Information processing systems, programs, and information processing methods

Abstract

To make it easy to create work manuals. [Solution] The information processing system (manual generation system 1) includes: a first question unit (virtual CPU 21) that obtains user answers to first questions, which are questions concerning all processes constituting the work; a second question unit (virtual CPU 21) that obtains user answers to second questions, which are questions for identifying a special process among all processes constituting the work; a third question unit (virtual CPU 21) that obtains user answers to third questions, which are questions concerning the work content in each process constituting the work; a fourth question unit (virtual CPU 21) that obtains user answers to fourth questions, which are additional questions concerning the special process identified based on the answers obtained by the second question unit; and a manual generation unit (virtual CPU 21) that generates a manual based on the answers obtained by the first question unit, the third question unit, and the fourth question unit.

Description

Technical Field

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

Background Art

[0002] Generally, in work processes at the production site of a product, work processes when performing maintenance and / or introduction of a product, etc., a work manual indicating work procedures is created. A worker who performs the work for the first time learns the work procedures while referring to this work manual.

[0003] In relation to this, for example, Patent Document 1 describes the following manual management device. Specifically, it is a device that promotes improvement of a work manual when there is a work process with different operations based on a comparison between the work time when a skilled worker performs the work process corresponding to the work manual and the work time when a novice worker performs the work process.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Work manuals are generally created by so-called skilled workers with a high level of work proficiency or created under the supervision of these skilled workers. However, there is a problem that among the creators of work manuals, there are creators with insufficient skills to create work manuals.

[0006] An object of this invention is to provide an information processing system, a program, and an information processing method capable of easily creating a work manual.

Means for Solving the Problems

[0007] To achieve the above objective, the information processing system described in claim 1 is: A first question unit presents the user with a first question, which is a question concerning all the processes that make up the work, and obtains the user's answer to the first question. A second questioning unit presents the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtains the user's answer to the second question. A third question unit presents the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtains the user's answer to the third question. A fourth questioning unit presents the user with a fourth question, which is an additional question relating to the special process identified based on the answer obtained by the second questioning unit, and obtains the user's answer to the fourth question. A manual generation unit generates a manual based on the answers obtained by the first questioning unit, the third questioning unit, and the fourth questioning unit, It is equipped with.

[0008] The invention described in claim 2 is an information processing system described in claim 1, The manual generation unit inputs the answer and instructions to generate the manual based on the answer to the large-scale language model, and outputs the manual.

[0009] The invention described in claim 3 is an information processing system described in claim 1, The first question unit presents the first question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the first question using the speech recognition means and obtains it as the answer. The second question unit presents the second question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the second question using the speech recognition means and obtains it as the answer. The third question unit presents the third question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the third question using the speech recognition means and obtains it as the answer. The fourth question unit presents the fourth question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the fourth question using the speech recognition means and obtains it as the answer.

[0010] The invention described in claim 4 is an information processing system described in claim 1, The fourth question includes at least one of the following: a question asking for precautions regarding matters other than the user's actions; a question asking for the movements of each part of the user's body; a question requesting a quantitative description of the user's actions; and a question requesting a description of the user's actions using onomatopoeia or mimetic words.

[0011] The invention described in claim 5 is an information processing system described in claim 4, If the fourth question includes a question that requires the user's actions to be expressed using onomatopoeia or mimetic words, the manual generation unit inputs an instruction to the large-scale language model to generate the manual, which includes the answer and the onomatopoeia or mimetic words based on the answer, and outputs the manual.

[0012] The invention described in claim 6 is an information processing system described in claim 1, A database storing a set of questions, including the first question, the second question, the third question, and the fourth question, for each industry or business type to which the aforementioned work is performed. An acquisition unit that acquires the set of questions corresponding to the industry or business type selected by the user, It is equipped with.

[0013] The program described in claim 7 is The computer in the information processing system A first question unit presents the user with a first question, which is a question concerning all the processes that make up the work, and obtains the user's answer to the first question. A second question unit presents the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtains the user's answer to the second question. A third question unit presents the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtains the user's answer to the third question. A fourth question unit presents the user with a fourth question, which is an additional question relating to the special process identified based on the answer obtained by the second question unit, and obtains the user's answer to the fourth question. A manual generation unit generates a manual based on the answers obtained by the first questioning unit, the third questioning unit, and the fourth questioning unit. To make it function as such.

[0014] The information processing method described in claim 8 is: A first question step involves presenting the user with a first question, which is a question concerning all the processes that make up the work, and obtaining the user's answer to the first question. A second question step involves presenting the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtaining the user's answer to the second question. A third question step involves presenting the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtaining the user's answer to the third question. A fourth questioning step involves presenting the user with a fourth question, which is an additional question relating to the special process identified based on the answers obtained in the second questioning step, and obtaining the user's answer to the fourth question. A manual generation unit step that generates a manual based on the answers obtained in the first question step, the third question step, and the fourth question step, Includes.

Effect of the Invention

[0015] According to the present invention, a work manual can be easily created.

Brief Description of the Drawings

[0016] [Figure 1] It is a block diagram showing the configuration of a manual generation system. [Figure 2] It is a diagram showing an example of a question set. [Figure 3] It is a flowchart of a manual generation process. [Figure 4] It is a flowchart of a manual generation process. [Figure 5] It is a diagram showing a manual generation screen on which a pull-down menu is displayed. [Figure 6] It is a flowchart of an answer acquisition process. [Figure 7] It is a diagram showing a manual generation screen on which a question is displayed. [Figure 8] It is a diagram showing a manual generation screen on which a manual is displayed.

Mode for Carrying Out the Invention

[0017] Hereinafter, embodiments of the present invention will be described based on the drawings. However, the scope of the invention is not limited to the illustrated examples.

[0018] <1. Configuration of the Manual Generation System> FIG. 1 is a block diagram showing the configuration of a manual generation system 1 (information processing system) according to an embodiment of the present invention. The manual generation system 1 includes a terminal device 10 and a cloud computing system 100. The terminal device 10 and the cloud computing system 100 are communicably connected via a communication network such as the Internet. The manual generation system 1 provides users of the terminal device 10 with a service that generates manuals and allows them to save and view those manuals. Hereinafter, this service will be referred to as the "manual generation service." In this embodiment, the manual generation system 1 will be used to explain the process using the example of generating a manual for work in the manufacturing industry.

[0019] (1-1. Terminal device configuration) The terminal device 10 may be, for example, a notebook PC (personal computer), a desktop PC, a tablet device, or a smartphone. The terminal device 10 comprises a CPU (Central Processing Unit) 11, memory 12, storage unit 13, display unit 14, operation unit 15, audio input / output unit 16, and communication unit 17. Each part of the terminal device 10 is connected via a data transmission path such as a bus.

[0020] The CPU 11 is a processor that controls the operation of each part of the terminal device 10 by executing various processes according to the program 131 stored in the memory unit 13. Memory 12 is, for example, RAM (Random Access Memory), which provides the CPU 11 with a working memory space and stores temporary data.

[0021] The storage unit 13 includes flash memory, an HDD (Hard Disk Drive), or an SSD (Solid State Drive), etc. The memory unit 13 stores various processing programs, including program 131, parameters necessary for executing the program, files, and the like. Program 131 includes a web browser. The CPU 11 accesses the cloud computing system 100 via the web browser. Based on data provided from the cloud computing system 100 in web application format, the CPU 11 displays various information, manuals, etc., on the display unit 14.

[0022] The display unit 14 is equipped with a monitor such as an LCD (Liquid Crystal Display). The display unit 14 displays various information, manuals, etc., according to control signals input from the CPU 11. The operation unit 15 is equipped with input means such as a mouse, keyboard, touch panel, and operation buttons. When an operation is performed on the input means, the operation unit 15 outputs an operation signal corresponding to that operation to the CPU 11. The audio input / output unit 16 includes an audio input unit such as a microphone and an audio output unit such as an amplifier and speakers. The audio input / output unit 16 acquires audio signals such as the user's voice via the audio input unit, converts them into audio data, and outputs them to the CPU 11. The audio input / output unit 16 outputs audio based on the audio data input from the CPU 11 via the audio output unit. The communication unit 17 performs communication operations in accordance with predetermined communication standards. Through these communication operations, the communication unit 17 sends and receives data with the service provider server 20 of the cloud computing system 100.

[0023] (1-2. Configuration of the Cloud Computing System) The cloud computing system 100 comprises a service provision server 20, a database 30, a document generation server 40, a speech synthesis server 50, and a speech recognition server 60. The service provider server 20, document generation server 40, speech synthesis server 50, and speech recognition server 60 are virtual servers. More specifically, the cloud computing system 100 comprises multiple physical servers (not shown) that are interconnected and communicate with each other. In the cloud computing system 100, these multiple physical servers realize a virtual environment in which multiple virtual servers can be logically constructed. The service provider server 20, document generation server 40, speech synthesis server 50, and speech recognition server 60 are virtual servers constructed in such a virtual environment. The virtual CPU, virtual memory, and virtual storage unit of a virtual server are realized by logically dividing or integrating the CPU, memory, and storage unit, etc., that constitute the physical server, respectively.

[0024] The service provision server 20 includes a virtual CPU 21, virtual memory 22, and virtual storage unit 23. The virtual CPU 21 executes various processes related to the provision of the manual generation service according to the program 231 stored in the virtual memory unit 23. Virtual memory 22 provides a working memory space to the virtual CPU 21 and stores temporary data. The virtual memory unit 23 stores program 231, as well as parameters, files, and other information necessary for executing program 231.

[0025] The database 30 is a database for storing various types of data and includes a question set storage unit 31 and a manual storage unit 32. The question set storage unit 31 stores question sets for each industry, business type, etc., related to the work for which the manual is to be generated. Figure 2 shows an example of a question set. The question set includes a first question, a second question, a third question, and a fourth question, which are questions presented to the user using the terminal device 10. The first question concerns all the steps that make up the work for which the manual will be generated. The second question is designed to identify any special processes within the overall workflow that constitute the task for which the manual will be generated, processes that require advanced skills, abilities, etc. The third question concerns the work content in each process that constitutes the work for which the manual is to be generated. The fourth question is an additional question regarding special processes. The fourth question includes questions asking about precautions regarding matters other than the user's actions in a special process. For example, such questions might be: "Are there any precautions to take regarding third parties or the environment other than your own work? For example, pre-checking the machine, environmental factors such as temperature and humidity, or the movements of your colleagues?" The fourth question includes questions about the movement of each part of the user's body during a specific process. For example, one such question might be: "What about the body movements of parts other than the most active part? In delicate tasks using the hands, parts that you are not consciously aware of, such as the shoulders and elbows, can actually be important. Try to imagine this." The fourth question includes one that asks for a quantitative description of the user's actions during a specific process. For example, this question might say, "Please describe your physical movements during the task using specific numerical expressions such as moving 1 cm or 1 mm. The numbers do not need to be exact; even an approximation will help the listener visualize the movement." The fourth question includes one that asks the user to describe the physical movements and / or sensations of a particular process using onomatopoeia or mimetic words. For example, such a question might be: "Please describe the physical movements and sensations using onomatopoeia or mimetic words such as 'snap' or 'swiftly.' This will help the listener visualize the task." The manual storage unit 32 stores the manuals that are generated in the manual generation process described later.

[0026] The document generation server 40, like a virtual server, includes a virtual CPU, virtual memory, and virtual storage unit, etc. (not shown in the figure). The document generation server 40 is equipped with a large language model (LLM) 41. The document generation server 40 causes the LLM 41 to generate the manual's title, summary, body text, etc. LLM41 is a language model pre-trained using vast amounts of data and deep learning techniques to assign probabilities to word sequences. In the deep learning pre-training, the neural network model parameters are adjusted so that appropriate probabilities are assigned to word sequences. When a prompt, which is an input sentence instructing LLM41's operation, is received, LLM41 estimates and outputs the word sequence following the prompt, i.e., the response sentence. Specifically, LLM41 divides the input prompt into the smallest units called tokens and extracts the features of each token. Based on the extracted features, LLM41 constructs the response sentence by repeatedly deriving the probabilities of the tokens following the prompt. Through this operation, LLM41 can perform various tasks requested by the prompt. Tasks performed by LLM41 in this embodiment include generating the title, summary, and body text of a manual based on input text, etc.

[0027] The speech synthesis server 50, like a virtual server, includes a virtual CPU, virtual memory, and virtual storage unit, etc. (not shown in the figure). The speech synthesis server 50 is a speech synthesis means that converts input text data into speech data for reading the text aloud and outputs it.

[0028] The speech recognition server 60, like a virtual server, includes a virtual CPU, virtual memory, and virtual storage unit, etc. (not shown in the figure). The speech recognition server 60 is a speech recognition means that recognizes and analyzes the speech contained in the input speech data, converts it into text, and outputs it. In this specification, the text obtained by this process is referred to as "speech text".

[0029] <2. Operation of the manual generation system> Next, the operation of the manual generation system 1 will be described. Figures 3 and 4 are flowcharts of the manual generation process performed by each device of the manual generation system 1 when it generates a manual for the provision of the manual generation service. Figures 3 and 4 show the processes executed by the CPU 11 of the terminal device 10, the virtual CPU 21 of the service provision server 20, the document generation server 40, the speech synthesis server 50, and the speech recognition server 60, respectively, as well as the flow of data transmitted and received between each device.

[0030] (Manual generation process) When the CPU 11 of the terminal device 10 receives an input operation from the user via the operation unit 15 instructing it to start manual generation, it sends a request to start the manual generation process to the service provider server 20. When the virtual CPU 21 of the service provision server 20 receives the start request, it sends data to the terminal device 10 to display the manual generation screen 140 shown in Figure 5 on the display unit 14 (step S1). When the CPU 11 of the terminal device 10 receives data from the manual generation screen 140, it displays the manual generation screen 140 on the display unit 14 in a web browser based on that data (step S2).

[0031] The manual generation screen 140 shown in Figure 5 displays a pull-down menu 141 for selecting the industry or business type related to the work for which the manual will be generated. The user selects the industry or business type related to the work for which the manual will be generated from the pull-down menu 141 via the operation unit 15. In Figure 5, "Manufacturing" is selected as the industry.

[0032] When CPU 11 receives an operation to select an industry or business type from the pull-down menu 141, it sends information about the industry or business type selected by the user to the service provider server 20 (step S3). When the virtual CPU 21 of the service provision server 20 receives information on the industry or business type, it retrieves a question set corresponding to the industry or business type from the question set storage unit 31 (step S4). In step S4, the virtual CPU 21 of the service provision server 20 functions as an acquisition unit.

[0033] Next, each device in the manual generation system 1 performs an answer acquisition process (see Figure 6) to acquire the answer to the first question included in the question set acquired in step S4 (step S5). Each device in the manual generation system 1 performs step S5 for all first questions. In step S5, the virtual CPU 21 of the service provision server 20 functions as the first question unit. Step S5 is the first question step.

[0034] (Response acquisition process) The virtual CPU 21 of the service provision server 20 sends data to the terminal device 10 to display the first question included in the question set acquired in step S4 on the manual generation screen 140 (step A1). When the CPU 11 of the terminal device 10 receives the data for the first question, it displays the first question on the manual generation screen 140 based on the data for the first question (step A2). Figure 7 shows an example of the manual generation screen 140 with the first question, question 142a, displayed. The manual generation screen 140 shown in Figure 7 displays a question audio output button 142b for outputting an audio recording of question 142a.

[0035] When the user presses the question audio output button 142b via the control unit 15, the CPU 11 sends an audio conversion instruction to the service provider server 20, which is an instruction to convert the text data indicating the content of the question 142a into audio data (step A3). When the virtual CPU 21 of the service provider server 20 receives a speech conversion instruction, it sends text data indicating the content of question 142a and the speech conversion instruction to the speech synthesis server 50 (step A4).

[0036] When the speech synthesis server 50 receives text data indicating the content of question 142a and a speech conversion instruction, it converts the text data indicating the content of question 142a into speech data and outputs it (step A5). The speech synthesis server 50 then sends the speech data of question 142a to the service provider server 20 (step A6). The virtual CPU 21 of the service provision server 20 receives the audio data of question 142a and forwards it to the terminal device 10 (step A7). When the CPU 11 of the terminal device 10 receives the audio data of question 142a, the audio output unit of the audio input / output unit 16 outputs an audio reading of question 142a based on the audio data of question 142a (step A8).

[0037] Next, the CPU 11 receives the user's response to question 142a (step A9). Specifically, as shown in Figure 7, the CPU 11 receives the response via text input from the user through the operation unit 15 in the response input field 142c displayed on the manual generation screen 140. Alternatively, the CPU 11 receives a press of the response voice input button 142d, which is displayed on the manual generation screen 140 to receive the user's voice response. The user enters their answer to question 142a as text into the answer input field 142c via the operation unit 15. Alternatively, the user may press the answer voice input button 142d via the operation unit 15 to provide an answer to question 142a by voice. When the CPU 11 receives a press operation for the answer voice input button 142d, it acquires the user's voice data using the voice input unit of the voice input / output unit 16. The CPU 11 sends the acquired answer voice data and a text conversion instruction, which is an instruction to convert the voice data into text data, to the service provider server 20 (step A10).

[0038] The virtual CPU 21 of the service provision server 20 receives the voice data of the response and the text conversion instructions, and transfers them to the speech recognition server 60 (step A11). When the speech recognition server 60 receives the response audio data and the text conversion instruction, it performs a predetermined speech recognition process on the audio data to identify the content of the audio, i.e., the words a person is speaking. Based on this identification result, the speech recognition server 60 converts the audio data into speech text that represents the content of the audio (step A12). The speech recognition server 60 sends the response speech text data to the service provider server 20 (step A13). The virtual CPU 21 of the service provider server 20 acquires the voice-to-text data of the response from the speech recognition server 60 (step A14), and then terminates the response acquisition process.

[0039] In step A9, if the CPU 11 of the terminal device 10 receives a text input operation for the answer in the answer input field 142c, the CPU 11 sends the received answer text data to the service provider server 20. Next, the virtual CPU 21 of the service provider server 20 retrieves the answer text data from the terminal device 10 and terminates the answer retrieval process.

[0040] Returning to Figure 3, the virtual CPU 21 of the service provision server 20 sends the text data of the answer to the first question obtained in step S5 and the first generation instruction to the document generation server 40 (step S6). The text data of the answer to the first question includes the audio text data of the answer to the first question. The first generation instruction is an instruction to generate the manual title, summary, and titles of each process based on the text data of the answer to the first question. When the document generation server 40 receives the text data of the answer to the first question and the first generation instruction, it inputs the text data of the answer to the first question and the first generation instruction into the LLM 41. This causes the document generation server 40 to have the LLM 41 generate the manual title, summary, and titles of each process (step S7). The document generation server 40 then transmits the generated manual title, summary, and titles of each process data to the service provider server 20 (step S8). The virtual CPU 21 of the service provision server 20 receives the manual's title, summary, and the titles of each process, and transfers them to the terminal device 10 (step S9).

[0041] When the CPU 11 of the terminal device 10 receives data for the manual's title, summary, and the titles of each process, it displays the manual's title, summary, and the titles of each process on the manual generation screen 140 based on this data (step S10). Figure 8 shows an example of the manual generation screen 140 with the manual's title 143a, summary 143b, and the titles of each process 143c displayed.

[0042] Next, each device of the manual generation system 1 performs an answer acquisition process to acquire answers to the second question included in the question set acquired in step S4, in the same manner as in step S5 (step S11). In step S11, the virtual CPU 21 of the service provision server 20 functions as the second question unit. Step S11 is the second question step.

[0043] Next, the virtual CPU 21 of the service provision server 20 sends the text data of the answer to the second question obtained in step S11 and a specific instruction to the document generation server 40 (step S12). The text data of the answer to the second question includes the audio text data of the answer to the second question. The specific instruction is an instruction that identifies a particular process among all the processes that constitute the work, based on the text data of the answer to the second question. When the document generation server 40 receives the text data of the answer to the second question and the specific instructions, it inputs the text data of the answer to the second question and the specific instructions into the LLM 41. This causes the document generation server 40 to cause the LLM 41 to determine whether or not there are any special processes in all the processes that make up the work. Furthermore, if it is determined that there are special processes, the document generation server 40 causes the LLM 41 to identify which of the processes that make up the work is the special process (step S13). The document generation server 40 transmits the identification information of the special process to the service provision server 20 (step S14). The virtual CPU 21 of the service provision server 20 receives specific information for a special process and forwards it to the terminal device 10 (step S15).

[0044] When the CPU 11 of the terminal device 10 receives information identifying a special process, it displays an indication of the special process on the manual generation screen 140 based on that information (step S16). In the example shown in Figure 8, among the processes that make up the work, the second process is a special process, and an indication 143d showing that it is a special process is displayed near the title 143c of the second process.

[0045] Next, each device in the manual generation system 1 performs an answer acquisition process to acquire answers to the third questions included in the question set acquired in step S4, in the same manner as in step S5 (step S17). Each device in the manual generation system 1 performs step S17 for all third questions for each process that constitutes the work. In step S17, the virtual CPU 21 of the service provision server 20 functions as the third question unit. Step S17 is the third question step.

[0046] Next, the virtual CPU 21 of the service provision server 20 sends the text data of the answer to the third question obtained in step S17 and the second generation instruction to the document generation server 40 (step S18). The text data of the answer to the third question includes the audio text data of the answer to the third question. The second generation instruction is an instruction to generate the main body of the document, which shows the work content in each process that constitutes the work, based on the text data of the answer to the third question. When the document generation server 40 receives the text data of the answer to the third question and the second generation instruction, it inputs the text data of the answer to the third question and the second generation instruction into the LLM 41. This causes the document generation server 40 to cause the LLM 41 to generate the main text that shows the work content for each process that constitutes the work (step S19). The document generation server 40 sends the data of the main text for each generated process to the service provision server 20 (step S20). The virtual CPU 21 of the service provision server 20 receives the body data for each process and transfers it to the terminal device 10 (step S21).

[0047] When the CPU 11 of the terminal device 10 receives the text data for each process, it displays the text 143e for each process on the manual generation screen 140 based on that data, as shown in Figure 8 (step S22).

[0048] Next, each device of the manual generation system 1 performs an answer acquisition process to acquire answers to the fourth questions included in the question set acquired in step S4, in the same manner as in step S5 (step S23). Each device of the manual generation system 1 performs step S23 for all fourth questions for the special process identified in step S13. In step S23, the virtual CPU 21 of the service provision server 20 functions as the fourth question unit. Step S23 is the fourth question step.

[0049] Next, the virtual CPU 21 of the service provision server 20 sends the text data of the answer to the fourth question obtained in step S23 and the third generation instruction to the document generation server 40 (step S24). The text data of the answer to the fourth question includes the audio text data of the answer to the fourth question. The third generation instruction is an instruction to generate additional items in a special process based on the text data of the answer to the fourth question. The third generation instruction includes, if the text data of the answer to the fourth question contains onomatopoeic or mimetic expressions, an instruction to include such onomatopoeic or mimetic expressions as they are in the additional special steps of the generation process. When the document generation server 40 receives the text data of the answer to the fourth question and the third generation instruction, it inputs the text data of the answer to the fourth question and the third generation instruction into the LLM 41. This causes the document generation server 40 to have the LLM 41 generate the additional information for the special process (step S25). The document generation server 40 then sends the data of the additional information for the special process to the service provider server 20 (step S26). The virtual CPU 21 of the service provision server 20 receives data on additional items in a special process and transfers it to the terminal device 10 (step S27).

[0050] When the CPU 11 of the terminal device 10 receives data on additional items for a special process, it displays the additional items 143f for the special process on the manual generation screen 140, as shown in Figure 8, based on that data (step S28). If, in step S13, it is determined that there are no special processes in any of the steps that make up the work, the manual generation system 1 omits the processing in steps S23 to S28.

[0051] The virtual CPU 21 of the service provision server 20 may send to the document generation server 40 text data of the answers to the third and fourth questions regarding the special process, and instructions to generate a document containing additional information regarding the special process based on the text data of the answers to the third and fourth questions. In this case, the document generation server 40 receives text data of the answers to the third and fourth questions regarding the special process, and instructions to generate the body of the special process. Next, the document generation server 40 inputs the text data of the answers to the third and fourth questions regarding the special process, and instructions to generate the body of the special process, into the LLM 41. This causes the document generation server 40 to cause the LLM 41 to generate the body of the special process, including the work content and additional information. The document generation server 40 then transmits the data of the body of the special process to the service provider server 20. The virtual CPU 21 of the service provision server 20 receives the text data of the special process and transfers it to the terminal device 10. When the CPU 11 of the terminal device 10 receives the text data for the special process, it displays the text 143e of the second process, which is the special process, on the manual generation screen 140 shown in Figure 8, based on that data. In this case, the CPU 11 does not display the additional information 143f for the special process on the manual generation screen 140.

[0052] Next, the CPU 11 accepts an operation from the user via the operation unit 15 to edit the contents of the manual on the manual generation screen 140 (step S29). The user can edit the manual's title 143a, summary 143b, titles of each process 143c, text of each process 143e, additional information for special processes 143f, etc., via the control unit 15 as needed. When the CPU 11 receives an operation to edit the contents of the manual, it sends edit data, which is data indicating the edited content, to the service provider server 20 (step S30). When the virtual CPU 21 of the service provision server 20 receives the edited data, it reflects the edited content in the manual (step S31). The virtual CPU 21 then sends the edited manual data to the terminal device 10 (step S32).

[0053] When the CPU 11 of the terminal device 10 receives the edited manual data, it displays the edited manual on the manual generation screen 140 based on that data (step S33). If the terminal device 10 does not accept an operation to edit the contents of the manual, the terminal device 10 and the service provision server 20 omit steps S30 to S33. Next, when the CPU 11 receives a command operation from the user via the operation unit 15 to save the manual, it sends a command to save the manual to the service provision server 20 (step S34). When the virtual CPU 21 of the service provision server 20 receives an instruction to save the manual, it saves the manual to the manual storage unit 32 of the database (step S35) and terminates the manual generation process.

[0054] In step S6 of the manual generation process described above, the virtual CPU 21 of the service provision server 20 generates a manual based on the answer obtained by the first questioning unit. In step S18, the virtual CPU 21 of the service provision server 20 generates a manual based on the answer obtained by the third questioning unit. In step S24, the virtual CPU 21 of the service provision server 20 generates a manual based on the answer obtained by the fourth questioning unit. In steps S6, S18, and S24, the virtual CPU 21 of the service provision server 20 functions as a manual generation unit. Steps S6, S18, and S24 are manual generation steps.

[0055] <3. Effects> As described above, the information processing system (manual generation system 1) according to this embodiment includes a first question unit (virtual CPU 21) that presents the user with a first question, which is a question relating to all the steps that constitute the work, and obtains the user's answer to the first question. The information processing system includes a second question unit (virtual CPU 21) that presents the user with a second question, which is a question for identifying a specific process among all the processes that make up the work, and obtains the user's answer to the second question. The information processing system includes a third question unit (virtual CPU 21) that presents the user with a third question, which is a question about the content of each process that constitutes the work, and obtains the user's answer to the third question. The information processing system includes a fourth questioning unit (virtual CPU 21) that presents the user with a fourth question, which is an additional question concerning a special process identified based on the answers obtained by the second questioning unit, and obtains the user's answers to the fourth question. The information processing system includes a manual generation unit (virtual CPU 21) that generates a manual based on the answers obtained by the first questioning unit, the third questioning unit, and the fourth questioning unit. Therefore, even if a user lacks the skills to create a manual, they can still create one by answering the provided questions. This makes it easy to create work manuals.

[0056] In the information processing system (manual generation system 1) according to this embodiment, the manual generation unit (virtual CPU 21) inputs the answer and instructions to generate a manual based on the answer to the large-scale language model (LLM 41), and causes the manual to output. Therefore, manuals can be easily created based on users' answers to questions.

[0057] In the information processing system (manual generation system 1) according to this embodiment, the first question unit (virtual CPU 21) presents the first question to the user using voice generated by the speech synthesis means. The first question unit recognizes the user's voice input in response to the first question using the speech recognition means and obtains it as an answer. The second question unit (virtual CPU 21) presents the second question to the user using speech generated by a speech synthesis means. The second question unit recognizes the user's voice input in response to the second question using a speech recognition means and obtains it as the answer. The third question unit (virtual CPU 21) presents the third question to the user using speech generated by a speech synthesis means. The third question unit recognizes the user's voice input in response to the third question using a speech recognition means and obtains it as the answer. The fourth question unit (virtual CPU 21) presents the fourth question to the user using speech generated by a speech synthesis means. The fourth question unit recognizes the user's voice input in response to the fourth question using a speech recognition means and obtains it as the answer. Therefore, even if the user is unfamiliar with the terminal device 10, such as a notebook PC, desktop PC, tablet device, or smartphone, the user can easily answer the questions. This makes it easy to obtain the user's answers to the questions.

[0058] In the information processing system (manual generation system 1) according to this embodiment, the fourth question includes at least one of the following: a question asking for precautions regarding matters other than the user's actions; a question asking for the movements of each part of the user's body; a question requesting a quantitative expression of the user's actions; and a question requesting an expression of the user's actions using onomatopoeia or mimetic words. Therefore, it is possible to create easy-to-understand manuals for novice workers for special processes that require advanced skills and abilities.

[0059] In the information processing system (manual generation system 1) according to this embodiment, if the fourth question includes a question that requires the user to express their actions using onomatopoeia or mimetic words, the manual generation unit (virtual CPU 21) inputs an instruction to the large-scale language model (LLM 41) to generate a manual that includes the answer and onomatopoeia or mimetic words based on the answer, and causes the manual to output. Therefore, by using onomatopoeia or mimetic words to describe user actions in the manual, it is possible to create a manual that is easy for novice users to understand.

[0060] The information processing system (manual generation system 1) according to this embodiment includes a database 30 that stores question sets, each containing a first question, a second question, a third question, and a fourth question, for each industry or business type involved in the work. The information processing system includes an acquisition unit (virtual CPU 21) that acquires a set of questions corresponding to the industry or business type selected by the user. Therefore, it is easy to set questions that correspond to the industry or business type related to the work for which the manual is being generated.

[0061] The present invention is not limited to the embodiments described above, and various modifications are possible. For example, while an example has been given in which the service provision server 20, document generation server 40, speech synthesis server 50, and speech recognition server 60 are virtual servers, the invention is not intended to be limited to this. The service provision server 20, document generation server 40, speech synthesis server 50, and speech recognition server 60 may be physical servers, that is, actual, independent servers.

[0062] An example has been given in which the service provision server 20 is provided with a virtual CPU 21 that functions as either the first questioning unit, the second questioning unit, the third questioning unit, the fourth questioning unit, the manual generation unit, or the acquisition unit, but the example is not limited to this example. Some or all of the first questioning unit, the second questioning unit, the third questioning unit, the fourth questioning unit, the manual generation unit, and the acquisition unit may be provided on a separate virtual server or a separate physical server.

[0063] The service provision server 20 and the document generation server 40 may be integrated.

[0064] The manual generation process shown in Figures 3 and 4 is just one example and can be modified as needed. For example, in steps S10 and S22, the user may be allowed to edit the content displayed on the manual generation screen 140.

[0065] Although several embodiments of the present invention have been described, the scope of the present invention is not limited to the embodiments described above, but includes the scope of the invention as described in the claims and its equivalents. [Explanation of Symbols]

[0066] 1. Manual generation system (information processing system) 10 Terminal devices 11 CPU 12 memory 13 Storage section 131 Programs 14 Display section 15 Control section 16 Audio Input / Output Section 17 Communications Department 20 Service Provider Servers 21 Virtual CPU (First Question Unit, Second Question Unit, Third Question Unit, Fourth Question Unit, Manual Generation Unit, Acquisition Unit) 22 virtual memory 23 Virtual Memory Unit 231 Programs 30 databases 31 Question Set Storage Unit 32 Manual storage compartment 40 Document generation servers 41 LLM 50 Speech synthesis servers 60 Speech Recognition Servers 100 Cloud Computing Systems 140 Manual generation screen

Claims

1. A first question unit presents the user with a first question, which is a question concerning all the processes that make up the work, and obtains the user's answer to the first question. A second questioning unit presents the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtains the user's answer to the second question. A third question unit presents the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtains the user's answer to the third question. A fourth questioning unit presents the user with a fourth question, which is an additional question relating to the special process identified based on the answer obtained by the second questioning unit, and obtains the user's answer to the fourth question. A manual generation unit generates a manual based on the answers obtained by the first questioning unit, the third questioning unit, and the fourth questioning unit, An information processing system equipped with the following features.

2. The information processing system according to claim 1, wherein the manual generation unit inputs the answer and an instruction to generate the manual based on the answer to a large-scale language model, and outputs the manual.

3. The first question unit presents the first question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the first question using the speech recognition means and obtains it as the answer. The second question unit presents the second question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the second question using the speech recognition means and obtains it as the answer. The third question unit presents the third question to the user using voice generated by the speech synthesis means, and recognizes the user's voice input in response to the third question using the speech recognition means and obtains it as the answer. The information processing system according to claim 1, wherein the fourth question unit presents the fourth question to the user using voice generated by a speech synthesis means, and the voice input by the user in response to the fourth question is recognized by a speech recognition means and obtained as the answer.

4. The information processing system according to claim 1, wherein the fourth question includes at least one of the following: a question asking for precautions regarding matters other than the user's actions; a question asking for the movements of each part of the user's body; a question requesting a quantitative expression of the user's actions; and a question requesting an expression of the user's actions using onomatopoeia or mimetic words.

5. The information processing system according to claim 4, wherein, if the fourth question includes a question that requires the user's actions to be expressed using onomatopoeia or mimetic words, the manual generation unit inputs an instruction to a large-scale language model to generate the manual including the answer and the onomatopoeia or mimetic words based on the answer, and outputs the manual.

6. A database storing a set of questions, including the first question, the second question, the third question, and the fourth question, for each industry or business type related to the aforementioned work, An acquisition unit that acquires the set of questions corresponding to the industry or business type selected by the user, The information processing system according to claim 1, comprising:

7. The computer in the information processing system A first question unit presents the user with a first question, which is a question concerning all the processes that make up the work, and obtains the user's answer to the first question. A second question unit presents the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtains the user's answer to the second question. A third question unit presents the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtains the user's answer to the third question. A fourth question unit presents the user with a fourth question, which is an additional question relating to the special process identified based on the answer obtained by the second question unit, and obtains the user's answer to the fourth question. A manual generation unit generates a manual based on the answers obtained by the first questioning unit, the third questioning unit, and the fourth questioning unit. A program that makes it function as such.

8. A first question step involves presenting the user with a first question, which is a question concerning all the processes that make up the work, and obtaining the user's answer to the first question. A second question step involves presenting the user with a second question, which is a question for identifying a specific step among all the steps that constitute the aforementioned work, and obtaining the user's answer to the second question. A third question step involves presenting the user with a third question, which is a question concerning the content of the work in each step that constitutes the aforementioned work, and obtaining the user's answer to the third question. A fourth questioning step involves presenting the user with a fourth question, which is an additional question relating to the special process identified based on the answers obtained in the second questioning step, and obtaining the user's answer to the fourth question. A manual generation unit step that generates a manual based on the answers obtained in the first question step, the third question step, and the fourth question step, Information processing methods, including those mentioned above.

Images