Information processing apparatus, information processing system, information processing method, and program

Abstract

To provide an information processor, an information processing system, an information processing method, and a program capable of improving efficiency by reducing time and effort in information processing.SOLUTION: The information processor 20 includes an acquiring unit 211 that acquires an operation instruction 5312a based on a natural language, a generating unit 213 that causes a generating AI to generate a predetermined numerical table using the operation instruction 5312a acquired by the acquiring unit 211 as input information for the generating AI, and a display control unit 214 that displays the numerical table generated by the generating unit 213 on the display unit 14 of the terminals 10.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

[0002] Conventionally, when creating a numerical table such as a budget proposal, it is common to create multiple numerical tables with different patterns in order to compare and consider different scenarios or approaches, or to diversify risks. However, creating a numerical table requires the user to carefully input the values ​​and formulas to be entered for each cell, and performing this task for each pattern is time-consuming for the user. Therefore, for example, Patent Document 1 describes a simulation budget creation device that assists in the creation of budget data based on simulation information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-117597 Summary of the Invention [Problem to be solved by the invention]

[0004] However, even if a simulation budget creation device such as that described in Patent Document 1 is used, creating multiple numerical tables requires many operations, which tends to place a burden on the user.

[0005] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an information processing device, an information processing system, an information processing method, and a program that can reduce the effort required to create a numerical table and improve efficiency. [Means for solving the problem]

[0006] In order to solve the above problem, the invention described in claim 1 is an information processing device, an acquisition unit that acquires operation instructions based on natural language from a terminal device; a generation unit that causes a generation AI that generates output information according to input information to generate output information for outputting numerical values ​​in a predetermined numerical table, using the operation instruction acquired by the acquisition unit as the input information; and a display control unit that causes a numerical table based on the output information to be displayed on a display unit of the terminal device.

[0007] The invention described in claim 2 is the information processing device described in claim 1, The generation unit causes the generation AI to generate program code for calculating the numerical values ​​in the predetermined numerical table, and executes the generated program code to calculate the numerical values ​​in the predetermined numerical table.

[0008] The invention described in claim 3 is the information processing device described in claim 2, The generation unit identifies a cell in the predetermined numerical table from the input information, and causes the generation AI to generate program code in which the numerical value of the identified cell becomes a numerical value based on the input information.

[0009] The invention described in claim 4 is the information processing device described in claim 3, an extraction unit that extracts text data from the file in a predetermined format acquired by the acquisition unit, The generation unit generates the output information based on the data content of the file in the predetermined format by inputting the text data extracted by the extraction unit to the generation AI.

[0010] The invention described in claim 5 is the information processing device described in claim 1, a storage unit that stores the plurality of operation instructions acquired by the acquisition unit in chronological order; When the generation unit receives a designation of any one of the plurality of operation instructions, it causes the generation AI to restore the numerical value table to the state it was in when the one operation instruction was acquired.

[0011] The invention described in claim 6 is the information processing device described in claim 1, an output unit that outputs the generated content of the generation unit; and a communication unit that transmits the output content of the output unit to another connected device.

[0012] The invention described in claim 7 is the information processing device according to any one of claims 1 to 6, an evaluation unit that receives an evaluation of the execution content of the generation AI; A transmission unit that transmits the evaluation received by the evaluation unit to the generation AI.

[0013] The invention described in claim 8 is the information processing device described in claim 7 which relies on claim 2, The evaluation unit includes a code input unit that accepts corrections to the program code generated by the generation AI.

[0014] The invention described in claim 9 is an information processing system, An information processing device according to any one of claims 1 to 6; a terminal device connected to the information processing device through a network, The terminal device includes an input unit for inputting the operation instruction and a display unit for displaying the predetermined numerical table.

[0015] The invention described in claim 10 is the information processing system described in claim 9, the input unit includes a voice input unit to which voice data is input, The acquisition unit acquires the operation instruction based on the voice data.

[0016] The invention described in claim 11 is an information processing method by an information processing device, an acquisition step of acquiring an operation instruction based on a natural language from a terminal device; a generation step of causing a generation AI that generates output information according to input information to generate output information for outputting a numerical value in a predetermined numerical table, using the operation instruction acquired in the acquisition step as the input information; and a display control step of displaying a numerical table based on the output information on a display unit of the terminal device.

[0017] The invention described in claim 12 is a program that causes a computer to function as an information processing device, an acquisition unit that acquires operation instructions based on natural language from a terminal device; a generation unit that causes a generation AI that generates output information according to input information to generate output information for outputting numerical values ​​in a predetermined numerical table, using the operation instruction acquired by the acquisition unit as the input information; The terminal device is caused to function as a display control unit that displays a numerical table based on the output information on a display unit of the terminal device. [Effects of the Invention]

[0018] According to the present invention, the time and effort required for creating a numerical table can be reduced, thereby improving efficiency. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a block diagram of an information processing system. [Figure 2] 10 is an example of a login screen. [Figure 3] 10 is an example of a management screen. [Figure 4] 10 is an example of a table creation screen. [Figure 5] 10 is an example of an output of a program code in a code output unit. DETAILED DESCRIPTION OF THE INVENTION

[0020] An information processing system including an information processing device according to an embodiment of the present invention will be described in detail below with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples. In the following description, components having the same functions and configurations will be assigned the same reference numerals and their description will be omitted.

[0021] [Overall configuration of information processing system] Fig. 1 is a block diagram showing the main configuration of an information processing system. An information processing system (hereinafter referred to as "system") 100 includes a terminal device (hereinafter referred to as "terminal") 10 and an information processing device (hereinafter referred to as "device") 20. The terminal 10 and the device 20 are connected to each other via a network N. Although Fig. 1 shows only one terminal 10, multiple terminals 10 may be connected to the device 20 at the same time.

[0022] (network) The network N may include various communication networks such as telephone networks, optical fibers, mobile communication networks, communication satellite networks, CATV (Community Antenna Television) networks, and other dedicated lines, as well as an Internet service provider (Internet) that connects them. The network N may also be a collective communication network in which various communication networks such as LANs (Local Area Networks), WANs (Wide Area Networks), WiFi (Wireless Fidelity), Bluetooth (registered trademark), and NFC (Near Field Communication) are interconnected so that they can communicate with each other. The connection method may be wired, wireless, or a combination of wired and wireless.

[0023] (Terminal Device) The terminal 10 is a device carried and used by each user of the system 100. The terminal 10 is a portable information terminal such as a smartphone or a tablet terminal. Alternatively, the terminal 10 is a terminal device such as a laptop computer (such as a notebook computer, a notebook, or an ultrabook) or a desktop PC.

[0024] Each terminal 10 uses a network N (such as a communication line of the terminal 10 or a wireless LAN) to communicate data with the device 20. The terminal 10 includes a control unit 11, a storage unit 12, a communication unit 13, a display unit 14, an input unit 15, and the like.

[0025] {Control Unit} The control unit 11 is a processor (computer) that has a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and controls the overall operation of each unit in the terminal 10. The CPU reads out programs such as apps (application programs) stored in the storage unit 12, expands them into the RAM, and executes the programs to perform various processes.

[0026] {Storage section} The storage unit 12 includes a nonvolatile semiconductor memory or the like, and stores programs such as apps, various data, etc. A web browser or program capable of executing the table creation process described below is installed on the terminal 10, and files for the web browser or program are stored in the storage unit 12. In this embodiment, the table creation process is described as being performed from the web browser.

[0027] {Communications Department} The communication unit 13 is configured by a communication interface, etc. The communication unit 13 transmits and receives data to and from the device 20 via the network N using a predetermined communication protocol.

[0028] {Display section} The display unit 14 includes a display device such as a liquid crystal display, etc. The display unit 14 displays various screens under the control of the control unit 11.

[0029] {Input section} The input unit 15 receives various input operations from the user. The input unit 15 includes an operation input unit 151 and a voice input unit 152.

[0030] <Operation input section> The operation input unit 151 is configured with an input device such as a mouse or a keyboard. The operation input unit 151 accepts an operation input from a user and outputs a signal corresponding to the operation input to the control unit 11. The operation input unit 151 may be configured with a touch panel integrated with the display unit 14.

[0031] <Audio input section> The voice input unit 152 is configured by, for example, a microphone. The voice input unit 152 collects voices uttered by the user and outputs the collected voices to the control unit 11.

[0032] (Information processing device) The device 20 is provided with functions necessary for the system 100. The device 20 includes a control unit 21, a storage unit 22, and a communication unit .

[0033] The device 20 is, for example, a cloud server realized by cloud computing such as Azure (registered trademark) provided by Microsoft Corporation, but is not limited to this. The device 20 may be a physical device or may be operated on-premise. Furthermore, when the device 20 is a physical device, the device 20 may be configured by multiple devices.

[0034] {Control Unit} The control unit 21 is composed of a CPU, RAM, etc. The CPU reads out various programs stored in the storage unit 22, loads them into the RAM, executes various processes in accordance with the loaded programs, and centrally controls the operation of each unit in the device 20. Note that the hardware resources such as the CPU, RAM, and storage unit 22 may be generated by virtualization technology.

[0035] In particular, the control unit 21 functions as an acquisition unit 211, an authentication unit 212, a generation unit 213, a display control unit 214, and an extraction unit 215 by the CPU executing a program.

[0036] <Acquisition Department> The acquisition unit 211 acquires, via the network N, information and data that are input by the input unit 15 of the terminal 10 and transmitted from the communication unit 13, via the communication unit .

[0037] As will be described later, when the user performs voice input via the voice input unit 152, it is preferable that the terminal 10 performs voice recognition processing on the voice data to acquire text data and transmits the text data to the device 20. However, the acquisition unit 211 may also perform voice recognition processing on the voice data acquired from the terminal 10 to convert it into text data.

[0038] Authentication Department The authentication unit 212 performs user authentication by comparing the authentication information (e.g., user ID and password) acquired by the acquisition unit 211 with reference data previously stored in user data 221 (described later) in the storage unit 22. The authentication unit 212 may also perform user authentication by reading the user ID from an IC card or the like carried by the user. The authentication information and reference data are not limited to the user ID and password, and may be, for example, the user's biometric information (fingerprint, iris, facial recognition data, etc.).

[0039] <Generation part> The generation unit 213 inputs predetermined input information to a generation AI (Artificial Intelligence) using a library such as LangChain, thereby acquiring and outputting predetermined output information. More specifically, when the generation unit 213 acquires from a user an operation instruction 5312a (see FIG. 4) for creating a predetermined numerical value table, the generation unit 213 generates a prompt for generating program code capable of calculating numerical values ​​in the numerical value table that satisfies the operation instruction 5312a, and inputs the generated prompt to the generation AI. When the generation AI generates the program code, the generation unit 213 executes the acquired program code. Furthermore, when the generation unit 213 acquires from a user an operation instruction 5312a for correcting the displayed numerical value table, the generation unit 213 identifies a cell to be corrected in the numerical value table, generates a prompt that satisfies the operation instruction 5312a, and executes the program code acquired from the generation AI.

[0040] An example of a generative AI is a text generation AI. The text generation AI is a language model trained to estimate and output the next token from an input token sequence, such as an attenuation model or a transfer model.

[0041] Examples of transfer models include, but are not limited to, GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). It is desirable that the input information, except for the evaluation input to the evaluation unit 5312c (see FIG. 4), described below, is trained so that it is not used as a new answer, and that highly confidential input information, such as personal information, is kept secret. The generation AI may also be trained (e.g., fine-tuned) specifically for generating table data.

[0042] The generation unit 213 according to this embodiment acquires output information from the network-connected generation AI from the input information acquired by the acquisition unit 211, for example, by using an API (Application Programming Interface) provided by a business that provides the generation AI. However, the method by which the generation unit 213 acquires output information from the generation AI is not limited to this configuration, and the information processing device 20 may be configured to include the generation AI.

[0043] Display control section The display control unit 214 transmits a predetermined display control signal to the terminal 10 based on the various programs and data stored in the storage unit 22, and causes the display unit 14 to display a desired image.

[0044] <Extraction part> The extraction unit 215 reads a spreadsheet data file written in a standardized format (for example, a file in Microsoft Excel (registered trademark) format) stored in external data 227 described later using the Pandas library of Python (registered trademark) or the like, extracts text data, and hands over the text data to the generation unit 213.

[0045] {Storage section} The storage unit 22 includes a hard disk drive (HDD), a nonvolatile semiconductor memory, etc. The storage unit 22 stores various programs and various data executed by the control unit 21. Note that at least a part of the various programs may be stored in the ROM of the control unit 21, etc.

[0046] The storage unit 22 stores a web server program, application programs, etc. The web server program communicates with a web browser or program installed in the terminal 10 using the HTTP protocol or the like, provides a website for using the system 100, and realizes the function of a web server. The application program runs on the web server and realizes various processes.

[0047] The storage unit 22 also stores user data 221, group data 222, company data 223, budget file data 224, budget table data 225, chat data 226, and external data 227.

[0048] <User Data> The user data 221 includes various information related to each user who connects to the device 20 using the terminal 10. The user data 221 stores reference data (user ID and password in this embodiment), user name, group ID, company ID, etc., associated with each user.

[0049] <Group Data> The group data 222 is data that defines the authority to table data for each group (for example, department) to which a user belongs. The group data 222 stores a group ID, group name, company ID, file data authority, etc., associated with each group. The file data authority is the authority to access specified file data on the management screen 52 (see FIG. 3), which will be described later.

[0050] <Company Data> For example, if the company to which a user belongs is made up of multiple group companies, the company data 223 is data that defines the authority to table data for each company to which the user belongs. The company data 223 stores the company ID, company name, and file data authority for each company in association with each other.

[0051] <Budget file data> The budget file data 224 stores a plurality of file data that manages a plurality of table data of a budget table that the user has generated using the system 100. The budget file data 224 stores a file ID and a file data name associated with each file data.

[0052] <Budget table data> Budget table data 225 stores table data of a budget table generated by a user using system 100. Budget table data 225 stores multiple table data linked to multiple file data, respectively. Budget table data 225 includes, for each table data, a table data ID, a table data name, the file ID of the linked file data, the creation date and time, the last update date and time, etc.

[0053] <Chat data> In the chat data 226, operation instructions 5312a and responses 5312b (see FIG. 4) are stored in chronological order corresponding to each table data.

[0054] External Data In the external data 227, the spreadsheet data file acquired by the acquisition unit 211 is stored.

[0055] {Communications Department} The communication unit 23 is configured by a communication module, etc. The communication unit 23 transmits and receives various signals and various data to and from the terminal 10 and other devices connected via the network N.

[0056] In addition, if the device 20 is a physical device, the device 20 may be provided with a configuration equivalent to the display unit 14 and input unit 15 of the terminal 10, so that operation input can be made directly to the device 20.

[0057] [Table creation process] The table creation process in this system 100 will be described with screen examples and screen transitions. First, when a user of the terminal 10 enters a specific URL represented by the IP information or the like of the device 20 into a web browser, the display control unit 214 causes the display unit 14 to display a login screen 51 as shown in Fig. 2. When the user inputs authentication information using the operation input unit 151 and sends it to the device 20, the authentication unit 212 performs authentication processing by comparing the authentication information acquired from the acquisition unit 211 with reference data stored in the user data 221, and determines whether or not to allow access.

[0058] (Management screen) If the authentication unit 212 permits access, the display control unit 214 displays a management screen 52 as shown in Fig. 3 on the display unit 14. The management screen 52 includes a file list 52a and a new registration button 52b. The display control unit 214 displays only file data corresponding to the user's authority information in the file list based on the user data 221, group data 222, company data 223, and budget file data 224.

[0059] (Registration screen) When the new registration button 52b is operated, the display control unit 214 transitions to a new file registration screen. When the file name, editing authority information, etc. are set on the registration screen, new file data is created.

[0060] (Dashboard screen) When a piece of file data is selected from the file list 52a on the management screen 52, or when new file data is created on the new file registration screen, the screen transitions to a dashboard screen for that file data. The dashboard screen displays a list of table data corresponding to that file data based on the budget file data 224 and the budget table data 225. On the other hand, if no corresponding table data exists, for example, when new file data is created, a button for creating new table data is displayed. When a piece of table data is selected on the dashboard screen, or when the button for creating new table data is operated, the screen transitions to a table creation screen 53.

[0061] (Table creation screen) Fig. 4 shows an example of table creation screen 53. As shown in Fig. 4, table creation screen 53 includes instruction section 531, table display section 532, and data linking section 533. On table creation screen 53, a numerical value table (budget proposal) is displayed in table display section 532 based on operation instruction 5312a input to instruction section 531.

[0062] {instruction section} <Instruction input section> The instruction unit 531 includes an instruction input unit 5311 and a chat unit 5312. The instruction input unit 5311 is a text box or the like into which the user inputs operational instructions 5312a. When operational instructions 5312a based on natural language are input into the instruction input unit 5311 and the send button is operated, the acquisition unit 211 acquires the operational instructions 5312a, and the generation unit 213 generates a prompt based on the operational instructions 5312a and inputs it to the generation AI.

[0063] The instruction input section 5311 is provided with a voice acquisition button, and when the voice acquisition button is operated, an operation instruction 5312 a is reflected based on the voice input to the voice input section 152 .

[0064] <Chat Club> Under the control of the display control unit 214, the chat unit 5312 displays a set of operation instructions 5312a to the generated AI that the user inputs into the instruction input unit 5311 and sends to the acquisition unit 211, and the response 5312b from the generated AI to the operation instructions 5312a.

[0065] [Evaluation Department] The display control unit 214 displays an evaluation unit 5312c together with each response 5312b. The evaluation unit 5312c receives an evaluation of the content of the response 5312b to the operation instruction 5312a and the operation (generation, calculation, correction, etc.) on the numerical table displayed in the table display unit 532 in accordance with the response 5312b. When the user operates the evaluation unit 5312c (clicks either the high rating button or the low rating button), the content of the operation is input to the generation AI via the acquisition unit 211 and the generation unit 213. The generation AI performs machine learning based on the input evaluation, thereby improving the accuracy of the response 5312b and the operation on the numerical table.

[0066] [Code output section] Furthermore, the display control unit 214 displays a code output section 5312d together with each response 5312b. When the code output section 5312d is operated, the display control unit 214 displays the program code generated by the generation AI along with the response 5312b, as shown in FIG. 5. By providing the code output section 5312d, the user can confirm whether the numerical table displayed in the table display section 532 is correct or not. After checking the program code, the user can evaluate the operation on the numerical table in the evaluation section 5312c. Note that, although FIG. 5 illustrates an example in which the program code is displayed in the chat section 5312, the display location of the program code is not limited to the chat section 5312. For example, when the code output section 5312d is operated, the program code may be configured to be displayed as a pop-up.

[0067] [Restoration section] Furthermore, the display control unit 214 displays a restoration section 5312e together with each response 5312b. When the restoration section 5312e is operated, the generation unit 213 generates a prompt to recreate the numerical value table based on the operational instructions 5312a up to the restoration section 5312e, inputs this to the generation AI, and executes the output program. The provision of the restoration section 5312e makes it possible to go back and correct the operation content, and even if there is an error in the operational instructions 5312a along the way, the numerical value table can be easily corrected.

[0068] {Table display section} Table display unit 532 displays a numerical value table based on the execution results of the program generated by generation AI based on operation instruction 5312a. Therefore, the contents of the numerical value table displayed in table display unit 532 change every time the user inputs operation instruction 5312a to apply a predetermined operation to the numerical value table into instruction input unit 5311 and the generation AI accepts a prompt based on operation instruction 5312a.

[0069] {Data Linkage Section} In response to a predetermined operation instruction 5312a, the data linking unit 533 displays output information generated by the extraction unit 215 extracting text data from the contents of the spreadsheet data file stored in the external data 227 and inputting it into the generation AI by the generation unit 213. In this embodiment, the generation unit 213 generates the base of the schema definition in the numerical value table as output information.

[0070] {Replication Department} Furthermore, the display control unit 214 displays a duplication unit 534 on the table creation screen 53. When the duplication unit 534 is operated, the control unit 21 generates duplicated table data by duplicating the table data currently being operated on, based on the operation instruction 5312a stored in the chat unit 5312. The duplicated table data is linked to the same file data as the table data from which it was copied.

[0071] Furthermore, replicated table data is independent of the original table data, so operations on replicated table data are not reflected in the original table data, and operations on the original table data are not reflected in the replicated table data.

[0072] By providing such a duplication unit 534, when it is desired to generate a plurality of table data pieces by changing only a portion of the data, it is not necessary to generate a plurality of table data pieces from scratch, thereby reducing the time and effort required.

[0073] {File output section} The display control unit 214 also displays a file output unit 535 on the table creation screen 53. When the file output unit 535 is operated, the control unit 21 applies, for example, a Python (registered trademark) library (Pandas, openpyxl, etc.) to the program that generates the numerical table currently displayed in the table display unit 532, and outputs the result as a spreadsheet data file (for example, a file in Microsoft Excel (registered trademark) format). In this configuration, the control unit 21 functions as an output unit. The file output by the output unit can be transmitted via the communication unit 23 to other systems connected to the system 100 via a network. Therefore, for example, budget proposals created by users in each department of each group company can be integrated with other budget management systems such as BizForecast (registered trademark) provided by Primal Corporation.

[0074] On the table creation screen 53 as described above, the table creation process proceeds, for example, as follows.

[0075] The user inputs into the instruction input unit 5311 operation instruction 5312a for creating a two-dimensional table in which the data contents of a file with a predetermined file name stored in the external data 227 are used as column headings in the data linking unit 533 and each month is used as row headings, and operates the send button. The acquisition unit 211 acquires the operation instruction 5312a, and the generation unit 213, in cooperation with the extraction unit 215, inputs the operation instruction 5312a and the text data of the file in the external data 227 to the generation AI as input information.

[0076] The generation unit 213, whose program code based on the input information acquires output information from the generation AI, executes the program code, and the display control unit 214 displays a numerical table with blank rows except for column headers and row headers in the table display unit 532 and the data linkage unit 533. In addition, the display control unit 214 displays operation instructions 5312a, responses 5312b, evaluation units 5312c, code output units 5312d, and restoration units 5312e in the chat unit 5312 in conjunction with the display of the numerical table.

[0077] Next, the user inputs operation instruction 5312a to the instruction input unit 5311 to set values ​​for each row (by quarter) in a desired column (consulting sales), for example, as shown in Fig. 4. The acquisition unit 211 transmits the operation instruction 5312a to the generation unit 213. Based on the operation instruction 5312a, the generation unit 213 identifies a cell in the numeric value table to be operated on, and inputs, as input information, a prompt to the generation AI to set the value of the identified cell to a predetermined value based on the operation instruction 5312a.

[0078] The generation unit 213 acquires program code based on the input information from the generation AI, executes the program code, and the display control unit 214 displays a numerical table with values ​​entered for each row in the desired column on the table display unit 532.

[0079] The user generates a desired budget plan by repeatedly inputting such operational instructions 5312a into the instruction input section 5311 on the table creation screen 53.

[0080] [Effects of the embodiment] As described above, the information processing device 20 according to this embodiment includes an acquisition unit 211 that acquires operation instructions 5312a based on natural language from the terminal 10, a generation unit 213 that causes a generation AI that generates output information according to input information to generate output information for outputting numerical values ​​in a predetermined numerical table, using the operation instructions 5312a acquired by the acquisition unit 211 as input information, and a display control unit 214 that displays the numerical table based on the output information on the display unit 14 of the terminal 10.

[0081] According to this configuration, if the necessary configuration of the numeric table is input, the desired numeric table is generated by the generation unit 213, and the user is not required to devise the numeric values ​​and formulas to be input for each cell, which reduces the user's effort in creating a budget proposal and improves efficiency. Also, in this configuration, since the generation AI operates the numeric table, flexible operations are possible, such as operation instructions 5312a based on values ​​of other items, such as "swap the SI sales value for April with the value for August," rather than being limited to operation instructions 5312a based on fixed values, such as "correct the SI sales value for April to 100,000."

[0082] Furthermore, the generation unit 213 causes the generation AI to generate program code that calculates numerical values ​​in a predetermined numerical value table, and executes the generated program code to calculate the numerical values ​​in the predetermined numerical value table. The generation unit 213 then identifies a cell in the predetermined numerical value table from the input information, and causes the generation AI to generate program code in which the value of the identified cell becomes a numerical value based on the input information. With this configuration, the numerical value table is drawn by executing the program, so that the numerical value table can be generated with high accuracy and efficiency even when the scale of the data being handled is large. Furthermore, the generation and modification of the numerical value table can be performed quickly.

[0083] Furthermore, the information processing device 20 according to this embodiment includes an extraction unit 215 that extracts text data from a file of a predetermined format acquired by the acquisition unit 211, and the generation unit 213 generates output information based on the data content of the file of the predetermined format by inputting the text data extracted by the extraction unit 215 into a generation AI. This configuration makes it possible to use the content of external files to create a numerical table, further reducing the user's workload and improving efficiency.

[0084] Furthermore, the information processing device 20 according to this embodiment includes a storage unit 22 that stores, in chronological order, the plurality of operation instructions 5312a acquired by the acquisition unit 211, and when the generation unit 213 receives the designation of any one of the plurality of operation instructions 5312a, causes the generation AI to restore the numerical value table at the time of acquisition of the one operation instruction. With this configuration, even if, for example, creation of a numerical value table is in progress due to an erroneous operation instruction 5312a, it is possible to restart creation of the numerical value table from immediately before input of the erroneous operation instruction 5312a.

[0085] In the information processing device 20 according to this embodiment, the control unit 21 functions as an output unit that outputs the generated content, and also includes a communication unit 23 that transmits the output content of the output unit to other connected devices. This configuration makes it possible to output the generated budget plan and manage it using an existing budget management system, further reducing the user's effort in creating a budget plan and improving efficiency.

[0086] The information processing device 20 according to this embodiment also includes an evaluation unit 5312c that receives an evaluation of the execution content of the generation AI, and a generation unit 213 that functions as a transmission unit that transmits the evaluation received by the evaluation unit 5312c to the generation AI. This configuration enables the generation AI to output a more accurate and appropriate response 5312b and program code.

[0087] [Other configurations] Although several embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and its equivalents.

[0088] For example, in the above example, the configuration in which user authentication is performed by the authentication unit 212 of the device 20 is exemplified, but this is not limiting. For example, a so-called single sign-on authentication method may be used in which authentication information acquired by the acquisition unit 211 is transmitted to an authentication server that stores reference data, whereby authenticated information is acquired from the authentication server. In this configuration, the storage unit 22 does not need to store the user data 221.

[0089] Furthermore, although the above describes an example of a configuration in which the extraction unit 215 reads a spreadsheet data file using the Pandas library, the present invention is not limited to this. The extraction unit 215 may read a spreadsheet data file by working with the generation unit 213 to generate and execute Pandas code using a generation AI. Furthermore, if the generation AI or its related API provides a function for reading a spreadsheet data file, the extraction unit 215 may read the spreadsheet data file by using the function.

[0090] In the above example, the generation unit 213 generates program code for drawing a numerical value table that satisfies the operation instruction 5312a, and displays the execution result of the program code on the table display unit 532. However, the present invention is not limited to this. For example, the numerical value table that satisfies the operation instruction 5312a may be drawn on the table display unit 532 in a text format.

[0091] Furthermore, when there is premise information common to each unit such as a "group" or a "company" (for example, monthly salary per employee in each department), a data item related to the premise information may be provided in the group data 222 or the company data 223. Then, when each generation unit 213 receives an input of an operation instruction 5312a, it may generate a prompt based on the premise information and input it to the generation AI.

[0092] In the above example, the control unit 21 outputs a numerical table as a spreadsheet data file when the file output unit 535 is operated, but this is not limiting. For example, if another budget management system provides an API for data linkage, the API may be used to output data to the budget management system without converting the data into a spreadsheet data file. Alternatively, if the other budget management system has a data table for data linkage, the table data may be directly reflected in the data table, thereby outputting the data to the budget management system.

[0093] Furthermore, when, for example, multiple table data (original table data and duplicated table data) are linked to one file data by operating the duplication unit 534 and stored in the budget table data 225, the display control unit 214 may perform control so as to highlight portions of the table data whose contents differ among the multiple table data on the table creation screen 53. Examples of types of highlighting include changing the cell format (background color, border, etc.) and changing the font typeface. Note that the highlighting method may be a predetermined one that the user can change as desired.

[0094] Furthermore, in the above example, the evaluation unit 5312c is configured with a thumbs-up button and a thumbs-down button, but this is not limiting. The evaluation unit 5312c is not limited to the thumbs-up button, and may also include an evaluation input unit for inputting detailed evaluations. If there is an error in the program code output result by the code output unit 5312d, the corrected program code may be input to the evaluation input unit. This configuration enables the generation AI to perform more appropriate learning, and more accurate responses 5312b and processing can be expected.

[0095] Furthermore, in the above example, the system 100 is used to create a budget proposal, but the present invention is not limited to this, and can be widely applied to the creation of spreadsheet data, mainly for business use. [Explanation of symbols]

[0096] 100 Information Processing Systems 10 Terminal Equipment 14 Display section 15 Input section 152 Audio input section 20 Information processing equipment 21 Control section (output section) 211 Acquisition Department 213 Generation unit (transmission unit) 214 Display control unit 215 Extraction part 22 Memory section 23 Communications Department 5312a Operating Instructions 5312b Response 5312c Evaluation Department

Claims

1. an acquisition unit that acquires operation instructions based on natural language from a terminal device; a generation unit that causes a generation AI to generate output information according to input information, using the operation instruction acquired by the acquisition unit as the input information, to generate output information for outputting numerical values ​​in a predetermined numerical table; a display control unit that displays a numerical table based on the output information on a display unit of the terminal device.

2. The information processing device according to claim 1 , wherein the generation unit causes the generation AI to generate program code for calculating the numerical values ​​in the predetermined numerical table, and calculates the numerical values ​​in the predetermined numerical table by executing the generated program code.

3. The information processing device according to claim 2, wherein the generation unit identifies a cell in the specified numerical table from the input information and causes the generation AI to generate program code in which the numerical value of the identified cell becomes a numerical value based on the input information.

4. an extraction unit that extracts text data from the file in a predetermined format acquired by the acquisition unit, The information processing device according to claim 3 , wherein the generation unit generates the output information based on the data content of the file in the predetermined format by inputting the text data extracted by the extraction unit to the generation AI.

5. a storage unit that stores the plurality of operation instructions acquired by the acquisition unit in chronological order; The information processing apparatus according to claim 1 , wherein the generation unit, when receiving a designation of any one of the plurality of operation instructions, causes the generation AI to restore the numerical value table to the state at the time of acquisition of the one operation instruction.

6. an output unit that outputs the generated content of the generation unit; The information processing apparatus according to claim 1 , further comprising: a communication unit that transmits the output content of the output unit to another connected apparatus.

7. an evaluation unit that receives an evaluation of the execution content of the generated AI; The information processing device according to claim 1 , further comprising: a transmission unit that transmits the evaluation received by the evaluation unit to the generation AI.

8. The information processing device according to claim 7 , which cites claim 2 , wherein the evaluation unit includes a code input unit that accepts corrections to the program code generated by the generation AI.

9. An information processing device according to any one of claims 1 to 6; a terminal device connected to the information processing device through a network, The terminal device is an information processing system including an input unit for inputting the operation instruction and a display unit for displaying the predetermined numerical table.

10. the input unit includes a voice input unit to which voice data is input, The information processing system according to claim 9 , wherein the acquisition unit acquires the operation instruction based on the voice data.

11. An information processing method by an information processing device, an acquisition step of acquiring an operation instruction based on a natural language from a terminal device; a generation step of causing a generation AI to generate output information according to input information, using the operation instruction acquired in the acquisition step as the input information, to generate output information for outputting a numerical value in a predetermined numerical table; and a display control step of displaying a numerical table based on the output information on a display unit of the terminal device.

12. A program that causes a computer to function as an information processing device, an acquisition unit that acquires operation instructions based on natural language from a terminal device; a generation unit that causes a generation AI that generates output information according to input information to generate output information for outputting numerical values ​​in a predetermined numerical table, using the operation instruction acquired by the acquisition unit as the input information; A program that functions as a display control unit that displays a numerical table based on the output information on a display unit of the terminal device.

Images