Information processing method, program, and information processing system

Abstract

To provide an information processing method, a program, and an information processing system for obtaining answers from a trained model while reducing the input burden on a user.SOLUTION: According to an information processing method according to one embodiment, the information processing method is executed by an information processing device and includes an information acquisition step of acquiring information stored in a storage unit, an input information generation step of generating input information for being input to a trained model based on the information acquired in the information acquisition step, and an input information output step of outputting the input information.SELECTED DRAWING: Figure 11

Description

[Technical Field]

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

[0002] Cited Document 1 discloses an information processing method related to natural language processing, which outputs, in response to a question input by a user, question candidates corresponding to the question and options for the user to request output of other question candidates on a display screen, accepts a user's selection from the question candidates and options output on the display screen, and outputs an answer based on the user's selection. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-135135 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the case of the above-mentioned prior art, since the question content input by the user is required, if the user does not think of asking a question, naturally no answer can be obtained. In other words, even if an attempt is made to improve business efficiency by using answers using an information processing method, if the user does not think of asking a question in the first place, no answer can be obtained using the information processing method, and in this respect there is room for improvement.

[0005] Taking the above facts into consideration, the present invention aims to obtain answers from a trained model while reducing the input burden on the user. [Means for solving the problem]

[0006] According to one embodiment of an information processing method, the information processing method is executed by an information processing device and includes an information acquisition step of acquiring information stored in a storage unit, an input information generation step of generating input information to be input to a trained model based on the information acquired in the information acquisition step, and an input information output step of outputting the input information.

[0007] According to one embodiment of the program, an information processing device is caused to execute an information processing method including an information acquisition step of acquiring information stored in a storage unit, an input information generation step of generating input information to be input to a trained model based on the information acquired in the information acquisition step, and an input information output step of outputting the input information.

[0008] According to one embodiment, the information processing system is executed by an information processing device, and includes an information acquisition unit that acquires information stored in a storage unit, an input information generation unit that generates input information to be input to a trained model based on the information acquired by the information acquisition unit, and an input information output unit that outputs the input information. [Effects of the Invention]

[0009] According to one embodiment, answers can be obtained from a trained model while reducing the input burden on the user. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server according to an embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to an embodiment. [Figure 4] FIG. 1 is a diagram illustrating an example of a processing flow of an information processing system according to an embodiment. [Figure 5] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 6] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 7] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 8] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 9] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 10] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 11] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. [Figure 12] 10A and 10B are diagrams illustrating an example of an input and output screen of a user terminal according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] An embodiment of an information processing system according to the present invention will be described below with reference to Figures 1 to 12. The same or equivalent components and parts in each figure are denoted by the same reference numerals. The dimensional proportions in the drawings are exaggerated for the sake of explanation and may differ from the actual proportions.

[0012] (System Overview) First, an overview of an information processing system 10 according to this embodiment will be described. The information processing system 10 according to this embodiment is an information processing system for obtaining a processing result using a trained model 222. This information processing system 10 obtains a processing result based on a prompt obtained by inputting a prompt as input information into a large-scale language model serving as a trained model 222 that has been trained with a large amount of text data from online articles, books, websites, and the like. Furthermore, the information processing system 10 is configured to generate at least a portion of the prompt to be input into the trained model 222 based on information regarding the content that a user U wishes to process, and present this to the user U to assist input. Therefore, even if a user U is unable to input an appropriate prompt for the desired processing result, the trained model 222 can obtain the desired processing result.

[0013] (System Configuration) Fig. 1 is a diagram showing an example of the configuration of an information processing system 10 according to this embodiment. As shown in Fig. 1, the information processing system 10 according to this embodiment includes a server 12 and a user terminal 14, which are connected to each other so as to be able to communicate with each other via a network N. The network N is, for example, a wired local area network (LAN), a wireless LAN, the Internet, a public line network, a mobile data communication network, or a combination thereof.

[0014] The user terminal 14 is an example of an information processing device that is operated by a user U to input and display various information. The user terminal 14 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, a wearable device, or a combination of these.

[0015] The server 12 is an example of an information processing device that acquires information input from the user terminal 14, processes the information, and outputs the results. The server 12 may be a PC (Personal Computer), a smartphone, a tablet terminal, a server device, a microcomputer, or a combination of these. The specific configuration and operation of the server 12 will be described later.

[0016] (Hardware configuration) 2 is a block diagram showing the hardware configuration of the server 12. The server 12 includes a processor 120, a memory 122, a storage 124, a communication I / F 126, an input / output I / F 128, and a drive device 134, which are communicatively connected to each other via a bus B.

[0017] The processor 120 controls each component of the server 12 and realizes the functions of the server 12 by loading various programs stored in the storage 124 into the memory 122 and executing them. The programs executed by the processor 120 include, but are not limited to, an operating system (OS) and a program 220 described below. Execution of these programs by the processor 120 realizes part of the state visualization method according to this embodiment. The processor 120 is, for example, a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a digital signal processor (DSP), or a combination thereof.

[0018] The memory 122 is, for example, a read-only memory (ROM), a random access memory (RAM), or a combination thereof. The ROM is, for example, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a combination thereof. The RAM is, for example, a dynamic random access memory (DRAM), a static random access memory (SRAM), a magnetoresistive random access memory (MRAM), or a combination thereof.

[0019] The storage 124 stores the OS, various programs described below, and various data. The storage 124 is, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a storage class memory (SCM), or a combination of these.

[0020] The communication I / F 126 is an interface for connecting the server 12 to external devices, including the user terminal 14 and the image capturing device 16, via the network N and for controlling communication. The communication I / F 126 is, for example, an adapter compliant with Bluetooth (registered trademark), Wi-Fi (registered trademark), ZigBee (registered trademark), Ethernet (registered trademark), or optical communication (e.g., Fibre Channel), but is not limited to these.

[0021] The input / output I / F 128 is an interface for connecting an input device 132 and an output device 130 to the server 12. The input device 132 is, for example, a mouse, a keyboard, a touch panel, a microphone, a scanner, a camera, various sensors, an operation button, or a combination thereof. The output device 130 is, for example, a display, a projector, a printer, a speaker, a vibrator, or a combination thereof.

[0022] The drive device 134 reads and writes data from and to the disk media 136. The drive device 134 is, for example, a magnetic disk drive, an optical disk drive, a magneto-optical disk drive, or a combination thereof. The disk media 109 is, for example, a compact disc (CD), a digital versatile disc (DVD), a floppy disk (FD), a magneto-optical disk (MO), a Blu-ray (registered trademark) disc (BD), or a combination thereof.

[0023] In this embodiment, the program may be written into memory 122 or storage 124 during the manufacturing stage of server 12, may be provided to server 12 via network N, or may be provided to server 12 via a non-transitory computer-readable recording medium such as disk media 136.

[0024] Furthermore, the hardware configuration of the user terminal 14 is substantially the same as the hardware configuration of the server 12 described above, and therefore a detailed description thereof will be omitted.

[0025] (Functional configuration) Next, the functional configuration of the server 12 will be described. Fig. 3 is a diagram showing an example of the functional configuration of the server 12. When executing various programs, the server 12 uses the above-mentioned hardware resources to realize various functions. The server 12 has a communication unit 20, a storage unit 22, and a control unit 24 as the functional configuration realized by the server 12. Each functional configuration is realized by the processor 120 reading and executing a program 220 stored in the memory 122 or the storage 124.

[0026] The communication unit 20 is realized by the communication I / F 126. The communication unit 20 transmits and receives information to and from the user terminal 14 via the network N. The communication unit 20 receives information input from the user terminal 14. The communication unit 20 also transmits information to the user terminal 14 and receives requests from the user U from the user terminal 14.

[0027] The storage unit 22 is realized by the memory 122 and the storage 124. The storage unit 22 stores a program 220, a trained model 222, a prompt DB 224, a user information DB 226, and a processing result DB 228.

[0028] The trained model 222 is composed of at least one trained machine learning model. As described above, the trained model 222 is, for example, a large-scale language model trained on a large amount of text data from internet articles, books, websites, etc. When text data called a prompt is input, the trained model 222 executes information processing according to the prompt, generates various data including the text data as a result, and outputs the data as a processing result RS.

[0029] Furthermore, when the trained model 222 receives information stored in the storage unit, it generates a prompt that matches the information. That is, the trained model 222 acquires information about user U (details of which will be described later) stored in the user information DB 226 as part of the storage unit, and uses the information to predict the next action that user U may take and the information that user U may need. Based on the results of this prediction, the trained model 222 generates a prompt for executing the required process or the process that it can support. Specifically, when information about user U that "is a member of the intellectual property department" is acquired from the user information DB 226, the trained model 222 predicts, based on the information, that the next action that a member of the intellectual property department may take is, for example, "research prior art related to new business," "research the patent application status of competitors," "check the rights status of the company's patent," "translation for foreign patent application," "communication with patent offices," or "preparation for inventor interview." For example, based on the inference result "prior art research related to new business," the trained model 222 generates a prompt saying, "Please research and summarize the latest patent information and technological trends in the XX field." Note that the "XX field..." in the prompt may be left blank or a placeholder to allow the user U to input additional information about the field. This additional information input by the user U corresponds to the "additional input information" described in claim 6 (see AD in Figure 11; the two-dot chain line indicating the template TP in the figure is added for illustrative purposes and is not actually displayed. The additional input information AD is text data other than the template TP). In other words, the trained model 222 can generate not only all prompts but also at least some prompts that leave room for input of additional information. At least some of these prompts correspond to the prompt template TP (see Figure 10). The template TP with the additional input information AD input corresponds to the prompt.

[0030] Furthermore, in the specific example described above, the next action that user U may take and the information that user U will need are estimated from information about user U stored in the user information DB 226 as part of the storage unit. However, this is not limited to this. Alternatively, the next action that user U may take and the information that user U will need may be estimated from information in a database that serves as part of the storage unit and stores various information linked to other applications, such as a calendar application, an office work application, or a customer management system. That is, at least one of the next action that user U may take and the information that user U will need may be estimated based on user U's schedule information linked to a calendar application. Specifically, when schedule information about a meeting is acquired from the schedule information, the next action that user U may take and the information that user U will need from the meeting may be estimated, such as "writing minutes," "researching the agenda," "sending an email to contact attendees," and "latest information on legal amendments related to the agenda." At least a portion of the prompts for performing processing that the trained model 222 can support for each estimation result may be generated. In addition, at least one of the next action that user U may take and the information that user U will need may be estimated based on business negotiation information linked to a customer management system. Specifically, when business negotiation information is acquired, the next actions that user U can take and information that user U will need are inferred from the information, such as "send a follow-up call or email," "conduct a demo or presentation," "conduct a demo or presentation," "prepare and review a contract," "analyze customer needs and readjust the proposal," "basic customer information," "history of past interactions," "current stage of the business negotiation," "detailed business negotiation information," "competitor information," and "customer decision-making process."Then, for each inference result, the trained model 222 generates at least a portion of a prompt for performing a process that can be supported (for example, a process that can be supported for the inferred result "send a follow-up call or email" is "create a draft email").

[0031] The user information 226 is a database that stores various information about a user U who has registered to use the information processing system 10. Specific examples of the various information about the user U include user identification information for unique identification, user preference information such as interest information, user history information including past usage status, and user attribute information such as occupation and job title.

[0032] The processing result DB 228 is a database that stores information indicating the results of processing based on a prompt (processing result RS). The processing result RS is various information including text information and image information, and the processing result DB 228 stores the processing result RS, the prompt, and information acquired from the storage unit, all linked to one another.

[0033] The control unit 24 is realized by the processor 120 reading and executing the program 220 from the memory 122 (see FIG. 2) and working in cooperation with other hardware components. The control unit 24 includes an information acquisition unit 242, an information processing unit 244, and an output unit 246.

[0034] The information acquisition unit 242 acquires various information required for processing by the information processing unit 244. Specifically, the information acquisition unit 242 acquires information stored in a storage unit, including the memory unit 22 and an external database connected for communication, information about the content that the user U wants to process, and additional input information. In this embodiment, the information about the content that the user U wants to process is the information about the category of processing displayed on the screen (see FIG. 5, corresponding to "Suggest how to use the generated AI based on your calendar," "Suggest how to use the generated AI based on linked customer management software," "Suggest how to use the generated AI based on recently used files," and "Suggest how to use the generated AI based on emails and messages") selected by the user U (see FIG. 6, "Suggest how to use the generated AI based on your calendar" selected by "you," i.e., "information about the content that the user U wants to process"). Note that the information about the content that the user U wants to process is not limited to this, and may be information specified by text data, or information obtained using various sensors such as voice input, gestures, hardware operations, eye tracking, and biometric sensors.

[0035] To acquire additional information, the information acquisition unit 242 displays a prompt template TP having blanks or placeholders (blanks in the example of FIG. 10) as shown in Fig. 10, and acquires additional input information AD (see Fig. 11) input by the user U to fill in the blanks in the template TP. Note that the additional input information AD is not limited to text data, and may be information such as images, videos, audio, and UI operation results.

[0036] The information processing unit 244 performs information processing using the trained model 222. Specifically, as described above, the information processing unit 244 acquires various pieces of information stored in the storage unit and, from the information, infers the next action (movement) that an entity related to the information, such as user U, may take, and the information that user U will need. Furthermore, based on the inference results, the information processing unit 244 generates a prompt or a prompt template TP for the trained model 222 to execute the required processing or the processing that can be supported. In other words, the information processing unit 244 corresponds to the "input information generation unit" recited in claim 9. Furthermore, the information processing unit 244 executes information processing according to the prompt and information related to the content that user U wants to process, and generates various data including text data as a result, and outputs the data as a processing result RS.

[0037] The output unit 248 controls the information processing unit 244 so that the processing result is output to the user terminal 14. In other words, the information processing unit 244 corresponds to the "input information output unit" recited in claim 9.

[0038] (Processing performed by information processing system 10) Next, the operation of the information processing system 10 will be described. Fig. 4 is a flowchart showing an example of the flow of processing by the information processing system 10. The processor 120 reads out the program 220 stored in the storage 124, expands it in the memory 122, and executes it, thereby performing processing. Note that when the processor 120 receives operation information to terminate the operation of the information processing system 10, or information on the termination of an operation from the user terminal 14 during the ongoing determination processing (these will be simply referred to as "termination operations"), the processor 120 terminates the processing based on the program 220 that is currently being processed.

[0039] The processor 120 outputs information regarding the content that the user U wants to process that can be processed by the server 12 to be displayed on the user terminal 14 (see Figure 5), and also acquires the input information regarding the content that the user U wants to process (step S100, see Figure 6).

[0040] The processor 120 acquires information from the storage unit (step S102) and analyzes the acquired information (step S104). Then, the processor 120 determines whether or not the next possible action of the subject related to the information can be inferred from the analysis result (step S106). If the next possible action cannot be inferred (step S106: NO), the processor 120 proceeds to step S110, which will be described later. On the other hand, if the next possible action can be inferred (step S106: YES), the processor 120 outputs the inference result (the inference results correspond to "research" in FIG. 7, "draft email" in FIG. 8, and "write minutes" in FIG. 9), and generates a prompt or template TP based on the next possible action selected by the user U from the inference results (for example, by operating the "Use generation AI with this method" button in FIGS. 7-9) (step S108). The processing in step S102 described above corresponds to the "information acquisition step" recited in claim 1.

[0041] The processor 120 determines whether or not other necessary information can be inferred from the analysis result in step S104 (step S110). If the necessary information cannot be inferred (step S110: NO), the processor 120 proceeds to step S114, which will be described later. On the other hand, if the necessary information can be inferred (step S110: YES), the processor 120 generates a prompt or template TP related to the necessary information (such as acquisition or support) (step S112). The processes from step S104 to step S112 described above correspond to the "input information generation step" recited in claim 1.

[0042] The processor 120 determines whether a prompt or template TP has been generated (step S114). If not (step S114: NO), the processor 120 proceeds to step S100. On the other hand, if generated (step S114: YES), the processor 120 outputs the prompt or template TP to be displayed on the user terminal 14 (step S116), and also outputs an additional input information screen IE (see FIG. 10) to be displayed on the user terminal 14 (step S118). The processes from step S112 to step S116 described above correspond to the "input information output step" recited in claim 1.

[0043] The processor 120 determines whether additional input information AD has been input by the user U and acquired (step S120). If additional input information AD has not been acquired (step S120: NO), the processor 120 inputs a prompt or template TP into the trained model 222 without the additional input information AD and performs processing (step S126), and proceeds to step S124. On the other hand, if additional input information AD has been acquired (step S120: YES), the processor 120 inputs the prompt or template TP, including the additional input information AD, into the trained model 222 and performs processing (step S122).

[0044] The processor 120 acquires the processing result RS (step S124) and outputs the processing result RS to the user terminal 14 for display (step S128, see FIG. 12). Then, the processor 120 determines whether or not an instruction to end the processing based on the program 220 has been given (step S130). If no instruction has been given (step S130: NO), the processor 120 proceeds to step S100. On the other hand, if an instruction has been given (step S130: YES), the processor 120 ends the processing based on the program 220. The processing from step S120 to step S126 described above corresponds to the "processing steps" recited in claim 7.

[0045] (Effects of one embodiment) The information processing system 10 according to this embodiment includes an information acquisition step of acquiring information stored in a storage unit, an input information generation step of generating at least a part of a prompt to be input to the trained model 222 based on the information acquired in the information acquisition step, and an input information output step of outputting a prompt, so that the user U can use a prompt that suits the situation or state of the user U without having to think about it from scratch. This allows the user U to obtain an answer from the trained model while reducing the input burden on the user U.

[0046] Furthermore, the input information generation step infers the next action from the information acquired in the information acquisition step and generates at least a part of the prompt from the inference result, so that the user U can use a prompt that is more suited to the situation or state of the user U without having to think about it from scratch. This allows the user U to obtain an answer from the trained model 222 while further reducing the input burden on the user U.

[0047] Furthermore, the input information generation step infers necessary information from the information acquired in the information acquisition step and generates at least a part of the prompt from the inference result, so that the user U can use a prompt that suits the situation or state of the user U without having to think about it from scratch. This allows the user U to obtain an answer from the trained model 222 while further reducing the input burden on the user U.

[0048] Furthermore, the input information generation step estimates at least one of the next action and the required information based on the schedule information stored in the storage unit, and generates at least a part of the prompt from the estimation result, so that the user U can use a prompt that more specifically suits the situation or state of the user U without having to think about it from scratch. This allows the user U to obtain an answer from the trained model 222 while further reducing the input burden on the user U.

[0049] Furthermore, the input information generation step estimates at least one of the next action and the required information based on the negotiation information stored in the storage unit, and generates at least a part of the prompt from the estimation result, so that the user U can use a prompt that is more specifically suited to the situation or state of the user U without having to think about it from scratch. This allows the user U to obtain an answer from the trained model 222 while further reducing the input burden on the user U.

[0050] Furthermore, the input information generation step presents at least a part of the generated prompt and acquires additional input information AD to be input to the trained model 222, and the input information output step outputs at least a part of the prompt and the additional input information AD, so that the user U or the like can issue instructions to the trained model 222 for processing that is more suited to their own situation or state. This makes it easier for the user U or the like to obtain the processing result they desire.

[0051] Furthermore, since the method includes a processing step of acquiring the processing results of inputting the output results from the input information output step into a trained model, the answer obtained from the trained model can be used.

[0052] In the above-described embodiment, the next action that user U may take and the information that user U will need are predicted based on various information linked to the calendar application and the customer management system application. However, this is not limited to this. The next action that user U may take and the information that user U will need may also be predicted based on various information linked to other applications, such as office work applications, email applications, and message applications. Specifically, in the case of various information linked to office work applications for document creation, spreadsheets, and presentations, the next action that user U may take and the information that user U will need are predicted based on information such as "document creation and revision," "data analysis and reporting," "presentation creation and implementation," "schedule management and task management," "collaborative editing and feedback collection," "resource planning and management," "basic information about the file," "metadata related to the file content," "usage history and access history," "related files and materials," "instructions and feedback," and "templates and standard formats." Then, for each prediction result, at least a portion of prompts for performing processing that the trained model 222 can support is generated. Specifically, for the prediction result of "document creation and revision," a process for supporting document proofreading is performed. Specifically, this process points out typos and grammatical errors in the document provided by the user. An example of a prompt (including template TP) generated in the input information generation step to execute this process is, "Please proofread the document (specified by the user as additional input information). Please point out any typos or grammatical errors."

[0053] In addition, for the estimation results of "Data Analysis and Reporting," a process is performed to support the creation of a pivot table of data, for example. Specifically, a pivot table that displays monthly sales totals is created based on the dataset provided by the user. An example of a prompt (including template TP) generated in the input information generation step to execute this process is "Please create a pivot table that displays monthly sales totals from the dataset (specified by the user as additional input information)."

[0054] Furthermore, for the estimation results of "Creating and delivering a presentation," a process is performed to support slide design improvement, as an example. Specifically, the process provides improvements to make the presentation materials provided by the user more visually appealing. An example of a prompt (including template TP) generated in the input information generation step to perform this process is "How can I make the presentation slides (specified by the user as additional input information) more visually appealing?"

[0055] Furthermore, for the estimation results of "schedule management and task management," a process is performed to support the creation of a task list and the setting of reminders, for example. Specifically, a list for managing task progress, deadlines, and resources is created based on the project plan provided by the user, and reminders are set. An example of a prompt (including template TP) generated in the input information generation step to perform this process is "Please create a project task list and deadlines for each task (specified by the user as additional input information) using spreadsheet software, and set reminders."

[0056] In addition, for the estimation result of "collaborative editing and feedback collection," a process is performed to support the setting up of an online document for collaborative editing, as an example. Specifically, the user saves the document file in a storage unit, generates a link for collaborative editing, and shares it with the team. An example of a prompt (including a template TP) generated in the input information generation step to execute this process is "Save the document file (specified by the user as additional input information) in a storage unit, create a link for collaborative editing, and share it with the team."

[0057] Furthermore, for the estimation results of "resource planning and management," a process is performed to support the creation of a resource allocation table, for example. Specifically, a resource (personnel and budget) allocation table is created using spreadsheet software based on the project plan provided by the user. An example of a prompt (including template TP) generated in the input information generation step to execute this process is "Please create a resource (personnel and budget) allocation table using spreadsheet software based on the project plan (specified by the user as additional input information)."

[0058] Furthermore, as an example, a process is performed to support the extraction of file metadata from the estimation results of the "basic file information." Specifically, basic information such as file name, creation date, and last update date for all files in the folder is listed. An example of a prompt (including template TP) generated in the input information generation step to perform this process is "Please list the file name, creation date, and last update date for all files in the folder (specified by the user as additional input information)."

[0059] In addition, for example, a process is performed to support summarization of document contents based on the estimated results of "metadata related to file contents." Specifically, the main sections and their contents are summarized based on the document file provided by the user. An example of a prompt (including template TP) generated in the input information generation step to perform this process is "Please summarize the main sections and contents of the document file (specified by the user as additional input information)."

[0060] Furthermore, for the estimated results of "usage history and access history," a process is performed to assist in checking the editing history of a file, for example. Specifically, the editing history of a sheet in a specific spreadsheet software is displayed, and it is possible to check who changed what data and when. An example of a prompt (including template TP) generated in the input information generation step to perform this process is "Please display the editing history of the sheet in the spreadsheet software (specified by the user as additional input information) and tell me who changed what data and when."

[0061] Furthermore, for the estimation results of "related files and materials," a process is performed to support the creation of a link collection of related materials, for example. Specifically, a link collection of files and materials related to the project is created. An example of a prompt (including template TP) generated in the input information generation step to execute this process is "Please create a link collection of files and materials related to the project (specified by the user as additional input information)."

[0062] Furthermore, for the estimated results of "instructions and feedback," a process is performed to support the collection and organization of feedback, as an example. Specifically, feedback on the report is collected from the team, and the main points are organized and compiled into a list. An example of a prompt (including template TP) generated in the input information generation step to execute this process is "Please collect feedback on the report (instructed by the user as additional input information) from the team, organize the main points, and compile them into a list."

[0063] Furthermore, for the estimation results of "templates and standard formats," a process is performed to support template customization, as an example. Specifically, a standard proposal template is used to create a customized version for future projects. An example of a prompt (including template TP) generated in the input information generation step to perform this process is, "Please create a customized version for future projects using the proposal template (specified by the user as additional input information)." Although several specific examples have been given above, the estimation results, processes that can be supported, and prompts (including template TP) are not limited to these.

[0064] <Additional Notes> The present embodiment includes the following disclosure.

[0065] (Appendix 1) An information processing method executed by an information processing device, an information acquisition step of acquiring information stored in the storage unit; an input information generation step of generating at least a portion of input information to be input to the trained model based on the information acquired in the information acquisition step; an input information output step of outputting the input information; An information processing method including:

[0066] (Appendix 2) the input information generating step infers a next action from the information acquired in the information acquiring step, and generates at least a part of the input information from an inference result. 1. The information processing method described in Appendix 1.

[0067] (Appendix 3) The input information generating step estimates necessary information from the information acquired in the information acquiring step, and generates at least a part of the input information from the estimation result. 1. An information processing method according to claim 1 or 2.

[0068] (Appendix 4) the input information generating step includes estimating at least one of a next action and necessary information based on schedule information stored in a storage unit, and generating at least a part of the input information from an estimation result. An information processing method according to any one of Supplementary Notes 1 to 3.

[0069] (Appendix 5) the input information generating step predicts at least one of a next action and necessary information based on the negotiation information stored in the storage unit, and generates at least a part of the input information from a prediction result. An information processing method according to any one of Supplementary Notes 1 to 4.

[0070] (Appendix 6) The input information generation step presents at least a portion of the generated input information and acquires additional input information to be input to the trained model; the input information output step outputs at least a part of the input information and the additional input information. An information processing method according to any one of Supplementary Notes 1 to 5.

[0071] (Appendix 7) and a processing step of acquiring a processing result obtained by inputting the output result in the input information output step into the trained model. An information processing method according to any one of Supplementary Notes 1 to 6.

[0072] (Appendix 8) In the information processing device, an information acquisition step of acquiring information stored in the storage unit; an input information generation step of generating at least a portion of input information to be input to the trained model based on the information acquired in the information acquisition step; an input information output step of outputting the input information; A program for executing an information processing method including the steps of:

[0073] (Appendix 9) An information processing system executed by an information processing device, an information acquisition unit that acquires the information stored in the storage unit; an input information generation unit that generates at least a portion of input information to be input to the trained model based on the information acquired by the information acquisition unit; an input information output unit that outputs the input information; An information processing system having the above.

[0074] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. Furthermore, the present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0075] 10 Information Processing Systems 220 Programs 222 trained models 242 Information Acquisition Department TP template (at least part of the input information) AD Additional input information RS processing result

Claims

1. An information processing method executed by an information processing device, an information acquisition step of acquiring information stored in the storage unit; an input information generation step of generating at least a portion of input information to be input to the trained model based on the information acquired in the information acquisition step; an input information output step of outputting the input information; An information processing method including:

2. the input information generating step infers a next action from the information acquired in the information acquiring step, and generates at least a part of the input information from an inference result. The information processing method according to claim 1 .

3. The input information generating step estimates necessary information from the information acquired in the information acquiring step, and generates at least a part of the input information from the estimation result. The information processing method according to claim 1 .

4. the input information generating step includes estimating at least one of a next action and necessary information based on schedule information stored in a storage unit, and generating at least a part of the input information from an estimation result. The information processing method according to claim 1 .

5. the input information generating step predicts at least one of a next action and necessary information based on the negotiation information stored in the storage unit, and generates at least a part of the input information from a prediction result. The information processing method according to claim 1 .

6. The input information generation step presents at least a portion of the generated input information and acquires additional input information to be input to the trained model; the input information output step outputs at least a part of the input information and the additional input information. The information processing method according to claim 1 .

7. and a processing step of acquiring a processing result obtained by inputting the output result in the input information output step into the trained model. The information processing method according to claim 1 .

8. In the information processing device, an information acquisition step of acquiring information stored in the storage unit; an input information generation step of generating at least a portion of input information to be input to the trained model based on the information acquired in the information acquisition step; an input information output step of outputting the input information; A program for executing an information processing method including the steps of:

9. An information processing system executed by an information processing device, an information acquisition unit that acquires the information stored in the storage unit; an input information generation unit that generates at least a portion of input information to be input to the trained model based on the information acquired by the information acquisition unit; an input information output unit that outputs the input information; An information processing system having the above.

Images