Information processing system

The information processing system addresses the limitations of large language models by generating real-time information tables and diagrams to ensure comprehensive discussion capture and report creation, improving problem resolution and recurrence prevention.

JP2025109692APending Publication Date: 2025-07-25SEMICON ENERGY LAB CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025003434
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-01-12
Filing Date
2025-01-09
Publication Date
2025-07-25

AI Technical Summary

Technical Problem

Existing large language models struggle to assist users in creating comprehensive trouble reports by identifying insufficient discussion content and deriving characteristic factors, leading to incomplete problem resolution and recurrence prevention.

Method used

An information processing system that monitors discussions in real-time, generates information tables and questions, and converts them into user-friendly formats like characteristic cause diagrams to assist users in completing discussions and creating reports.

Benefits of technology

Enhances the completeness of trouble reports by ensuring all necessary information is captured, facilitating effective problem resolution and recurrence prevention through structured information display and analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025109692000001_ABST
    Figure 2025109692000001_ABST
Patent Text Reader

Abstract

To provide an information processing system which assists a discussion among users.SOLUTION: The information processing system is provided which includes: an input / output interface which acquires voice data of users to display information relating to the voice data of the users; a processing unit which generates text data on the basis of the voice data and generates prompts including the text data; and an information collection unit which collects information on the basis of the prompts to generate an information table and questions to the users. The input / output interface has a function of outputting the voice data to the processing unit, and the processing unit has a function of transmitting the prompts to the information collection unit, and the information collection unit has a function of transmitting the information table and the questions to the users to the processing unit. The processing unit has a function of generating information relating to the voice data of the users on the basis of the information table and the questions to the users and outputting the information to the input / output interface.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] One aspect of the present invention relates to an information processing system and an information processing method.

[0002] Note that one aspect of the present invention is not limited to the above technical field. The technical field of one aspect of the invention disclosed in this specification or the like relates to an article, a method, or a manufacturing method. Or, one aspect of the present invention relates to a process, a machine, a manufacture, or a composition of matter. Therefore, more specifically, as the technical field of one aspect of the present invention disclosed in this specification, semiconductor devices, display devices, light-emitting devices, power storage devices, storage devices, their driving methods, or their manufacturing methods can be cited as an example.

Background Art

[0003] In recent years, the development of language models using neural networks has been actively carried out, and in particular, large language models (LLMs) have attracted attention. A large language model is a natural language processing model trained using a large amount of data. With a large language model, for example, a dialogue model that answers user instructions can be realized. In Non-Patent Document 1, GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) is disclosed as a large language model, and ChatGPT is disclosed as a dialogue model.

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] By using large language models, it is possible to summarize text or extract key points from conversation transcripts or meeting minutes. For example, when a problem occurs within a company, a draft report (hereinafter referred to as a trouble report) regarding the problem can be created from the conversation transcript of the discussion regarding the trouble.

[0006] However, in the method of extracting key points from conversation transcripts or the like using a large language model after the discussion, when the user checks the key points and determines that the content of the discussion is insufficient, the user has to conduct the discussion again or make corrections to the key points. Therefore, it is difficult for the user to obtain the benefits of using the large language model. For example, when creating a trouble report using a large language model, if the content of the discussion is insufficient, it is difficult to improve the completion degree of the trouble report, and it is less likely to lead to the prevention of recurrence of the trouble. In addition, in order to strengthen the prevention of recurrence of the trouble, it is necessary to create a characteristic factor diagram or the like for deriving a solution from the trouble report, but it is difficult to do this only with a large language model.

Means for Solving the Problems

[0007] Therefore, one aspect of the present invention provides an information processing system that monitors a user's discussion in real time, displays an information table based on the discussion content and questions to the user, and assists the user's discussion. In addition, one aspect of the present invention provides an information processing system that, in addition to the above configuration, converts the information table into a user-friendly format (for example, a characteristic cause diagram) and displays it.

[0008] One aspect of the present invention includes an input / output interface that acquires a user's voice data and displays information related to the user's voice data, a processing unit that creates text data based on the user's voice data and creates a prompt including the text data, and an information collection unit that collects information based on the prompt and generates an information table and questions to the user. The input / output interface has a function of outputting the voice data to the processing unit, the processing unit has a function of transmitting the prompt to the information collection unit, the information collection unit has a function of transmitting the information table and questions to the user to the processing unit, and the processing unit creates information related to the user's voice data based on the information table and questions to the user and has a function of outputting it to the input / output interface.

[0009] In the information processing system with the above configuration, the processing unit has a function of converting the display format of the information table, and the information related to the user's voice data includes at least any one of, for example, the information table, questions to the user, and the information table with the converted display format.

[0010] In the information processing system with the above configuration, the information collection unit can collect information related to troubles, for example.

[0011] In the information processing system with the above configuration, the processing unit has a function of converting the information table into a characteristic cause diagram, and the information related to the user's voice data includes at least any one of, for example, the information table, questions to the user, and the characteristic cause diagram.

Advantages of the Invention

[0012] According to one aspect of the present invention, an information processing system for assisting a user's discussion can be provided. Further, according to one aspect of the present invention, an information processing system for supporting the creation of a trouble report can be provided. Further, according to one aspect of the present invention, an information processing system for creating a characteristic factor diagram can be provided.

Brief Description of Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be easily understood by those skilled in the art that its form and details can be variously changed. Further, the present invention is not to be construed as limited to the description of the embodiments shown below.

[0015] (Embodiment) In this embodiment, an information processing system according to one aspect of the present invention will be described with reference to FIGS. 1 to 6.

[0016] FIG. 1 shows an example of an information processing system according to an aspect of the present invention. The information processing system according to an aspect of the present invention includes at least an input / output interface 101, a processing unit 102, and an information collection unit 104. The information processing system according to an aspect of the present invention acquires user voice data at the input / output interface 101, creates text data based on the user voice data in the processing unit 102 included in the information processing apparatus 10, creates a prompt including the text data, and transmits the prompt to the information collection unit 104 included in the information processing apparatus 40 via a network. The information collection unit 104 performs processing using a language model.

[0017] Although not shown, the information processing system according to an aspect of the present invention may be configured such that one information processing apparatus includes at least a part of the processing unit 102 and at least a part of the information collection unit 104. Further, the information processing system according to an aspect of the present invention may be configured such that one information processing apparatus includes at least a part of the input / output interface 101 and at least a part of the processing unit 102. Further, the information processing system according to an aspect of the present invention may be configured such that one information processing apparatus includes at least a part of the input / output interface 101, at least a part of the processing unit 102, and at least a part of the information collection unit 104.

[0018] <Input / Output Interface> The input / output interface 101 can acquire the user's voice and display information related to the user's voice data. Therefore, the input / output interface 101 includes at least a voice input unit 106 capable of recording at least the user's voice and a display unit 105 capable of displaying information. Specific examples of the user's voice include voice data obtained by recording the user's discussion. Specific examples of information related to the user's voice data include an information table, a question to the user, and an information table converted into a format that is easy for the user to read. In the present specification, the user's discussion refers to, for example, one user stating an opinion or multiple users stating opinions to each other.

[0019] The input / output interface 101 is an information processing device having an audio input unit 106 and a display unit 105. For example, it is an information processing device typified by a mobile information terminal represented by a smartphone or a tablet computer, a desktop computer having a keyboard, or a notebook computer. The audio input unit 106 is, for example, a microphone. The display unit 105 is, for example, a display device such as a liquid crystal display device or an organic EL display device.

[0020] <Processing unit> The processing unit 102 has a function of receiving audio data from the input / output interface 101 and creating text data based on the audio data. That is, it transcribes the user's discussion.

[0021] Also, the processing unit 102 has a function of adding an instruction sentence to the created text data to create a prompt, and transmitting the created prompt to the information collection unit 104 via a network. The instruction sentence includes an instruction to collect information from the text data and generate an information table and a question to the user about the information lacking in the information table.

[0022] Examples of the information table that can be generated by the processing unit 102 include a situation confirmation table regarding troubles, a system diagram regarding troubles, and the like. Specific examples of these information tables and the instruction sentence including an instruction to generate a question to the user are shown below.

[0023] 《Example 1 of instruction sentence》 "Currently, a trouble report is being made. Please summarize 'when', 'where', 'who', 'when it was happening', and 'what happened' from the content of the discussion as a situation confirmation table. Then, create a question about the information lacking in the situation confirmation table."

[0024] 《Example 2 of instruction sentence》 "Currently, we are in the process of analyzing the causes of the problem and discussing countermeasures. Please create a tree diagram by summarizing the statements made during the discussion. A tree diagram is a diagram used to develop concepts by gradually branching from larger to smaller ones, to devise several measures to solve problems (measure development type), or to organize the components of something and check the mutual relationships between the components and any omissions (component development type). For the tree diagram, under the two categories of causes of occurrence and improvement measures, provide four sub-categories: human factors, system factors, method factors, and material factors, and allocate the content of the statements to each. Then, for each of the causes of occurrence and improvement measures, create questions about the factors for which no statements have been allocated among human factors, system factors, method factors, and material factors."

[0025] By adding instructions such as Instruction Example 1 and Instruction Example 2 to the prompt, the information collection unit 104 can collect information related to the trouble, thus assisting the user's discussion. Also, it can support the user in creating a trouble report.

[0026] The prompt can specify the information table to be created and the output format of the questions to the user. The format is not particularly limited, but specific examples include HTML format, JavaScript Object Notation (abbreviation: json) format, etc.

[0027] Note that the processing unit 102 can determine the instructions to be included in the prompt according to the progress of the user's discussion. The progress of the discussion is judged by the processing unit 102 based on the information table created by the information collection unit 104. For example, at the initial stage of the discussion, create a prompt with Instruction Example 1 above as the instruction. If it is determined that the information necessary for the initial stage of the discussion, namely, "when", "where", "who", "what were you doing at the time", and "what happened", is filled in the information table, then a prompt can be created with Instruction Example 2 above as the instruction.

[0028] In addition, the processing unit 102 receives the information table and questions from the user, and determines whether the necessary information in the information table is filled. Whether the necessary information in the information table is filled can be determined, for example, by the fact that there are no blank fields in the information table. Also, for example, it can be determined based on whether the information collection unit 104 has generated questions for the user.

[0029] In addition, the processing unit 102 has a function of receiving the information table and questions from the user, and outputting them to the input / output interface 101 as information related to the user's voice data.

[0030] In addition, the processing unit 102 has a function of receiving the information table and questions from the user, and further outputting to the input / output interface 101, as information related to the user's voice data, the information table converted into a format that is easy for the user to read. For example, the processing unit 102 can convert a situation confirmation table including "when", "where", "who", "when doing what", "what happened" generated by the information collection unit 104 based on a prompt created with Example 1 of the instruction text as the instruction text, into a table in a display format that is easy for the user to read. Also, for example, the processing unit 102 can create a characteristic cause-and-effect diagram from an information table including major, medium, and minor factors of trouble occurrence generated by the information collection unit 104 based on a prompt created with Example 2 of the instruction text as the instruction text. FIG. 3 shows an example of a characteristic cause-and-effect diagram that can be created by the processing unit 102. Note that the characteristic cause-and-effect diagram shown in FIG. 3 is created based on the above-mentioned information table and the system diagram of the cause of occurrence shown in Example 2 of the instruction text.

[0031] The creation of the characteristic cause-and-effect diagram can be performed, for example, by the processing unit 102 extracting necessary information from the information table, processing it into an input format compatible with commercially available software such as JUSE-StatWorks, inputting it into the software, and obtaining an output.

[0032] <Information collection unit> When the information collection unit 104 receives a prompt from the processing unit 102, it collects information based on the prompt and creates an information table and a question for the user about the missing information. The information collection unit 104 performs processing using a language model. The information collection unit 104 is a large computer such as a server computer or a supercomputer. Specific examples of the information table and the question for the user are as follows. Note that Specific Example 1 of the information table and the question for the user is an example of an information table and a question that the information collection unit 104 can create by receiving a prompt including text data created based on the discussion about "troubleshooting of a sputtering device in the manufacturing process of a semiconductor device" and Example 1 of the instruction text. Also, Specific Example 2 of the information table and the question for the user is an example of an information table and a question that the information collection unit 104 can create by receiving a prompt including text data created based on the discussion about "troubleshooting of mis-sent emails" and Example 2 of the instruction text.

[0033] 《Specific Example 1 of Information Table and Question to User》 When: No specific date and time are described Where: The dry pump behind the sputtering device Who: Person A, equipment responsible person, administrator When it was like that: When the cleaning process was completed What happened: Abnormal noise was generated from the dry pump, and it was discovered that a part of the joint was about to come off. Question 1: Could you tell me the specific date and time when this trouble occurred? Question 2: When this trouble occurred, was only Person A working, or were there other workers as well?

[0034] 《Specific Example 2 of Information Table and Question to User》 1. Cause of occurrence 1.1 Human factors 1.1.1 Fatigue 1.1.2 Busyness 1.1.3 Overlooking check items (tedious, no margin) 1.1.4 Character (General) 1.2 System Factors 1.2.1 Mail Check Function (Check items appear but are not viewed) 1.2.2 Warning for Newly Entered Email Address 1.3 Method Factors 1.3.1 No Manual for Sending Emails 1.3.2 No Specific Check Method for Check Items 1.4 Material Factors 1.4.1 Errors in Newly Entered Email Addresses 2. Improvement Measures 2.1 Human Factors 2.1.1 Environmental Improvement to Reduce Fatigue and Busyness 2.1.2 Awareness Reform to Avoid Missing Check Items 2.2 System Factors 2.2.1 Improvement of Mail Check Function (Strengthen Warning for New Entries) 2.3 Method Factors 2.3.1 Creation of Manual for Sending Emails 2.3.2 Indicate Specific Check Methods for Check Items 2.4 Material Factors 2.4.1 Strengthen Verification of Newly Entered Email Addresses Question 1: Regarding the human factor of character, is there a way to improve a general character? Question 2: Is there a way to correct errors in newly entered email addresses?

[0035] Similar to Information Table and Specific Examples 1 and 2 of Questions to Users, by collecting the information necessary for creating a trouble report by the Information Collection Unit 104 and generating an information table and questions to the user, the discussion of the user can be assisted. Also, the user can be supported in creating a trouble report.

[0036] In addition, when the discussion content of the user has progressed sufficiently and no information lacking in the information table is found, the Information Collection Unit 104 does not need to generate questions to the user.

[0037] Figure 2 shows an example of the processing flow of the information processing system according to one aspect of the present invention.

[0038] [Processing Flow 1] First, the input / output interface acquires the user's voice data (step S11).

[0039] Next, the processing unit creates text data based on the recorded voice data (step S12).

[0040] Next, the processing unit creates a prompt including the text data and an instruction sentence, and transmits the prompt to the information collection unit (step S13).

[0041] Based on the received prompt, the information collection unit generates an information table and a question for the user (step S14), and transmits them to the processing unit. Note that if the user's discussion content has advanced sufficiently and no information lacking in the information table is found, the information collection unit may not generate a question.

[0042] Next, based on the information table and the question for the user received from the information collection unit, the processing unit determines whether the information required in the information table is sufficient (step S15). For example, the processing unit can determine that the information required in the information table is sufficient when there are no blanks in the information table or when no question for the user is generated.

[0043] If it is determined in step S15 that the information required in the information table is not sufficient, the processing unit displays the information table and the question for the user on the display unit as information related to the user's voice data (step S16), and then returns to step S11.

[0044] In step S15, when the processing unit determines that the information required in the information table is sufficient, the processing unit converts the information table into a display format that is easy for the user to read, and displays it on the display unit as information related to the user's voice data (step S17). For example, an information table representing a system diagram of the cause of occurrence can be converted into a characteristic factor diagram as shown in FIG. 3 and displayed as information related to the user's voice data.

[0045] The information processing system according to one aspect of the present invention can assist the user's discussion according to the above processing flow. In addition, it can support the user in creating a trouble report. Further, a characteristic factor diagram can be created based on the discussion content.

[0046] FIG. 4 shows another example of the processing flow of the information processing system according to one aspect of the present invention. In the processing flow shown in FIG. 4, n information tables are filled by sequentially transmitting a prompt including the first to nth instruction sentences to the information collection unit (n is an integer of 2 or more).

[0047] 〔Processing Flow 2〕 At the start of the flow, let x = 1. First, similar to the processing flow of FIG. 2, after acquiring voice data (step S11), text data is created based on the voice data (step S12).

[0048] Next, the processing unit creates a xth prompt including the text data and the instruction sentence, and transmits the xth prompt to the information collection unit (step S21).

[0049] The information collection unit generates a xth information table and a question to the user based on the received xth prompt (step S22), and transmits it to the processing unit. Note that when the user's discussion content has advanced sufficiently and no information lacking in the information table is found, the information collection unit may not generate a question.

[0050] Next, the processing unit determines whether the necessary information in the x-th information table is sufficient based on the x-th information table received from the information collection unit and the questions to the user (step S23).

[0051] In step S23, if it is determined that the necessary information in the x-th information table is not sufficient, the processing unit displays the information table and the questions to the user on the display unit as information related to the user's voice data (step S24), and then returns to step S11.

[0052] In step S23, if the processing unit determines that the necessary information in the x-th information table is sufficient, it determines whether x = n (step S25). In step S25, if x ≠ n (that is, if x is less than n), 1 is added to x (step S26), and the process returns to step S11. Note that after displaying the x-th information table on the display unit as information related to the user's voice data, the process may also return to step S11.

[0053] In step S25, if x = n, the processing unit displays on the display unit, as information related to the user's voice data, the converted form of the first to n-th information tables into a display format that is easy for the user to read (step S27).

[0054] The information processing system according to one aspect of the present invention can assist the user's discussion and fill n information tables according to the above processing flow. In the processing flow shown in FIG. 4, after the necessary information in a certain information table is filled by sufficient discussion by the user, in order to fill the next information table, appropriate questions are displayed according to the progress of the user's discussion, and the discussion can proceed smoothly.

[0055] FIG. 5 shows another example of the processing flow of the information processing system according to an aspect of the present invention. In the processing flow shown in FIG. 5, when the prompt includes instructions for generating all of the first to nth information tables and questions to the user, instead of displaying all of the first to nth information tables and questions to the user on the display unit, appropriate ones among the first to nth information tables and questions to the user can be sequentially displayed according to the progress of the user's discussion.

[0056] 〔Processing Flow 3〕 At the start of the flow, set x = 1. First, similar to the processing flows of FIGS. 2 and 4, after acquiring voice data (step S11), text data is created based on the voice data (step S12).

[0057] Next, the processing unit creates a prompt including the text data and instructions, and transmits the prompt to the information collection unit (step S31). Here, the instructions include instructions for generating the first to nth information tables and questions to the user.

[0058] Next, the information collection unit generates each information table and questions to the user based on the received prompt (step S32), and transmits them to the processing unit. Note that when the content of the user's discussion has progressed sufficiently and no information lacking in the information table is found, the information collection unit may not generate questions.

[0059] Next, the processing unit determines whether the information required for the xth information table is sufficient based on the first to nth information tables and questions to the user received from the information collection unit (step S33).

[0060] If it is determined in step S33 that the information required for the xth information table is not sufficient, the processing unit displays the xth information table and questions to the user on the display unit (step S34), and then returns to step S11.

[0061] In step S33, if it is determined that the information required in the x-th information table is sufficient, it is determined whether x = n (step S25). In step S25, if x ≠ n (that is, if x is less than n), 1 is added to x (step S26), and the process returns to step S33. Although not shown in FIG. 5, in step S33, when it is determined that the information required in the x-th information table is sufficient, the x-th information table can also be displayed on the display unit.

[0062] In step S25, if x = n, the processing unit converts the first to n-th information tables into a display format that is easy for the user to read and displays them on the display unit (step S27).

[0063] The information processing system according to one aspect of the present invention can assist the user's discussion and fill n information tables according to the above processing flow. In the processing flow shown in FIG. 5, even if there is only one type of instruction sentence included in the prompt, after the information required in a certain information table is filled by the user's sufficient discussion, a question for filling the next information table can be displayed. Therefore, appropriate questions can be displayed according to the progress of the user's discussion, and the discussion can proceed smoothly.

[0064] Also, an example of a network configuration diagram for executing the above flow is shown in FIG. 6.

[0065] As an example of the input / output interface, FIG. 6 shows information terminals 20a, 20b, 20c, and 20d. The information terminals 20a, 20b, 20c, and 20d can transmit and receive data to and from the information processing apparatus 10 via the network 31. Also, the information processing apparatus 10 can transmit and receive data to and from the information processing apparatus 40 via the network 30.

[0066] As the network 30 and the network 31, a global network or a local network can be used respectively. As the global network, the Internet which is the basis of the World Wide Web (WWW) can be used. As the local network, an intranet or an extranet can be used. For example, the Internet can be used for both the network 30 and the network 31. Or, an intranet or an extranet can be used for both the network 30 and the network 31. Also, as the network 31, a computer network smaller than the network 30 may be used. For example, the network 30 may be a global network (for example, the Internet), and the network 31 may be a local network (for example, an intranet).

[0067] In addition, as the network 30 and the network 31, computer networks such as PAN (Personal Area Network), LAN (Local Area Network), CAN (Campus Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), GAN (Global Area Network), etc. can be used respectively.

[0068] Also, when performing wireless communication, as the communication protocol or communication technology, communication standards such as the 4th generation mobile communication system (4G), the 5th generation mobile communication system (5G), the 6th generation mobile communication system (6G), etc., or specifications standardized by the IEEE such as Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. can be used.

[0069] The user of the information processing system can access the information processing apparatus 10 via the network 31 from information terminals 20a to 20d, etc. And the user can receive services using the information processing system according to an aspect of the present invention.

[0070] The user can use the information processing apparatus 10 by using, for example, dedicated software or an application installed on the information terminal 20a. Alternatively, the user can use the information processing apparatus 10 from, for example, the network 31 or a web browser using the information terminal 20a.

[0071] For example, when discussions are held among a plurality of users using the information processing system according to one aspect of the present invention, each user may use the same information terminal or different information terminals. When each user uses a different information terminal, the information processing system according to one aspect of the present invention can be used to assist discussions among users located at different locations.

[0072] An organization such as a company that provides a service using the information processing system according to one aspect of the present invention (hereinafter also referred to as a service provider) can provide a service using the information processing apparatus 10. The information processing apparatus 10 is an apparatus that can execute processing using the information processing system according to one aspect of the present invention. In FIG. 6, as an example, a server computer is illustrated.

[0073] The information processing apparatus 10 creates a prompt based on the original text (first text data) input to the input / output interface. The information processing apparatus 10 is a computer with higher processing power compared to the information terminal 20a. In the present embodiment, the information processing apparatus 10 functions as a processing unit. This stage corresponds to step S12 in FIG. 2.

[0074] A plurality of prompts created by the information processing apparatus 10 are input as data to the information processing apparatus 40 via the network 30. The information processing apparatus 40 can perform information processing such as calculations using the data transmitted from the information processing apparatus 10.

[0075] The information processing device 40 is a large computer such as a server computer or a supercomputer. The information processing device 40 is a computer with higher processing power compared to the information terminal 20a. Also, the information processing device 40 is a computer with higher processing power compared to the information processing device 10. The information processing device 40 preferably has a function as a parallel computer. By using the information processing device 40 as a parallel computer, for example, large-scale calculations required for AI learning and inference can be performed. When both the information processing device 10 and the information processing device 40 have a function as a parallel computer, the information processing device 40 has higher processing power and can perform large-scale calculations compared to the information processing device 10.

[0076] The information processing device 40 can perform processing using a natural language processing model using AI. As a natural language processing model using AI, for example, processing using natural language models (Natural Language Processing) such as BERT (Bidirectional Encoder Representations from Transformers), T5 (Text-to-Text Transfer Transformer), GPT-3, GPT-3.5, GPT-4 (registered trademark), LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), Llama2, etc. can be executed.

[0077] In the present embodiment, the information processing device 40 can utilize an AI text correction tool, for example, GPT-4 (registered trademark). The service provider does not need to prepare the information processing device 40 by itself and can utilize the information processing device 40 via the network 30.

[0078] The information processing device 40 can transmit the result of the information processing to the information processing device 10 via the network 30.

[0079] Inputting data into the information processing apparatus 40 is called prompt transmission. In this specification, sending a prompt to the information processing apparatus 40 is synonymous with sending a prompt to the information collection unit.

[0080] Note that in this embodiment, an example of assisting a user's discussion and supporting the user in creating a trouble report using the information processing system according to an aspect of the present invention has been shown. However, the use of the information processing system according to an aspect of the present invention is not limited to supporting the creation of trouble reports. For example, in the information processing system according to an aspect of the present invention, by making the prompt correspond to each document, it can be used to support the creation of various documents with determined entry items, such as project proposals, contracts, specifications, product manuals, research reports, and the like.

Explanation of Reference Numerals

[0081] 10 Information processing apparatus 20a Information terminal 20b Information terminal 20c Information terminal 20d Information terminal 30 Network 31 Network 40 Information processing apparatus 101 Input / output interface 102 Processing unit 104 Information collection unit 105 Display unit 106 Voice input unit

Claims

1. An input / output interface that acquires voice data of a user and displays information related to the voice data of the user; A processing unit that creates text data based on the voice data of the user and creates a prompt including the text data; An information collection unit that collects information based on the prompt, generates an information table and a question to the user, and has: The input / output interface has a function of outputting the voice data to the processing unit; The processing unit has a function of transmitting the prompt to the information collection unit; The information collection unit has a function of transmitting the information table and the question to the user to the processing unit; An information processing system, wherein the processing unit has a function of creating information related to the voice data of the user based on the information table and the question to the user, and outputting the information to the input / output interface.

2. In Claim 1, The processing unit has a function of converting the display format of the information table; The information related to the voice data of the user includes at least any one of the information table, the question to the user, and the information table with the converted display format. An information processing system.

3. In Claim 1, The information collection unit collects information related to troubles. An information processing system.

4. In Claim 3, The processing unit has a function of converting the information table into a characteristic factor diagram; The information related to the voice data of the user includes at least any one of the information table, the question to the user, and the characteristic factor diagram. An information processing system.