Information processing device and information processing method

Abstract

This information processing device (10) comprises: a reception unit (11) that receives generation request information about an answer sentence to a question sentence pertaining to a business of a target user; an acquisition unit (12) that acquires attribute information about the target user pertaining to the business; an extraction unit (13) that extracts, from a plurality of pieces of business data registered in advance or acquired from a business tool, corresponding business data that is related to the generation request information and corresponds to the attribute information; and an output unit (14) that outputs an input sentence for a prompt for instructing to generate the answer sentence on the basis of the extracted corresponding business data, the attribute information, and the generation request information.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] Remote work is now widespread, and to facilitate the smooth execution of work during remote work, SaaS (Software as a Service), known as "Software as a Service," which makes necessary functions available as a service in the amounts needed, is being used in a wide variety of fields. Examples include the communication tool Slack (registered trademark), the document management tool Notion (registered trademark), the task management tool Jira (registered trademark), and the file management tool Google Drive (registered trademark).

[0003] Japanese Patent Application Laid-Open No. 2019-028646

[0004] However, because different SaaS services are used depending on the phase and purpose of a business project, business data is distributed across the various SaaS services. Furthermore, because the functions provided by each SaaS service can basically only handle business data processed by that SaaS service, it is difficult to comprehensively capture all business data from multiple tasks in which a user is involved. Furthermore, simply aggregating business data from various SaaS services can result in an increase in unnecessary business data, given the user's business attributes (e.g., position within the company), making efficient processing difficult. While Patent Literature 1 discloses processing based on user attributes such as age group, it does not disclose how to appropriately extract and process business data in light of the user's business attributes.

[0005] Meanwhile, in recent years, various types of content have been generated using generative artificial intelligence (AI) models. A generative AI model is a model that can generate content (generation results) in response to a prompt containing input information, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and return the generated content as response information.

[0006] Taking the above circumstances into consideration, the present disclosure aims to obtain appropriate answer sentences to questions related to a user's work by utilizing a generative AI model based on business data extracted in accordance with the user's attribute information related to the work and the attribute information.

[0007] The information processing device according to the present disclosure includes a reception unit that receives request information for generating an answer sentence to a question sentence related to the business of a target user, an acquisition unit that acquires attribute information of the target user related to the business, an extraction unit that extracts corresponding business data that is related to the generation request information and corresponds to the attribute information from a plurality of business data that are pre-registered or acquired from a business tool, and an output unit that outputs an input sentence to a prompt for instructing the generation of the answer sentence based on the extracted corresponding business data, the attribute information, and the generation request information.

[0008] According to the present disclosure, a generative AI model can be utilized based on business data extracted in accordance with a user's attribute information related to the business and the attribute information to obtain appropriate answer sentences to question sentences related to the user's business.

[0009] FIG. 1 is a configuration diagram of an entire system including an information processing device; FIG. 2 is a flow diagram of processing executed by the information processing device; FIG. 3 is a diagram showing an example of an input sentence to a prompt; FIG. 4 is a diagram showing an example of a content generation result (answer sentence); FIG. 5 is a diagram showing another configuration example of an entire system; and FIG. 6 is a diagram showing an example of a hardware configuration of an information processing device.

[0010] Hereinafter, an embodiment of an information processing device and an information processing method according to the present disclosure will be described with reference to the drawings. In the following embodiment, a form will be described in which a large language model (LLM) that is mainly used for text generation is used as an example of a generative AI model.

[0011] [Configuration of a system including an information processing device] Fig. 1 shows a configuration diagram of a system 1 including an information processing device 10 according to the present disclosure. As shown in Fig. 1, the system 1 includes an external server 30A on which a large-scale language model (LLM) 30 runs, the information processing device 10, and an in-house server 20A on which an in-house system runs. The in-house server 20A includes the following multiple databases that store various data processed in the in-house system. The multiple databases include an employee information database (employee information DB) 20, a business database (business DB) 21, and a term information database (term information DB) 22.

[0012] Of these, employee information DB20 stores the following attribute information of users (employees) related to their work: The attribute information of the target user related to their work includes, for example, information about the target user's position (executive, department manager, section manager, general employee, etc.), information about the target user's work experience (content of experience, years of experience, work location experience, etc.), information about the target user's ability to perform work (for example, ability to speak a foreign language (English, Chinese, Korean, etc.), reading ability, translation ability, interpretation ability, etc.), or information about the target user's qualifications (for example, various qualifications related to information processing, various qualifications related to accounting, etc.), and includes at least one of these.

[0013] The business DB 21 stores various business-related information, either pre-registered or acquired from business tools. Examples of stored business-related information include text information in various document files and information output from the various SaaS business tools (applications) mentioned above. For example, log data output from the communication tool Slack (registered trademark), such as which channel, who entered what text, and when, is stored in the business DB 21. For example, log data for a message exchange between Manager X and Employee Y, such as: Log Data (1) Employee Y: What price should we propose for Product S? Log Data (2) Manager X: Please keep it under 2 million yen. Log Data (3) Employee Y: Then, let's make it 1.8 million yen, may be added as information about how the proposed price for Product S was determined. Log Data (3) may be supplemented with text information to clarify the meaning, such as "Employee Y: Then, 'based on the conversation with Manager X,' we will propose 1.8 million yen." In the above example, log data from Slack (registered trademark) was shown, out of the various SaaS business tools, but information output from other business tools (such as Notion (registered trademark), a document management tool, Jira (registered trademark), a task management tool, and Google Drive (registered trademark), a file management tool) may also be stored in business DB21.

[0014] The terminology information DB 22 is a database that stores in advance information on various work-related terms (terms to be used) for each employee's attribute information (e.g., job title). As an example, for executives, department heads, new employees, etc., who are not likely to be familiar with the on-site project situation, "general terms" that represent various matters related to the work are stored in association with the executives, department heads, new employees, etc., while for section managers, general employees, etc., who are likely to be familiar with the on-site project situation, "technical terms" that represent various matters related to the work are stored in association with the executives, department heads, new employees, etc. For example, in the case of "patent" work, there is a technical term "public application" that refers to a system in which the contents of an application (specification, drawings, etc.) are made public after a certain period of time has passed since the filing date. In the terminology information DB 22, the technical term "public application" is stored as a term to be used for section managers, general employees, etc., while a general term such as "a system for making the contents of an application (specification, drawings, etc.) public" is stored as a term to be used for executives, department heads, new employees, etc. The output unit 14, which will be described later, searches the term information DB 22, obtains information on terms (terms to be used) that correspond to the attribute information of the target user from the stored term information, and includes in the prompt input to the LLM 30 an instruction to generate an answer sentence using terms that are appropriate for the attribute information, as well as information on the terms.

[0015] The information processing device 10 may employ various information processing devices (smartphones, mobile phones, smartwatches, wearable devices, notebook computers, desktop computers, servers, etc.) as hardware.

[0016] An RAG (Retrieval-Augmented Generation) system application is installed on the information processing device 10, and the RAG system operates. The RAG system is a type of prompt extension technology used for corporate information collaboration between LLMs. Specifically, when a generation request is made to an LLM via a prompt based on a content generation request, the system searches for related information (reference information) in advance if necessary and requests the LLM to generate the obtained information along with an instruction. The present disclosure corresponds to an invention that extends and improves the functions of the RAG system, and has an aspect of enriching and optimizing prompts to the LLM 30 using various information stored in the DB in the in-house server 20A that cannot be directly accessed by the LLM 30 or various information obtained by searching from an external server (not shown).

[0017] The above-mentioned prompt refers to information indicating an instruction or question input to a generative AI model (LLM 30 in this embodiment) in an interactive system such as a dialogue with the generative AI model or a command line interface (CLI). The prompt input to the LLM 30 in this embodiment is text data including, for example, information indicating the command to be executed by the LLM 30, the task to be executed by the LLM 30, the background / context to be considered by the LLM 30 (e.g., role, condition), the question to be answered by the LLM 30, and the output format of the response information from the LLM 30. The prompt may also include input information that is the target of the command / task to be executed by the LLM 30. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. The above-mentioned application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0018] In order to realize the functions according to the present disclosure, the information processing device 10 includes a reception unit 11, an acquisition unit 12, an extraction unit 13, and an output unit 14. The function of each unit will be described below.

[0019] The reception unit 11 is a functional unit that receives a request for generating an answer to a question about the target user's business. The generation request information is notified to the reception unit 11 when a generation request button provided on a web page or application page displayed on the display of the information processing device 10 is pressed.

[0020] The acquisition unit 12 is a functional unit that acquires the target user's attribute information related to the business. Specifically, the acquisition unit 12 receives a user ID for identifying the target user from the reception unit 11, searches the employee information DB 20 using the user ID as a key, and acquires the target user's attribute information related to the business, such as information about the target user's job title, information about the target user's work experience, information about the target user's business ability, and information about the target user's qualifications.

[0021] The extraction unit 13 is a functional unit that extracts corresponding business data, which is business data related to the above-mentioned generation request information and corresponding to the above-mentioned attribute information, from multiple business data registered in advance in the business DB 21 or acquired from various business tools. Specifically, the extraction unit 13 extracts corresponding business data related to the above-mentioned generation request information and corresponding to the attribute information from various business data registered in advance in the business DB 21 or, for example, message sending and receiving history data acquired from SLACK (registered trademark), a communication tool, using keywords extracted from the above-mentioned generation request information and attribute information of the target user acquired by the acquisition unit 12 as keys.

[0022] The output unit 14 is a functional unit that outputs an input sentence to a prompt for instructing the generation of an answer sentence based on the extracted corresponding task data, attribute information, and generation request information. As will be described in detail later, the output unit 14 includes in the prompt an instruction to generate an answer sentence whose content is appropriate for the attribute information related to the task (e.g., a position within the company). In addition, the output unit 14 receives and outputs an answer sentence whose content corresponds to the attribute information as a generation result (content) output from the LLM 30 in response to the input of the prompt.

[0023] Furthermore, the output unit 14 may search the term information DB 22, obtain information on terms (terms to be used) corresponding to the attribute information of the target user from the stored term information, and include an instruction to generate an answer sentence using terms appropriate for the attribute information and information on the terms in the prompt input to the LLM 30. As described above, the term information DB 22 stores general terms representing various matters related to the work for executives, department managers, new employees, etc. who are not likely to be familiar with the on-site circumstances of the project, in association with each other, and stores specialized terms representing various matters related to the work for section managers, general employees, etc. who are likely to be familiar with the on-site circumstances of the project, in association with each other. Therefore, it is expected that an answer sentence using terms appropriate for the attribute information can be generated and obtained by obtaining information on "terms to be used" corresponding to the attribute information of the target user.

[0024] Furthermore, when the extraction unit 13 extracts corresponding task data containing information about the history of a certain project from message transmission history data acquired from a communication tool (e.g., SLACK (registered trademark)), the output unit 14 may include in the prompt an instruction to generate a response sentence that takes into account the information about the history. In this case, it is expected that a more appropriate response sentence can be generated and acquired based on the information about the history of the project that is understood from the message exchange between the manager X and employee Y. Examples of the above prompts and examples of content output from the LLM 30 will be described in detail in the processing explanation of FIG. 2.

[0025] [Processing Executed in Information Processing Device] Hereinafter, processing executed in the information processing device 10 (processing related to the information processing method of the present disclosure) will be described with reference to the flow diagram of FIG. 2 .

[0026] When a user presses a generation request button provided on a web page or application page displayed on the display of the information processing device 10, the reception unit 11 is notified of the generation request information for an answer sentence to a question sentence regarding the target user's business, and the process of Figure 2 begins to be executed when the reception unit 11 receives the above generation request information.

[0027] In response to receiving the above-mentioned generation request information, the acquisition unit 12 receives a user ID for identifying the target user from the reception unit 11, searches the employee information DB 20 using the user ID as a key, and acquires the target user's attribute information related to the work, such as information about the target user's job title, information about the target user's work experience, information about the target user's ability to perform work, and information about the target user's qualifications (step S1).

[0028] Next, the extraction unit 13 extracts corresponding business data related to the above-mentioned generation request information and corresponding to the above-mentioned attribute information from various business data pre-registered in the business DB 21, or, for example, historical data on message sending and receiving obtained from SLACK (registered trademark), a communication tool (step S2).

[0029] Furthermore, the output unit 14 outputs an input sentence to the prompt for instructing the generation of an answer sentence based on the extracted corresponding task data, attribute information, and generation request information (step S3).

[0030] In step S3, the output unit 14 searches the term information DB 22, obtains information on terms (terms to be used) corresponding to the attribute information of the target user from the stored term information, and may include in the prompt input to the LLM 30 an instruction to generate an answer sentence using terms appropriate for the attribute information, as well as information on the terms.

[0031] Furthermore, when the extraction unit 13 extracts corresponding business data including information about the history of a certain project from historical data of message sending and receiving obtained from a communication tool (for example, SLACK (registered trademark)), the output unit 14 may include in the prompt an instruction to generate a response sentence that takes into account the information about the history.

[0032] The input sentence to the prompt may be, for example, text information containing multiple items such as role, task, and condition, as shown in Figure 3: "Role: You are an executive. Task: Please give us an overview of Project A, which you have been newly assigned to oversee. Conditions: (1) Please provide an explanation for executives. (2) Please explain from a macro perspective, not a micro perspective. (3) Please use as general terms as possible, referring to the attached "Executive Glossary." (4) Please refer to the attached "Search Results from SaaS." ..." In this case, the output unit 14 outputs the input sentence to the prompt to the LLM 30, along with the following: - Search results from SaaS containing a description of the overview of Project A, and - Executive glossary data.

[0033] Thereafter, the LLM 30 outputs the answer sentence to the question sentence as the generated content, and the output unit 14 acquires and outputs the content (step S4).

[0034] As shown in Figure 4, an example of the output content is (1) Project overview, background, value, rationale, etc. (2) How AI will be used in the project (3) Target demographic (4) Sales forecast (5) Current status of efforts (6) Planned future activities

[0035] In this way, the user can obtain appropriate answer sentences to questions about the user's work by utilizing the generative AI model (LLM30) based on the business data extracted according to the user's attribute information related to the work and the attribute information. This makes it possible to obtain appropriate answer sentences for the following: - executive in charge of the project - department manager in charge of the project - section manager in charge of the project - general employees involved in the project - new employees involved in the project

[0036] Furthermore, the output unit 14 searches the term information DB 22 and obtains information on terms (terms to be used) corresponding to the target user's attribute information from the stored term information, and includes an instruction to generate an answer sentence using terms appropriate for the attribute information and information on the terms in the prompt input to the LLM 30. This allows the information on "terms to be used" corresponding to the target user's attribute information to be obtained, and an answer sentence with appropriate content using terms appropriate for the attribute information to be generated and obtained. Therefore, for example, when preparing an answer sentence for a new employee who has just joined a project, it is no longer necessary to spend a lot of time and effort creating an answer sentence for the new employee based on answer sentences for existing general employees, paying close attention to the terminology used, thereby reducing the labor and streamlining of operations.

[0037] Furthermore, when the extraction unit 13 extracts corresponding business data including information about the history of a certain project from historical data of message sending and receiving obtained from a communication tool (for example, SLACK (registered trademark)), the output unit 14 can generate and obtain a more appropriate answer sentence based on the information about the history of the project by including in the prompt an instruction to generate an answer sentence that takes into account the information about the history.

[0038] (Modification of System 1) System 1 is not limited to the configuration shown in FIG. 1 , and may be configured as shown in FIG. 5 , in which the LLM 30 is implemented inside the information processing device 10. As described above, the information processing device 10 may be a mobile terminal such as a smartphone, a mobile phone, a smartwatch, or a wearable device, and the LLM 30 may be implemented on such a mobile terminal. This configuration can be realized by installing an application that executes the functions of the LLM 30 on the information processing device 10. Furthermore, while FIG. 1 shows an example in which various DBs (such as the employee information DB 20) are implemented outside the information processing device 10 (e.g., on a network), at least one of the various DBs may be implemented inside the information processing device 10.

[0039] The gist of the present disclosure lies in the following [1] to [6]. [1] An information processing device comprising: a receiving unit that receives information requesting the generation of an answer sentence to a question sentence related to a business of a target user; an acquisition unit that acquires attribute information of the target user related to the business; an extraction unit that extracts corresponding business data that is business data related to the generation request information and corresponds to the attribute information from a plurality of business data registered in advance or acquired from a business tool; and an output unit that outputs an input sentence to a prompt for instructing the generation of the answer sentence based on the extracted corresponding business data, the attribute information, and the generation request information. [2] The attribute information of the target user related to the business includes at least one of information on the target user's job title, information on the target user's work experience (experience content, years of experience, and place of work), information on the target user's ability to perform the job (foreign language conversation ability and reading comprehension), or information on the target user's qualifications. The information processing device described in [1], wherein the output unit includes in the prompt an instruction to generate the answer sentence having content corresponding to the attribute information. [3] The information processing device according to [2], wherein the output unit acquires information on terms corresponding to the attribute information of the target user from information on terms to be used stored in advance for each attribute information, and includes in the prompt an instruction to generate the answer sentence having content corresponding to the attribute information based on the information on the term and information on the term. [4] The information processing device according to any one of [1] to [3], wherein the plurality of business data include information on a process acquired from a communication tool among the business tools, the extraction unit extracts the corresponding business data including information on the process, and the output unit includes in the prompt an instruction to generate the answer sentence having content taking into account the information on the process. [5] The information processing device according to any one of [1] to [4], wherein the output unit receives and outputs the answer sentence as a generation result output from a generative AI model in response to input of the prompt.[6] An information processing method comprising the steps of: an information processing device receiving request information for generating an answer sentence to a question sentence related to a target user's business; the information processing device acquiring attribute information of the target user related to the business; the information processing device extracting corresponding business data that is related to the generation request information and corresponds to the attribute information from a plurality of business data that have been pre-registered or acquired from a business tool; and the information processing device outputting an input sentence to a prompt for instructing the generation of the answer sentence based on the extracted corresponding business data, the attribute information and the generation request information.

[0040] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 6), etc.] The block diagrams used in the description of the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0041] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0042] For example, an information processing device according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 6 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0043] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0044] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0045] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0046] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. While the various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0047] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0048] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0049] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0050] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0051] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0052] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0053] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0054] Each aspect / embodiment described in the present disclosure may be implemented using any of the following standards: LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal number)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.17 (WiMAX (registered trademark)), IEEE 802.19 (WiMAX (registered trademark)), IEEE 802.20 (WiMAX (registered trademark)), IEEE 802.21 (Wi-Fi (registered trademark)), IEEE 802.22 (WiMAX (registered trademark)), IEEE 802.23 (WiMAX (registered trademark)), IEEE 802.24 (WiMAX (registered trademark)), IEEE 802.25 (WiMAX (registered trademark)), IEEE 802.26 (WiMAX (registered trademark)), IEEE 802.27 (WiMAX (registered trademark)), IEEE 802.28 (WiMAX (registered trademark)), IEEE 802.29 (WiMAX (registered trademark)), IEEE 802.30 (WiMAX (registered trademark)), IEEE 802.31 (Wi-Fi (registered trademark)), IEEE 802.32 (WiMAX (registered trademark)), IEEE 802.33 (WiMAX (registered trademark)), IEEE 802.34 ( The present invention may be applied to at least one of systems using 802.20, Ultra-Wideband (UWB), Bluetooth, or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. It may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0055] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0056] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0057] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0058] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0059] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0060] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0061] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0062] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0063] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0064] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0065] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0066] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0067] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0068] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0069] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0070] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0071] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0072] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0073] 1...system, 10...information processing device, 11...reception unit, 12...acquisition unit, 13...extraction unit, 14...output unit, 20A...in-house server, 20...employee information DB, 21...business DB, 22...terminology information DB, 30...LLM, 30A...external server, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An information processing device comprising: a reception unit that receives request information for generating an answer sentence to a question sentence related to a target user's business; an acquisition unit that acquires attribute information of the target user related to the business; an extraction unit that extracts corresponding business data that is related to the generation request information and corresponds to the attribute information from multiple business data that are pre-registered or acquired from a business tool; and an output unit that outputs an input sentence to a prompt to instruct the generation of the answer sentence based on the extracted corresponding business data, the attribute information and the generation request information.

2. The information processing device of claim 1, wherein the attribute information of the target user relating to the work includes at least one of information about the target user's job title, information about the target user's work experience (experience content, years, place of work), information about the target user's ability to perform the work (foreign language conversation ability, reading comprehension), or information about the target user's qualifications, and the output unit includes in the prompt an instruction to generate the answer sentence whose content corresponds to the attribute information.

3. The information processing device according to claim 2, wherein the output unit obtains information on terms corresponding to the attribute information of the target user from information on terms to be used stored in advance for each attribute information, and includes in the prompt an instruction to generate the answer sentence having content corresponding to the attribute information based on the information on the terms, as well as information on the terms.

4. The information processing device described in claim 1, wherein the plurality of business data includes information regarding the process obtained from a communication tool among the business tools, the extraction unit extracts the corresponding business data including the information regarding the process, and the output unit includes in the prompt an instruction to generate the answer sentence based on the information regarding the process.

5. The information processing device according to claim 1, wherein the output unit receives and outputs the answer sentence as a generation result output from the generative AI model in response to input of the prompt.

6. An information processing method comprising: a step in which an information processing device receives information requesting the generation of an answer sentence to a question sentence related to a target user's business; a step in which the information processing device acquires attribute information of the target user related to the business; a step in which the information processing device extracts corresponding business data that is related to the generation request information and corresponds to the attribute information from a plurality of business data that have been pre-registered or acquired from a business tool; and a step in which the information processing device outputs an input sentence to a prompt for instructing the generation of the answer sentence based on the extracted corresponding business data, the attribute information and the generation request information.

Images