Information processing systems and programs

Abstract

This system and program provides an information processing system that generates questions based on user responses and allows for deeper analysis of the acquired information. [Solution] The control means 20 comprises a user terminal communication unit 30, a generation AI system communication unit 31, a prompt generation unit 32, and an information output unit 33. The prompt generation unit 32 generates an instruction prompt that includes a question generation instruction to generate additional questions based on basic questions and their answers. After the additional questions are answered, the prompt generation unit 32 generates an instruction prompt that includes a question generation instruction to generate additional questions based on the questions sent to the user terminal 12 and the answers received from the user terminal 12, and an instruction to generate target information based on the acquired information, and outputs the target information if the accuracy of the context information is above a certain level. The information output unit 33 outputs the target information if the information from the generation AI system 15 includes the target information.

Description

Technical Field

[0001] The present invention relates to an information processing system and a program that perform step-by-step hearings using a generative AI system.

Background Art

[0002] In recent years, services that generate text in an interactive format with users have been provided by generative AI systems using large language models (LLMs). Many such services using generative AI systems are provided. For example, Patent Document 1 discloses a system that generates information (prompt) to be input into a generative AI system without the user's intervention, transmits the prompt to the generative AI system, obtains the generated information, and provides it to the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When considering an information processing system that organizes information using a generative AI system and makes proposals based on the organized information, the information processing system needs to widely and deeply acquire the context (background and situation) of the target information. For this purpose, the information processing system needs to perform step-by-step hearings with the user and dig deeper into the acquired information.

[0005] To conduct a phased interview, it is necessary to prepare a set of questions tailored to the objective in advance. However, to elicit sufficient information from the user, it is necessary to modify the questions based on the user's answers, rather than just using a set set of questions. For this reason, one might consider preparing questions based on the answers, but this would result in an enormous number of questions, which is not practical.

[0006] This invention has been made in view of the above-mentioned problems, and aims to provide an information processing system and program that can generate questions in accordance with the user's answers and gradually improve the accuracy of the acquired information. [Means for solving the problem]

[0007] To solve the aforementioned problems, the information processing system according to the present invention is an information processing system that acquires contextual information through questions to a user and outputs target information based on the contextual information, comprising control means and storage means, wherein the storage means stores basic questions in advance, the control means comprises a user terminal communication unit that sends and receives information to and from a user terminal used by the user, a generation AI system communication unit that sends and receives information to and from a generation AI system, a prompt generation unit that generates instruction prompts for the generation AI system, and an information output unit that outputs the target information in a certain format, wherein the user terminal communication unit sends the basic questions to the user terminal and receives answers corresponding to the basic questions, and the prompt generation unit issues a question generation instruction to cause the generation AI system to generate additional questions based on the contextual information consisting of the basic questions and the answers corresponding to the basic questions. The prompt generation unit generates an instruction prompt including the following: the generation AI system communication unit generates the instruction prompt and transmits the instruction prompt to the generation AI system and receives the generated additional questions; the user terminal communication unit transmits the additional questions to the user terminal and receives the answers corresponding to the additional questions; the prompt generation unit generates an instruction prompt including a question generation instruction that causes the generation AI system to generate additional questions based on the context information consisting of the questions transmitted to the user terminal and the answers received from the user terminal; and a target information generation instruction that causes the target information to be generated based on the acquired context information, and enables the output of the target information if the accuracy of the context information is above a certain level; and the information output unit outputs the target information if the information from the generation AI system received by the generation AI system communication unit includes the target information or information indicating that the target information has become outputtable.

[0008] Furthermore, in the information processing system according to the present invention, the prompt generation unit includes an instruction in the question generation instruction to cause the generation AI system to generate a plurality of options that serve as answers to the additional questions.

[0009] Furthermore, the information processing system according to the present invention includes an instruction in the prompt generation unit to determine that the accuracy of the context information is above a certain level when the number of items included in the generated target information is above a certain level.

[0010] Furthermore, the information processing system according to the present invention includes an instruction in the prompt generation unit in the objective information generation instruction that determines the accuracy of the context information to be above a certain level regardless of the number of items included in the objective information, if the number of additional questions already generated is above a certain level.

[0011] Furthermore, in the information processing system according to the present invention, the user terminal communication unit receives a file containing information transmitted from the user terminal, and the prompt generation unit analyzes the file and generates the instruction prompt as part of the context information.

[0012] Furthermore, in the information processing system according to the present invention, the information output unit causes the generating AI system to generate objective information in a certain format based on the context information via the generating AI system communication unit, and outputs the objective information.

[0013] To solve the aforementioned problems, the present invention provides a program that acquires contextual information through questions to a user and creates objective information based on the contextual information, wherein the program causes a computer to execute a user terminal communication process that sends and receives information with a user terminal used by the user, a generation AI system communication process that sends and receives information with a generation AI system, a prompt generation process that generates instruction prompts for the generation AI system, and an information output process that outputs the objective information in a certain format, wherein the user terminal communication process generates an instruction prompt that includes a question generation instruction to cause the generation AI system to generate additional questions based on the contextual information consisting of pre-stored basic questions and the answers corresponding to the basic questions, and the prompt generation process generates an instruction prompt that includes a question generation instruction to cause the generation AI system to generate additional questions, The system generates an instruction prompt using the question and the corresponding answer as context information; in the generation AI system communication process, it transmits the instruction prompt to the generation AI system and receives the generated additional question; in the user terminal communication process, it transmits the additional question to the user terminal and receives the corresponding answer; in the prompt generation process, it generates an instruction prompt including a question generation instruction that causes the generation AI system to generate additional question based on the context information consisting of the question transmitted to the user terminal and the answer received from the user terminal, and a target information generation instruction that causes the target information to be generated based on the acquired context information, and enables the output of the target information if the accuracy of the context information is above a certain level. In the information output process, if the information received from the generating AI system in the generating AI system communication process includes the target information or information indicating that the target information has become available for output, the target information is output. [Effects of the Invention]

[0014] According to the information processing system and program of the present invention, additional questions can be generated in response to the user's answers to the questions, and the user can be asked to answer them. This makes it possible to generate target information while gradually improving the accuracy of the acquired information. [Brief explanation of the drawing]

[0015] [Figure 1] This diagram shows the configuration of the information processing system according to this embodiment. [Figure 2] A detailed diagram of the control system is shown. [Figure 3] This is a flowchart in an information processing system. [Figure 4] This is an example of a screen displaying basic questions on a user's terminal. [Figure 5] This is an example of a screen displaying additional questions on the user's terminal. [Modes for carrying out the invention]

[0016] Embodiments of the present invention will be described in detail with reference to the drawings. First, a first embodiment of the information processing system 10 will be described. The information processing system 10 is a system that acquires contextual information through questions to the user and creates objective information based on this contextual information. The objective information of this information processing system 10 is information that proposes ways to utilize the generation AI system for users who do not use it or are not fully utilizing it in their work. To this end, the information processing system 10 asks questions about the user's work, and based on the answers obtained from the user, asks further questions to gradually enrich the contextual information and thereby improve the accuracy of the objective information.

[0017] The information processing system 10 utilizes a generative AI system 15 equipped with a large language model (LLM) for generating additional questions and target information. An LLM (Large Language Model) is a language model constructed using a large amount of text data and deep learning techniques. As a result, the generative AI system 15 can perform natural language processing and enable natural conversations and text generation similar to that of humans. The generative AI system 15 can receive prompts from the information processing system 10 and transmit corresponding AI output information.

[0018] As shown in FIG. 1, the information processing system 10 can be connected to a plurality of user terminals 12 via a communication network 16. Thus, the information processing system 10 can be used by multiple users logging in. Each user terminal 12 has display means 13 such as a monitor. The user terminal 12 is a computer such as a PC or a mobile information terminal such as a smartphone. However, the user terminal 12 is not limited to these.

[0019] The information processing system 10 can be connected to the generative AI system 15 via the communication network 16. In FIG. 1, the information processing system 10 is connected to one generative AI system 15, but the information processing system 10 may utilize multiple generative AI systems 15 as needed. Also, the information processing system 10 itself may include the generative AI system 15. In this embodiment, the exchange of information between the information processing system 10 and the generative AI system 15 is performed by sending and receiving information. However, when the information processing system 10 includes the generative AI system 15, it is assumed that information is communicated within the system.

[0020] In FIG. 1, the information processing system 10 is connected to the plurality of user terminals 12 and the generative AI system 15 via a single communication network 16, but the information processing system 10 may be connected to the user terminal 12 and the generative AI system 15 via separate communication networks, respectively. For example, the information processing system 10 can be connected to the user terminal 12 via an in-house LAN and connected to the generative AI system 15 via the Internet.

[0021] The information processing system 10 can be composed of a computer such as a server. The information processing system 10 includes at least a control means 20, a storage means 21, and a communication means 22. The control means 20 can be composed of a processor such as a CPU. The storage means 21 can be configured using, for example, RAM, DRAM, HDD, SSD, or external cloud or distributed storage. The communication means 22 can be configured using, for example, a NIC or a wireless LAN connection device.

[0022] As shown in FIG. 2, the control means 20 includes a user terminal communication unit 30 that transmits and receives information to and from the user terminal 12, a generation AI system communication unit 31 that transmits and receives information to and from the generation AI system 15, a prompt generation unit 32 that generates an instruction prompt, an information output unit 33 that outputs target information in a certain format, and a file analysis unit 34 that analyzes the content of the file transmitted from the user terminal 12.

[0023] The storage means 21 stores basic question items in advance. The basic question items are basic question items in line with the purpose of the information processing system 10. Since the information processing system 10 of the present embodiment proposes a method for utilizing a generation AI system related to business, the basic question items are those that inquire about basic matters related to the user's business.

[0024] The user terminal communication unit 30 of the control means 20 transmits the basic question items and additional question items to be generated later to the user terminal 12 and receives the answers input by the user. Also, the user terminal communication unit 30 receives a file including the information transmitted from the user terminal 12.

[0025] The prompt generation unit 32 of the control means 20 generates an instruction prompt that includes a question generation instruction that causes the AI ​​system 15 to generate additional questions based on context information obtained from the user, and a target information generation instruction that causes the AI ​​system 15 to generate target information once the context information obtained from the user reaches a certain level of accuracy.

[0026] The generation AI system communication unit 31 of the control means 20 sends an instruction prompt to the generation AI system 15 and receives the generated additional questions or objective information.

[0027] The information analysis unit 34 of the control means 20 analyzes the contents of a file sent from the user terminal 12 to obtain information. The information analysis unit 34 can also scrape information from a website using the URL of the website sent from the user terminal 12.

[0028] Next, we will describe the flow in which the information processing system 10 acquires contextual information and creates target information. As shown in Figure 3, the user terminal communication unit 30 reads basic questions from the storage means 21 and transmits them to the user terminal 12 (S1). The basic questions for proposing how to utilize the generation AI system related to business are items for understanding the overall picture of the user's business, and include questions such as the department (department name) to which the user belongs, an overview of the work, the role assigned to the individual, and goals.

[0029] The user enters answers to basic questions on the user terminal 12 (S2). As shown in Figure 4, the display means 13 of the user terminal 12 displays a question display area 40 where the questions are displayed, an answer input area 41 where answers can be entered, and an upload area 42 where files can be sent to the information processing system 10 by dragging and dropping them. A button 43 for moving to the next question is also displayed at the bottom of the display means 13. When the user enters an answer and presses button 43, the answer to the questions is sent from the user terminal 12 to the information processing system 10. If the user has dragged and dropped a file into the file upload area 42, the file is also sent to the information processing system 10.

[0030] The user terminal communication unit 30 receives the answers to the basic questions sent from the user terminal 12 (S3). If a file has been sent from the user terminal 12, the user terminal communication unit 30 also receives the file. This file is then analyzed by the information analysis unit 34.

[0031] Next, the prompt generation unit 32 generates an instruction prompt based on the received information (S4). The instruction prompt includes a question generation instruction and an objective information generation instruction, as described above. The instruction prompt clearly states the purpose of the information to be generated. For example, the instruction prompt may state the purpose as follows: "Your objective is to collect detailed information about the user's work through a series of questions and ultimately propose how to utilize the generated AI in the user's work."

[0032] The instruction prompt's question generation instruction uses basic questions and their corresponding answers as initial information, and based on this initial information, instructs the system to create useful additional questions to comprehensively understand the work content and challenges. If a file has been sent from the user terminal 12, the initial information includes information analyzed by the information analysis unit 34. The question generation instruction also specifies guidelines for creating additional questions. These guidelines include, for example, asking specific and easy-to-answer questions, using the provided information to ask relevant follow-up questions, and utilizing metacognition to create diverse questions from multiple perspectives to explore the user's work from various angles.

[0033] The question generation instructions also include instructions for creating answer choices for additional questions. For this purpose, the instructions may include statements such as, "For each question, create three possible answer examples, representing the most typical answer based on the provided information. The answer examples should be simple and concise." By generating multiple answer choices for additional questions, the system allows users to answer these questions by presenting options, eliminating the need to manually type text and facilitating information gathering. Furthermore, when answering additional questions, users can also enter their own answers in text, in addition to the generated options.

[0034] The question generation instructions include prompting the generating AI system 15 to consider the following items: (1) a summary of the current information, (2) areas where the information is lacking, (3) potential applications of the generating AI, (4) an assessment of the progress of information gathering, and (5) planning for the next question. The question generation instructions also include additional guidelines for generating questions. These additional guidelines include instructions on how to ask questions, such as the number of questions and avoiding repeating similar questions.

[0035] The instruction prompt includes an instruction to generate objective information, which generates objective information based on the acquired contextual information and outputs the objective information if the accuracy of the contextual information is above a certain level. In order to generate objective information, the instruction to generate objective information includes an instruction to output a summary of important insights obtained from the consideration items, for example, once it is determined that sufficient information has been collected to make a proposal. The instruction to generate objective information includes an instruction to output the objective information, which is considered to be above a certain level of accuracy of the acquired contextual information, once the generation AI system 15 has been able to generate a predetermined number of proposal items based on the consideration instructions in the question generation instruction. Furthermore, regarding the determination of the accuracy of the contextual information, the instruction to generate objective information may also include an instruction to output the objective information, which is considered to be above a certain level of accuracy of the contextual information, regardless of the number of proposal items, if the number of additional questions already generated is above a certain level.

[0036] The instruction prompt instructs the system to output the target information only if the context information is accurate enough. Therefore, the generating AI system 15 outputs additional questions if the context information is not accurate enough, and outputs the target information if the context information is accurate enough.

[0037] The user terminal 12 may be configured to allow the user to immediately output the target information. In this case, the instruction prompt generated by the prompt generation unit 32 includes an instruction to the generation AI system 15 to output the generated target information regardless of the accuracy of the context information.

[0038] Once an instruction prompt is generated, the generating AI system communication unit 31 sends the instruction prompt to the generating AI system 15 (S5) and receives additional questions or objective information generated by the generating AI system 15 (S6).

[0039] Examples of additional questions and answer choices generated by the AI ​​system 15 using the information processing system 10 of this embodiment are given below. (Additional questions) In your PM (Project Management) work, what specific tasks take the most time or feel the most burdensome? (Options) 1. Creating and updating project plans and status reports. 2. Coordinating communication between teams and creating meeting minutes. 3. Documenting risk management and issues, and considering countermeasures. (Additional questions) What process do you use for gathering information and generating ideas when planning and developing new services? (Options) 1. Analysis of market research reports and benchmarking of competing services 2. Conducting internal brainstorming sessions and customer interviews. 3. Analysis of industry trends and research on user needs (Additional questions) What types of documents are most commonly created when making proposals to clients, and what challenges do you face in creating them? (Options) 1. Creating proposals and quotations takes time and requires customization. 2. Creating technical specifications and preparing explanatory materials is cumbersome. 3. It is difficult to search for and reuse past examples of similar cases.

[0040] If the information received in S6 is the target information (S7), the information output unit 33 outputs the target information (S8). If the information received in S6 is an additional question (S7), the user terminal communication unit 30 sends the additional question to the user terminal 12 (S9). The information generated by the generation AI system 15 includes options for the additional question, and the user terminal communication unit 30 sends the information of the options along with the additional question to the user terminal 12.

[0041] As shown in Figure 5, the display means 13 of the user terminal 12 displays multiple options 51 below the question display area 50 where additional questions are displayed. Also, a button 53 for moving to the next question is displayed at the bottom of the display means 13. The user can move to the next additional question by selecting one or more of the options 51, entering an arbitrary answer if other options are selected, and pressing the button 53. Information of the options selected by the user or the answer entered is transmitted from the user terminal 12 to the information processing system 10 (S10).

[0042] The user terminal communication unit 30 receives information on the answers to the additional questions from the user terminal 12 (S11). The steps from S4 are repeated using the information on the additional questions and the answers to those additional questions as context information. If the generating AI system 15 determines that the context information is sufficiently accurate, the generating AI system 15 transmits the target information, and in S8, the information output unit 33 outputs the target information.

[0043] The objective information generated by the generation AI system 15 includes information such as a summary of contextual information, identified issues, proposed uses and effects of the generation AI system based on the collected information, and priorities. The information output unit 33 outputs the objective information from the generation AI system 15 in a fixed format. In this embodiment, the information proposing how to utilize the generation AI system 15 is output, for example, as follows. Proposal 1: Transportation expense application check support system - Automatically checks the validity of the requested route and amount. - Detection of unnatural routes or amounts - Automatic generation of check result reports Proposal 2: Labor Compliance Checker - Automatic detection of legal violation risks in attendance data - Detection of signs of violation of Article 36 Agreement - Automatic generation of monthly reports on legal compliance status Proposal 3: Support for creating event-related documents - Generating a proposal template - Drafting the email for the event announcement. - Support for designing survey forms Proposal 4: Automated FAQ response system for internal use - Automated response to general application procedure questions - Presenting answer candidates that have learned from past answer history. - Sorting and prioritizing new inquiries Proposal 5: Event Management Efficiency Assistant - Automatic creation of management sheet for supplies and lunch orders - Proposal to optimize order quantities based on the number of participants - Automatic generation of time schedules Proposal 6: Attendance Anomaly Detection System - Automatic detection of missed time stamps and input errors - Detection of anomalies in work patterns - Determining and notifying the confirmation priority

[0044] The target information is transmitted from the user terminal communication unit 30 to the user terminal 12, and multiple suggestions like the ones described above are displayed on the user terminal 12. The user can select one or more of these suggestions and send them to the information processing system 10. The information processing system 10 can then have the generation AI system 15 generate more specific instructions for utilizing the generation AI system regarding the suggestions selected by the user, and send these instructions to the user terminal 12.

[0045] Regarding the objective information, the information output unit 33 may output objective information compiled in a certain format. In this case, the information output unit 33 causes the generating AI system 14 to generate objective information compiled in a certain format from the generating AI system communication unit 31, and receives and outputs this objective information. Alternatively, in this case, in S6, the information processing system 10 may receive information from the generating AI system 15 indicating that the objective information has become ready for output, rather than the objective information itself. Based on this information, the information processing system 10 determines in S7 that the objective information has become ready for output, and in S8, the information output unit 33 causes the generating AI system 15 to generate the objective information and outputs it.

[0046] Next, a second embodiment of the information processing system 10 will be described. In this embodiment, the target information of the information processing system 10 is data referenced by the RAG (Retrieval-Augmented Generation) system (hereinafter referred to as RAG data). In order to create RAG data, the information processing system 10 confirms the target and the information that forms the basis of the RAG data from the user, and based on the answers, asks further questions to deepen the contextual information, thereby increasing the accuracy of the target information.

[0047] The configuration of the information processing system 10 is the same as that of the first embodiment shown in Figures 1 and 2. The operation flow is also the same as that of the first embodiment shown in Figure 3, in which, first, basic questions are sent from the user terminal communication unit 30 to the user terminal 12 (S1). The basic questions in this embodiment are questions to (1) confirm the purpose and (2) confirm the prescribed documents and basic information. In confirming the purpose, questions are asked to confirm the main use of the RAG data and the users of the RAG system (for example, internal or external customers). In confirming the prescribed documents and basic information, questions are asked for the purpose of data input to create RAG data, such as uploading document files such as internal documents and manuals, entering URLs of websites, or the user directly entering information as text.

[0048] Basic questions are sent to the user terminal 12, the user inputs information (S2), and when the user terminal communication unit 30 receives this information (S3), the prompt generation unit 32 generates an instruction prompt that includes a question generation instruction and a target information generation instruction (S4). At this time, the information analysis unit 34 analyzes the file sent from the user terminal 12 to obtain information. The information analysis unit 34 also obtains information from the URL of the website sent from the user terminal 12 by web scraping. Using the basic questions, the answers to them, and the information obtained by the information analysis unit 34 as context information, the prompt generation unit 32 generates an instruction to create additional questions in the question generation instruction.

[0049] The purpose of the information to be generated, as explicitly stated in the instruction prompt, is "to gather comprehensive information through a series of questions based on the initial information provided by the user." The instruction prompt includes instructions to analyze the purpose and basic information, which are answers to the initial questions, and to create additional questions to gather more comprehensive information about potential data sources.

[0050] The instruction prompt's question generation instructions provide the following steps for generating additional questions: (1) analyze the initial information and the user's subsequent responses, (2) create up to three additional questions, (3) provide three example answers for each question, and (4) wait for the user's response before generating the next question. The question generation instructions also provide points to keep in mind when generating additional questions, such as focusing on data collection and organization rather than the implementation of the RAG system, deepening the understanding of existing information, and making questions specific and easy to answer.

[0051] Question generation instructions include prompting the generating AI system 15 to consider the following items: (1) summarizing key points, (2) identifying key themes and topics, (3) classifying and evaluating potential data sources, (4) information gaps and ambiguities, (5) new perspectives to explore, (6) rationale for new questions, (7) data organization considerations, and (8) suitability of text analysis and topic modeling. Instruction prompts also include instructions to continue the analysis, question generation, and user response waiting process until comprehensive information about potential data sources for the RAG system is gathered.

[0052] The instruction prompt includes an instruction to generate target information, which generates target information based on the acquired context information and outputs the target information if the accuracy of the context information is above a certain level. In this embodiment, the target information is output as text data that can be referenced by the RAG system. When a user inputs a question, the RAG system extracts the intent and keywords of the question through text analysis, and identifies which topic the question belongs to in the topic classification master information based on the extracted keywords and context information. Furthermore, the RAG system searches for and retrieves data sources related to the identified topic, and generates an answer and responds to the user based on the retrieved information. In this embodiment, the target information includes the topic classification master information and data sources used by the RAG system. Whether the accuracy of the context information is above a certain level can be determined by the generation AI system 15 based on whether the number or volume of items in the topic classification master information and data sources, which are the target information, is above a certain level, or whether the number of additional questions to be generated has reached the upper limit.

[0053] The operation of the information processing system 10 after the prompt generation unit 32 generates an instruction prompt (S5-S7, S9-S11 in Figure 3) is the same as in the first embodiment, so a description will be omitted.

[0054] In the second embodiment, when information is output in S8, the information output unit 33 causes the generating AI system 15 to generate target information by summarizing the context information in a certain format via the generating AI system communication unit 31. In this embodiment, since the information ultimately generated is RAG data, the context information is summarized in the generating AI system 15 into a format that can be recognized by the RAG system to generate the target information. For this purpose, the prompt generation unit 32 generates prompts that include instructions to format and classify the context information, consisting of questions and answers accumulated up to that point, into content suitable for text analysis and topic modeling, and to construct a data source, so that it can be used by the RAG system. The target information generated by the generating AI system 15 is output from the information output unit 33.

[0055] Furthermore, the program used in the information processing system 10 of this embodiment can also be provided independently. In this case, the program executes user terminal communication processing for sending and receiving information with the user terminal 12 used by the user, generation AI system communication processing for sending and receiving information with the generation AI system 15, prompt generation processing for generating instruction prompts for the generation AI system 15, and information output processing for outputting target information in a fixed format. In the user terminal communication processing, an instruction prompt is generated that includes a question generation instruction to cause the generation AI system 15 to generate additional questions, based on context information consisting of pre-stored basic questions and corresponding answers. In the prompt generation processing, an instruction prompt is generated using the basic questions and corresponding answers as context information. In the generation AI system communication processing, the instruction prompt is sent to the generation AI system 15 and the generated additional questions are received. In the user terminal communication processing, the additional questions are sent to the user terminal 12 and the corresponding answers are received. In the prompt generation process, a prompt is generated that includes a question generation instruction that causes the generation AI system 15 to generate additional questions based on context information consisting of the questions sent to the user terminal 12 and the answers received from the user terminal 12, and a target information generation instruction that causes the target information to be generated based on the acquired context information, and enables the output of the target information if the accuracy of the context information is above a certain level. In the information output process, if the information received from the generation AI system 15 in the generation AI system communication process includes the target information or information indicating that the target information is ready to be output, the target information is output.

[0056] Although embodiments of the present invention have been described above, the application of the present invention is not limited to these embodiments and can be applied in various ways within the scope of its technical concept. In this embodiment, the target information is the method of utilizing the generation AI system and RAG data, but questions may be set and generated using other information as the target information. For example, a resume required by a job seeker can be used as the target information. Furthermore, other information may also be used as the target information. [Explanation of symbols]

[0057] 10 Information Processing Systems 12 user terminals 13 Display means 15. Generating AI System 16. Communication Networks 20 Control means 21 Memory means 22 Means of communication 30 User Terminal Communication Unit 31. Generation AI System Communication Department 32 Prompt generation unit 33 Information Output Unit 34 Information Analysis Department 40 Question display area 41 Answer input area 42 Upload area 43 buttons 50 Question display area 51 options 53 buttons

Claims

1. An information processing system that obtains contextual information through questions to the user and outputs target information based on said contextual information, Equipped with control means and storage means, The aforementioned storage means stores basic question items in advance. The control means is The user terminal communication unit sends and receives information with the user terminal used by the aforementioned user, The generation AI system and the generation AI system communication unit that sends and receives information, A prompt generation unit that generates instruction prompts for the AI ​​generation system, The system includes an information output unit that outputs the aforementioned target information in a specific format, The user terminal communication unit transmits the basic questions to the user terminal and receives answers corresponding to the basic questions. The prompt generation unit generates an instruction prompt that includes a question generation instruction to cause the generation AI system to generate additional questions based on the context information consisting of the basic questions and the answers corresponding to the basic questions. The AI ​​generation system communication unit receives the additional questions generated by sending the instruction prompt to the AI ​​generation system. The user terminal communication unit transmits the additional questions to the user terminal and receives answers corresponding to the additional questions. The prompt generation unit generates an instruction prompt that includes a question generation instruction that causes the generation AI system to generate additional questions based on the context information consisting of the questions sent to the user terminal and the answers received from the user terminal, and a target information generation instruction that causes the target information to be generated based on the acquired context information, and enables the output of the target information if the accuracy of the context information is above a certain level. The information output unit is an information processing system that outputs the target information if the information received from the generating AI system by the generating AI system communication unit includes the target information or information indicating that the target information has become available for output.

2. The information processing system according to claim 1, wherein the prompt generation unit includes an instruction to cause the generation AI system to generate a plurality of options that are answers to the additional questions in the question generation instruction.

3. The information processing system according to claim 1, wherein the prompt generation unit includes an instruction in the objective information generation instruction that determines the accuracy of the context information is above a certain level when the number of items included in the generated objective information is above a certain level.

4. The information processing system according to claim 3, wherein the prompt generation unit includes an instruction in the objective information generation instruction that determines the accuracy of the context information is above a certain level regardless of the number of items included in the objective information, if the number of additional questions already generated is above a certain level.

5. The user terminal communication unit receives a file containing information transmitted from the user terminal. The information processing system according to claim 1, wherein the prompt generation unit generates the instruction prompt as part of the context information by analyzing the file.

6. The information processing system according to claim 1, wherein the information output unit causes the generating AI system to generate objective information in a certain format based on the context information via the generating AI system communication unit, and outputs the objective information.

7. A program that obtains contextual information through questions to the user and creates target information based on said contextual information, On the computer, User terminal communication processing that sends and receives information with the user terminal used by the aforementioned user, A generation AI system and a generation AI system communication process that sends and receives information, A prompt generation process that generates instruction prompts for the AI ​​generation system, The system performs an information output process that outputs the aforementioned target information in a specific format, In the user terminal communication process, an instruction prompt is generated that includes a question generation instruction to cause the generation AI system to generate additional questions based on the context information consisting of pre-stored basic questions and the answers corresponding to those basic questions. In the prompt generation process, the instruction prompt is generated using the basic questions and the corresponding answers as context information. In the AI ​​generation system communication process, the instruction prompt is sent to the AI ​​generation system to receive the generated additional questions. In the user terminal communication process, the additional questions are sent to the user terminal and answers corresponding to the additional questions are received. In the prompt generation process, a prompt is generated that includes a question generation instruction causing the generation AI system to generate additional questions based on the context information consisting of the questions sent to the user terminal and the answers received from the user terminal, and a target information generation instruction causing the system to generate target information based on the acquired context information, and enabling the output of the target information if the accuracy of the context information is above a certain level. The information output process includes a program that outputs the target information if the information received from the generating AI system in the generating AI system communication process includes the target information or information indicating that the target information has become available for output.

Images