10 comprises a communication interface 12, an input device 13, an output device 14, memory 15, storage 16, and a processor 19. The input device 13 is a device for receiving input operations from the interviewee (text input of query content, correction instructions, etc.). The output device 14 is a device for presenting information to the interviewee, such as questions from the AI ​​interviewer and generated articles.

[0030] Server 20 is, for example, an information processing device for managing and operating an interview article creation service, and is implemented by a computer connected to the network 80. Server 20 receives requests from terminal devices 10 (for example, instructions to start an interview, or input from the interviewee during a conversation) and controls the sending and receiving of necessary information with the generation AI system 30. Server 20 may also be, for example, an API (Application Programming Interface) server.

[0031] The storage unit 202 of the server 20 (implemented by memory 25 and storage 26) stores data and programs used to provide the interview article creation service. The programs include application programs for providing this service. The storage unit 202 may also store the original or a portion thereof of the basic prompts, records of dialogue sessions for each interviewee, a dialogue technique table 2021, generated articles, etc. The server 20 may, as necessary, provide the generating AI system 30 with a portion of the basic prompts or related contextual information as part of the prompts at the start of the dialogue or at each step of the dialogue.

[0032] As shown in Figure 1, the server 20 includes a communication IF 22, an I / O IF 23, memory 25, storage 26, and a processor 29. The I / O IF 23 functions as an interface for an input device that receives input operations from the administrator of the interview article creation service, and an output device that outputs information to the administrator.

[0033] The generation AI system 30 is, for example, a cloud server that has an LLM. The number of LLMs included in the generation AI system 30 may be one or multiple.

[0034] LLM (Language Modeling) is a single-modal natural language model built by training on large amounts of text data, and is used for many NLG (Natural Language Generation) tasks, such as generating responses to specific questions, automatically generating sentences, and summarizing text. LLM is an example of a generative AI model. Examples of LLMs include the following: • OpenAI: GPT-4 Google: Gemini 1.5 Flash Anthropic:Claude 3.5 Sonnet

[0035] The generating AI system 30 autonomously controls the overall flow of the dialogue (management of dialogue phases, selection of dialogue techniques, determination of termination requirements, etc.), the content of responses (questions to the interviewee, interjections, comments, etc.), and the generation of the final article, based on pre-configured basic prompts. When the server 20 provides a trigger to start the dialogue, input from the interviewee (content of the query), and relevant contextual information as part of the prompts as needed, the generating AI system 30 comprehensively interprets these and its internal basic prompts, generates a response or article corresponding to the next step in the dialogue, and sends it to the server 20.

[0036] The basic prompt contains information about a set of detailed instructions that the generating AI system 30 uses to autonomously control the dialogue. The basic prompt is either pre-configured within the generating AI system 30 or stored in the memory unit 202 of the server 20, and is provided to the generating AI system 30 as part of the prompt at the start of the dialogue or as needed. The basic prompt includes instructions regarding the dynamic selection of dialogue techniques. The basic prompt also includes various instructions for achieving smooth dialogue with the interviewee and creating a high-quality article, and its main components include role instructions, answer generation instructions, reference information specifications, query information specifications, and article output format instructions.

[0037] Role instructions include text that specifies the role (position) and dialogue style that the LLM should take when generating responses. In this embodiment, role instructions are defined, for example, within the basic prompt as follows: "You are an experienced interviewer and writer named '○○'. Aim to connect with the interviewee and bring out their charm and true feelings to the fullest. Also, to foster a sense of familiarity with the interviewee, use friendly Hakata dialect and intersperse emojis appropriately in your dialogue." This specifies an appropriate persona and dialogue style for the AI ​​interviewer. For example, by using friendly dialect and interspersing emojis appropriately, it is possible to create an atmosphere where the interviewee can relax and speak their true feelings.

[0038] The response generation instructions include text that instructs the LLM on what kind of response to generate. In this embodiment, the response generation instructions include, in the basic prompt, instructions for the LLM to analyze the current dialogue situation, autonomously select the most appropriate technique from the defined dialogue technique categories, and generate the next question. For example, the instructions may include: "Consider the current dialogue phase, the content of the query from the interviewee, and the progress of information gathering, refer to the dialogue technique table to determine the most effective dialogue technique, and generate a question based on that." Furthermore, in the article generation stage, the response generation instructions include specific instructions for creating a structured article. For example, the instructions may include: "Summarize the entire dialogue record to date and generate a high-quality interview article according to the specified article structure (title, lead paragraph, and three-chapter body) and word count (approximately 3500 characters)." In addition, in the article revision stage, the response generation instructions may include instructions to reflect feedback from the interviewee, such as: "Analyze the interviewee's revision requests for the presented article, understand their intent, and revise the article accordingly."

[0039] Furthermore, response generation instructions may include guidance for generating the next question by considering not only the content of the interviewee's query but also the emotional state inferred from that query, in the selection of dialogue techniques. For example, if the LLM determines that the interviewee is hesitant or nervous, they may use this guidance to select empathetic dialogue techniques (e.g., expressing emotion such as "That must have been tough") or adjust the frequency of using more friendly emojis, thereby increasing psychological safety and making it easier to elicit honest responses.

[0040] Furthermore, response generation instructions may include instructions for managing the dialogue in multiple phases. For example, instructions such as, "Proceed with the dialogue in the following order: 'listening phase,' 'deepening phase,' 'concretization phase,' and 'development phase.' Only move to the next phase when you determine that the objective of each phase has been achieved," allow the generating AI to manage the overall flow of the dialogue.

[0041] Furthermore, the response generation instructions may include instructions to ensure comprehensive information gathering. For example, instructions such as, "Always refer to the list of information items necessary for article creation, and if there are any missing items, prioritize generating questions to collect them," allow the generating AI to autonomously monitor the degree of information sufficiency.

[0042] The reference information specification includes instructions for using information obtained from the dialogue history, the dialogue technique table 2021, or a placeholder indicating where to insert that information. For example, it could be in the format of "Consider the following dialogue history and the interviewee's previous statement to determine the next dialogue technique to apply: {dialogue history}". Here, the placeholder {dialogue history} will contain all statements between the AI ​​interviewer and the interviewee in chronological order from the start of the interview to the present. This allows the generating AI to generate the next response based not only on the previous statement but also on the overall flow of the dialogue.

[0043] The query information specification includes instructions for the LLM to recognize and use the input query from the interviewee, or a placeholder indicating where to insert the string of that input query. For example, it could be in the form of, "Generate a question using appropriate techniques in response to the following statement from the interviewee, "{Interviewee's input query}." Here, the placeholder {Interviewee's input query} will be replaced with the actual text entered by the interviewee during that turn of dialogue.

[0044] Output format instructions include instructions regarding the output format (template), structure, or style of the responses generated by the LLM. For example, you can instruct the LLM to format responses in a dialogue as JSON and include keys such as "dialogue_act" (dialogue action type, e.g., question, empathy) and "next_technique" (next recommended technique).

[0045] <3. Configuration of terminal equipment> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10. As shown in Figure 2, the terminal device 10 comprises a communication unit 120, an input device 13, an output device 14, an optional voice processing unit 17, a microphone 171, a speaker 172, a camera 160, a location information sensor 150, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus. In this embodiment, the terminal device 10 primarily provides an interface for interviewees to use the interview article creation service.

[0046] The communication unit 120 performs modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and sends it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from the external source and outputs it to the control unit 290. As a result, the content of the query entered by the interviewee or the correction instructions for the article are sent to the server 20, and the questions from the AI ​​interviewer or the generated article are received by the terminal device 10 from the server 20.

[0047] The input device 13 is a device for the interviewee to give instructions or input information while operating the terminal device 10. The input device 13 can be implemented, for example, by a touch panel on which instructions are input by touching the operating surface, or by a keyboard, mouse, etc. The input device 13 converts the instructions input from the interviewee (for example, text input to the AI ​​interviewer, correction instructions for the generated article, etc.) into electrical signals and outputs the electrical signals to the control unit 190.

[0048] The output device 14 is a device for presenting information to the interviewee operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data (for example, questions from the AI ​​interviewer, dialogue content, a preview of the generated article, and correction results) according to the control of the control unit 190.

[0049] The audio processing unit 170 performs, for example, digital-to-analog conversion processing of the audio signal. The microphone 171 receives an audio input and provides the audio signal corresponding to the audio input to the audio processing unit 170. The speaker 172 converts the audio signal provided by the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10. In this embodiment, these audio-related components can be used when the interviewee inputs statements by voice or receives questions from the AI ​​interviewer by voice.

[0050] Camera 160 is a device that receives light using a photodetector and outputs it as a shooting signal. In the interview article creation service of this embodiment, the camera function is not essential, but it can be used if an extended function such as video call-style dialogue is envisioned.

[0051] The location information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. A GPS module is a receiving device used in a satellite positioning system. In a satellite positioning system, signals are received from at least three or four satellites, and the current position of the terminal device 10, which is equipped with a GPS module, is detected based on the received signals. The location information sensor 150 may also detect the current position of the terminal device 10 from the position of the wireless base station to which the terminal device 10 is connected. In the interview article creation service of this embodiment, the location information sensor is not essential, but it can be used, for example, when providing support information according to the region or location.

[0052] The storage unit 180 is implemented, for example, by memory and storage, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, interviewee information, application programs for using the interview article creation service, or configuration information. The interviewee information includes, for example, information for identifying the interviewee using the terminal device 10, and the service usage history (if stored locally).

[0053] The control unit 190 is realized when the processor reads a program stored in the memory unit 180 and executes instructions contained in the program. The control unit 190 controls the operation of the terminal device 10. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193.

[0054] The operation reception unit 191 processes instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 can receive information such as text related to the interviewee's statements or correction instructions for the generated article, which are input from a keyboard or touch panel. The operation reception unit 191 can also receive voice instructions input from the microphone 171.

[0055] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 sends the content of the query and correction instructions entered by the interviewee to the server 20. The transmitting / receiving unit 192 also receives information provided by the server 20 (questions from the AI ​​interviewer, generated article data, etc.).

[0056] The presentation control unit 193 controls the output device 14 to present the information provided by the server 20 to the interviewee. Specifically, for example, the presentation control unit 193 displays various information related to the interview article creation service on the display 141, such as questions from the AI ​​interviewer sent from the server 20, the history of the conversation, the generated article, and the revised article.

[0057] <4. Server Configuration> Figure 3 is a block diagram showing an example of the functional configuration of the server 20 shown in Figure 1. As shown in Figure 3, the server 20 performs the functions of a communication unit 201, a storage unit 202, and a control unit 203.

[0058] The communication unit 201 performs processing to enable the server 20 to communicate with an external device, such as a terminal device 10 or a generation AI system 30.

[0059] The memory unit 202 is implemented by memory and storage and stores data and programs used by the server 20 to provide the interview article creation service. The programs include application programs for providing the interview article creation service. The memory unit 202 also stores, for example, a dialogue technique table 2021, dialogue records for each interviewee, and generated articles.

[0060] The dialogue technique table 2021 stores information on systematized dialogue techniques that the generative AI system 30 references to autonomously control the dialogue. Specifically, it stores information organized for each dialogue technique, such as a "definition" that explains the purpose or overview of each technique, a "category" that classifies the techniques by purpose (e.g., "A. In-depth questioning"), "activation conditions" that indicate the dialogue context or situation to which the technique should be applied, and a "question template" that serves as a template for generating specific questions.

[0061] The control unit 203 is implemented when the processor reads a program stored in the memory unit 202 and executes the instructions contained in that program. The control unit 203 controls the operation of the server 20. By operating according to the loaded program, the control unit 203 can perform the functions of a receive control module 2031, a transmit control module 2032, a service processing module 2033, and an information presentation module 2034.

[0062] The receiving control module 2031 controls the process by which the server 20 receives signals from external devices according to a communication protocol. For example, it receives operational information such as interviewee queries and article modification instructions from the terminal device 10. It also receives responses output from the generation AI system 30 (next question, generated article data, etc.). The received information is passed to other related modules (mainly the service processing module 2033).

[0063] The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices according to a communication protocol. For example, it executes processes such as sending a prompt containing the interviewee's query to the generation AI system 30 based on instructions from the service processing module 2033, and sending a response (question or article data, etc.) from the generation AI system 30 to the terminal device 10 based on instructions from the information presentation module 2034.

[0064] The service processing module 2033 serves as the primary communication interface with the generation AI system 30. Specifically, it formats the interviewee's query or correction instruction received from the terminal device 10 via the receiving control module 2031 as a prompt and inputs it to the generation AI system 30 via the transmission control module 2032. It also acquires the response output from the generation AI system 30 (next question, generated article, instructions regarding dialogue control, etc.) via the receiving control module 2031. The acquired response data is passed to the information presentation module 2034 for processing for output to the terminal device 10 or recorded in the storage unit 202.

[0065] The information presentation module 2034 processes the output content of the generation AI system 30 (questions for the interviewee, generated article, revised article, etc.) received from the service processing module 2033 into a format suitable for the interface used by the interviewee (such as the display 141 of the terminal device 10), and transmits it to the terminal device 10 via the transmission control module 2032 for presentation.

[0066] <5. Data Structure> This section describes the data structures used in System 1. Note that the data structures described are examples only, and data not listed is not excluded. The main data structure used in the interview article creation service in this embodiment is the dialogue technique table 2021.

[0067] Figure 4 shows an example of the data structure of the dialogue technique table 2021 that the AI ​​interviewer refers to when selecting a dialogue technique in this embodiment. This table systematizes the dialogue techniques used by professional interviewers and is referred to by the generating AI system 30 to select and apply the most appropriate technique depending on the situation. The dialogue technique table 2021 shown in Figure 4 has a data structure that associates a technique ID as the key with a category, activation conditions, and question template. The generating AI system 30 may maintain the contents of this dialogue technique table 2021 along with the basic prompts during the dialogue.

[0068] The "Technique ID" field stores identification information to uniquely identify individual dialogue techniques. This identification information is, for example, a unique code combining alphanumeric characters and symbols, and is used by the generating AI system 30 to programmatically refer to, select, and record specific dialogue techniques as execution logs. For example, an ID such as "A-1" might be managed to indicate the first technique belonging to the "A. In-depth" category. This allows the system to track and analyze which dialogue techniques were used, in what situations, and how frequently, contributing to the optimization of dialogue strategies and performance evaluation.

[0069] The "Category" item is a field for storing information to classify dialogue techniques according to their purpose or nature. This classification allows the Generative AI System 30 to select the most appropriate technique from a group of techniques that match the current purpose of the dialogue. For example, "Deep Dive" is a set of techniques aimed at eliciting more detailed information about specific aspects of the interviewee's responses, such as motivation, emotions, behavioral processes, or specific numerical values. "Relationship Building" aims to reduce the psychological distance with the interviewee using means such as praise, empathy, or self-disclosure, and to create an atmosphere that makes it easier to elicit honest and implicit opinions. "Topic Development" aims to make the dialogue more multifaceted and smooth by connecting one topic to another related topic, asking questions from different perspectives, or summarizing and confirming the content of the dialogue. "Concretization" aims to increase the resolution and objectivity of information by asking for specific episodes, examples, or quantitative data in response to abstract statements or general opinions.

[0070] The "Activation Conditions" field stores information that defines the context or situation in which the dialogue technique is deemed appropriate to apply. For example, the interviewee's query, the phase of the dialogue, and the progress of information gathering may be set as conditions.

[0071] The "Question Template" field stores the text template used when generating questions using the dialogue technique in question. The AI ​​generation system 30 uses this template to generate specific questions tailored to the actual dialogue content.

[0072] Furthermore, the storage unit 202 of the server 20 may store an interview data table for managing the records of dialogues and generated articles for each interviewee (not shown). This table may include items such as interview ID, interviewee ID, dialogue record, generated article, and status. The "Dialogue Record" item stores the entire history of statements between the AI ​​interviewer and the interviewee in chronological order. The "Generated Article" item stores the text data (title, lead paragraph, body, etc.) of the article generated by the generation AI system 30. The "Status" item stores the progress of the article (e.g., "Dialogue in progress," "Article generated," "Revising," "Approved") and is used to manage the interactive revision process.

[0073] <6. Operation> The operation of System 1 in this embodiment will now be described. Figure 5 is a flowchart showing an example of the processing flow resulting from the cooperation between Server 20 and Generation AI System 30 in this embodiment. The control unit 203 of Server 20 can perform functions such as a reception control module 2031, a transmission control module 2032, a service processing module 2033, and an information presentation module 2034. In this embodiment, Generation AI System 30 internally holds pre-set basic prompts and has the ability to autonomously control the overall flow of the dialogue, the determination of the end of the dialogue, and article generation and article modification based on these prompts.

[0074] In step S1, when the interviewee operates the application program on the terminal device 10 to instruct the creation of an interview article, the communication unit 120 of the terminal device 10 sends the instruction to the server 20. The receiving control module 2031 of the server 20 receives the instruction sent from the terminal device 10.

[0075] In step S2, the service processing module 2033 of the server 20 inputs a trigger to start the interview to the generating AI system 30. In response, the generating AI system 30 generates the first comment that signals the start of the dialogue, and the server 20 retrieves that comment.

[0076] In step S3, the service processing module 2033 of the server 20 sends the first comment it receives to the interviewee's terminal device 10. The display control unit 193 of the terminal device 10 displays the received comment on the chatbot screen of the application program.

[0077] In step S4, the input of queries from the interviewee and the presentation of responses from the generating AI system 30 are repeated until the end of the dialogue. Specifically, when the interviewee inputs a query from the application program, the server 20 inputs that query to the generating AI system 30. Based on the basic prompt, the generating AI system 30 analyzes the context of the dialogue and autonomously selects the optimal dialogue technique, and uses that technique to generate the next question as a response. The server 20 sends the generated question to the terminal device 10, and the terminal device 10 displays the question on the chatbot screen. This series of dialogue processes is repeated until the generating AI system 30 autonomously determines the end of the dialogue based on the termination conditions defined in the basic prompt. Examples of termination conditions include when all the information items necessary for article creation have been collected, or when a predetermined dialogue time has elapsed.

[0078] In step S5, when the generating AI system 30 determines that the dialogue has ended, it autonomously generates an article based on the entire dialogue record up to that point. The server 20 retrieves the generated article from the generating AI system 30 and sends it to the interviewee's terminal device 10. The presentation control unit 193 of the terminal device 10 displays the received article on the chatbot screen.

[0079] In step S6, when the interviewee inputs instructions for modifying the article from the application program, the service processing module 1033 of the server 20 receives the instructions and inputs them to the generating AI system 30. The generating AI system 30 modifies the article based on the basic prompts and the received instructions, and the server 20 retrieves the modified article.

[0080] In step S7, the server 20 transmits the acquired revised article to the interviewee's terminal device 10. The display control unit 193 of the terminal device 10 displays the received revised article on the display 141.

[0081] In step S4, assuming that the basic prompt contains instructions, the system can not only select a dialogue technique appropriate to the immediate response but also perform higher-level control. For example, to structurally manage the entire dialogue, it can determine the degree of achievement of each phase defined for the purpose of the dialogue and move to the next phase. It can also monitor the completeness of the collected information in real time based on a list of information items necessary for article creation and control the generation of questions to prioritize obtaining missing information.

[0082] Furthermore, the revision process in steps S6 and S7 is not mandatory and is only performed if the interviewee requests revisions or if the basic prompt includes instructions for revising the interview article. Otherwise, this process terminates with the presentation of step S5.

[0083] <7. Screen example> Figures 6 and 7 illustrate examples of the screen of the display 141 of the terminal device 10 in this disclosure. The following screen examples illustrate the creation of a job change experience report as an example of an interview article, but the scope of this disclosure is not limited to this.

[0084] Figure 6 shows an example of a chat-style interface screen in which the interviewee interacts with an AI interviewer using the generation AI system 30. This screen is displayed on the display 141 of the terminal device 10, allowing the interviewee to proceed with the conversation with the AI ​​interviewer.

[0085] Areas 1411, 1413, and 1415 are areas that display questions or comments sent by the AI ​​interviewer (generating AI system 30) to the interviewee. The example in Figure 6 shows how the AI ​​interviewer actively controls the dialogue and extracts information from the interviewee in stages, based on the interview technology system of the present invention. For example, in area 1411, following the greeting to start the dialogue, an open question such as "First, could you tell me what prompted you to start thinking about changing jobs?" is presented to start the listening phase. Next, in response to the interviewee's answer "I want to challenge myself with new technologies," in area 1413, a relationship-building praise and a question to specify are combined to extract more specific information, such as "I see, so you wanted to challenge yourself with new technologies! That's great! What specific technologies were you interested in?" Furthermore, in response to the interviewee's answer "React," in area 1415, a digging technique is used to further explore the motivation, such as "What was it that particularly attracted you to React?" These questions and comments were optimized by the generating AI system 30 based on basic prompts, taking into account the interviewee's statements, the dialogue phase, and the level of information sufficiency.

[0086] Areas 1412 and 1414 are areas that display the responses entered and sent by the interviewee in response to the AI ​​interviewer's questions. In the example in Figure 6, area 1412 displays the interviewee's reason for changing jobs, "In my previous job, I didn't have many opportunities to try new technologies...", and area 1414 displays specific aspirations, such as "I'm interested in web-related technologies. In particular, I wanted to be involved in front-end development using React." These input texts from the interviewee are sent to server 20 and become information for the AI ​​system 30 to generate the next response from the AI ​​interviewer.

[0087] Figure 7 shows an example of an article review screen that, after the interview is completed, presents the interviewee with an automatically generated article based on the content of the conversation and prompts them to review and revise it. This screen is displayed on the display 141 of the terminal device 10, allowing the interviewee to review a preview of the generated article and provide revision instructions as needed.

[0088] At the top of the screen shown in Figure 7, introductory text indicating the purpose of the screen may be displayed, such as, "Thank you for your hard work during the interview! We have created an article based on what you told us, so please take a look." Below that, the various elements of the generated article are displayed.

[0089] Area 1416 displays the "title" of the generated article. Area 1417 displays the "lead paragraph," which is a summary of the entire article. Area 1418 displays the "body" of the article, which includes specific episodes and statements obtained during the dialogue. This article content is generated by the generation AI system 30 based on instructions from server 20, after analyzing the entire record of the dialogue.

[0090] Area 1419 is a chat input field where the interviewee can enter revision instructions for the article. The interviewee reads the article content displayed in areas 1416 to 1418, and if there are any points they would like to revise, they can enter instructions in natural language in this input field (e.g., "Please change the title from 'Challenge' to 'New Career'," "Please soften the wording in the third paragraph") and submit it. Server 20 receives these revision instructions, has the generation AI system 30 revise the article, and then presents the revised article on this screen again. This interactive process allows for the efficient completion of an article that accurately reflects the interviewee's intentions.

[0091] <8.Summary> As described above, in System 1, Server 20 first initiates a dialogue with the interviewee based on basic prompts, instructing the Generating AI System 30 to start a conversation. Next, during the dialogue, Server 20 causes the Generating AI System 30 to autonomously select a dialogue technique appropriate to the situation and generate questions to elicit useful information, based on the dialogue history with the interviewee and the previous query from the interviewee. When the dialogue meets predetermined termination requirements, Server 20 causes the Generating AI System 30 to generate a structured article based on the entire record of the dialogue up to that point, and presents it to the interviewee. In this way, by using dialogue control that systematizes the techniques of professional interviewers, it is possible to efficiently elicit genuine opinions or specific episodes from the interviewee and improve the quality of the article.

[0092] [Differentiation] Although embodiments of the present disclosure have been described above, the present disclosure is not limited to the embodiments described above, and various modifications are possible without departing from its essence.

[0093] For example, in the above embodiment, the interviewee was described as communicating via text chat, but this is not the only option. The interviewee may input voice using the microphone 171 provided by the terminal device 10, and the voice may be converted into text through speech recognition processing. Conversely, the questions generated by the generation AI system 30 can be synthesized into speech and output as voice from the speaker 172 of the terminal device 10.

[0094] Furthermore, although the above embodiment describes an example of configuration as a client-server system, the system configuration is not limited to this. For example, it is also possible to install the generated AI model on the terminal device 10 and implement it as a standalone application.

[0095] Furthermore, the technology disclosed herein can be applied to a variety of dialogue scenarios, not just to creating interview articles such as job change experience stories. For example, it can be used in various situations where specialized knowledge and dialogue skills are required, such as creating employee profiles in the recruitment and human resources field, creating articles on customer success stories and user research in the marketing field, and creating articles based on interviews with experts in the news and media field. In such cases, the content of the basic prompts and dialogue techniques will be customized according to the respective purpose.

[0096] <Basic Computer Hardware Configuration> Figure 8 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 includes at least a processor 901, main memory 902, auxiliary memory 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0097] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0098] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0099] Auxiliary storage device 903 refers to a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0100] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0101] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0102] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 8) will be explained. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0103] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0104] The control unit is realized when the processor 901 reads various programs stored in the auxiliary storage device 903, loads them into the main memory device 902, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0105] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0106] A database, specifically a relational database, is used to manage and link together tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs. Furthermore, by storing data, various programs, and various databases in the memory unit, the information processing device and information processing system related to this disclosure can be considered to have been manufactured.

[0107] Furthermore, the databases and masters in this disclosure may include any data structures (lists, dictionaries, associative arrays, objects, etc.) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc., written in any programming language.

[0108] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0109] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0110] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0111] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0112] The functions realized by the components described herein may be implemented in a circuit or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor is considered to be a circuit or processing circuitry, including transistors and other circuits. A processor may be a programmed processor that executes a program stored in memory. In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein. If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0113] While several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications are permitted without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0114] (Note) The details described in each of the above embodiments are noted below.

[0115] (Note 1) A program for operating a computer that includes a processor and memory, The program is provided to the processor: The process involves a step of inputting a basic prompt into the generating AI, which includes instructions for the generating AI to autonomously select a dialogue technique from among several predefined dialogue techniques, based on the context of the dialogue, including the dialogue history with the interviewee and queries from the interviewee. The process involves, in response to a query from the interviewee, having the generating AI generate the next question using a dialogue technique selected with the basic prompt, and presenting the generated next question to the interviewee, repeating this series of dialogue processes until a predetermined termination condition is met. After the dialogue ends, the process involves having the generating AI generate an article based on the dialogue history and the basic prompts, The steps include presenting the generated article to the interviewee, A program that executes something. (Note 2) The aforementioned dialogue techniques are categorized according to at least one of the following: the purpose of the dialogue, which indicates what is to be achieved through the interview, and the nature of the dialogue, which indicates how the interviewee is speaking, as described in (Appendix 1). (Note 3) The basic prompt includes instructions for managing the dialogue in multiple phases defined for each dialogue objective indicating what to achieve through the interview, The program described in (Appendix 1) or (Appendix 2), which includes, in the step of repeating the dialogue processing, causing the generating AI to manage the dialogue while moving to the next phase based on the degree of achievement of the objectives of each phase. (Note 4) The aforementioned basic prompt includes instructions for monitoring information completeness, indicating whether the necessary information items for article creation have been collected. The program according to any one of (Appendix 1) to (Appendix 3), which includes, in the step of repeating the dialogue processing, causing the generating AI to monitor the degree of information sufficiency and, if the degree of information sufficiency does not meet a predetermined standard, to generate additional questions to supplement the missing information. (Note 5) The aforementioned basic prompt includes instructions for conducting a conversation using at least one of a specific regional dialect and emojis. The program according to any one of (Appendix 1) to (Appendix 4), wherein in the step of repeating the dialogue processing, the generating AI engages in dialogue using at least one of a specific regional dialect and emojis. (Note 6) The basic prompt includes instructions for selecting the dialogue technique based on the emotional state of the interviewee, as analyzed from the context of the dialogue. The program according to any one of (Appendix 1) to (Appendix 5), wherein in the step of selecting the dialogue technique, the generating AI selects the dialogue technique based on the emotional state of the interviewee analyzed from the context of the dialogue. (Note 7) The aforementioned basic prompt includes instructions for generating a structured article that includes a title, a lead paragraph, and multiple sections. A program according to any one of (Appendix 1) to (Appendix 6), which in the step of generating the aforementioned article includes causing the generation AI to generate the structured article. (Note 8) The aforementioned basic prompt includes instructions for revising the article based on revision requests from the interviewee regarding the presented article. The program according to any one of (Appendix 1) to (Appendix 7), which causes the processor to receive the correction instruction, to have the generating AI correct the article based on the basic prompt and the correction instruction, and to further execute the steps of presenting the corrected article to the interviewee. (Note 9) An information processing apparatus comprising a processor and memory, wherein the processor executes all steps in any of the programs described in (Appendix 1) to (Appendix 8). (Note 10) A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps in any of the programs described in (Appendix 1) to (Appendix 8). (Note 11) A system comprising means for executing all steps in any of the programs described in (Appendix 1) to (Appendix 8). [Explanation of symbols]

[0116] 1... System 10…Terminal device 12…Communication IF 13…Input device 14…Output device 15…Memory 16…Storage 19… Processor 20... Server 22...Communication IF 23…Input / Output Interface 25…Memory 2 hours… storage 29… Processor 30…Generative AI System 80…Network

Claims

1. A program for operating a computer that includes a processor and memory, The program is provided to the processor: The process involves analyzing the dialogue history with the interviewee and the context of the dialogue, including the most recent query from the interviewee, determining whether to move to the next dialogue phase or maintain the current dialogue phase from among several predefined dialogue phases, and inputting a basic prompt into the generating AI that instructs the generating AI to autonomously select a dialogue technique from among several predefined dialogue techniques, taking into account the determined dialogue phase. The process involves, in response to a query from the interviewee, having the generating AI generate the next question using a dialogue technique selected with the basic prompt, and presenting the generated next question to the interviewee, repeating this series of dialogue processes until a predetermined termination condition is met. After the dialogue ends, the process involves having the generating AI generate an article based on the dialogue history and the basic prompts, A program that performs the steps of presenting the generated article to the interviewee.

2. The program according to claim 1, wherein the dialogue techniques are categorized according to at least one of the objective of the dialogue, which indicates what is to be achieved through the interview, and the nature of the dialogue, which indicates how the interviewee is speaking.

3. The aforementioned basic prompt includes instructions for monitoring information completeness, indicating whether the necessary information items for article creation have been collected. The program according to claim 1, wherein in the step of repeating the dialogue processing, the generating AI is instructed to monitor the degree of information sufficiency, and if the degree of information sufficiency does not meet a predetermined standard, it is instructed to generate additional questions to supplement the missing information.

4. The aforementioned basic prompt includes instructions for conducting a conversation using at least one of a specific regional dialect and emojis. The program according to claim 1, wherein in the step of repeating the dialogue processing, the program includes having a dialogue with the generating AI using at least one of a specific regional dialect and emojis.

5. The basic prompt includes instructions for selecting the dialogue technique based on the emotional state of the interviewee, as analyzed from the context of the dialogue. The program according to claim 1, wherein in the step of selecting the dialogue technique, the generating AI is instructed to select the dialogue technique based on the emotional state of the interviewee, which is analyzed from the context of the dialogue.

6. The aforementioned basic prompt includes instructions for generating a structured article that includes a title, a lead paragraph, and multiple sections. The program according to claim 1, wherein the step of generating the article includes causing the generation AI to generate the structured article.

7. The aforementioned basic prompt includes instructions for revising the article based on revision requests from the interviewee regarding the presented article. The program according to claim 1, further comprising the steps of causing the processor to receive the correction instruction, to cause the generating AI to correct the article based on the basic prompt and the correction instruction, and to present the corrected article to the interviewee.

8. An information processing apparatus comprising a processor and memory, wherein the processor executes all steps in the program described in any one of claims 1 to 7.

9. A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps of a program according to any one of claims 1 to 7.

10. A system comprising means for performing all steps in a program according to any one of claims 1 to 7.

Images