Information processing device and information processing method

Abstract

This information processing device (10) comprises: a reception unit (11) that receives information relating to a problem; a target setting unit (12) that sets a target on the basis of the received information relating to the problem; a determination unit (13) that, on the basis of the set target, determines a framework for decision-making regarding the problem; and an output unit (14) that, on the basis of a result of analysis in which the determined framework is used, outputs, to a LLM 30 (generative AI model), a decision-making result for the problem and generation request information for instructing generation of a basis for the decision-making.

Description

Information processing device and information processing method

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

[0002] There are many opportunities for people to make decisions in their work in a company, in their personal lives, etc. It is also known that, regardless of the importance of the decision, repeated decision-making can cause mental and physical fatigue, which can reduce the validity of the decision results.

[0003] On the other hand, decision-making is often based on tacit knowledge cultivated over many years of experience. Frameworks, which are commonly used frameworks for thinking, analysis, problem solving, strategy planning, and the like, are known as decision-making support tools in business. For example, frameworks are used to comprehensively organize all necessary perspectives without omission, such as identifying problems, analyzing them, and sharing ideas. As described above, improving the efficiency of decision-making is a major challenge, and Patent Document 1 proposes a support technology for improving the efficiency of decision-making based on a method for solving multi-objective optimization problems.

[0004] JP 2023-022768 A

[0005] In recent years, various types of content have been generated using generative artificial intelligence (AI) models. A generative AI model is a model that generates 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 returns the content as response information. However, the technology disclosed in Patent Document 1 does not take into account the utilization of generative AI models, and therefore there is still room for improvement.

[0006] Therefore, the aim is to utilize a generative AI model to easily obtain appropriate decision-making results and their rationale.

[0007] The information processing device according to the present disclosure includes a receiving unit that receives information about a problem, a goal setting unit that sets a goal based on the received information about the problem, a decision unit that determines a framework for making a decision about the problem based on the set goal, and an output unit that outputs generation request information to a generative AI model to instruct the generation of a decision-making result about the problem and the basis for the decision-making based on an analysis result using the determined framework.

[0008] According to the present disclosure, by utilizing a generative AI model, it is possible to easily obtain appropriate decision-making results and their rationale, thereby enabling people to allocate their mental energy and time to the creative activities that they should be engaged in, thereby improving labor productivity.

[0009] 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 information required for a framework. FIG. 4 is a diagram showing an example of a directive. FIG. 5 is a diagram showing an example of output of a decision-making result and a rationale. FIG. 6 is a flow diagram of processing executed by the information processing device of FIG. 6. (a) is a diagram showing an example of a directive in the first stage of a two-stage image, and (b) is a diagram showing an example of a directive in the second stage of the two-stage image. (a) is a diagram showing a first variation example related to the system configuration, and (b) is a diagram showing a second variation example related to the system configuration. FIG. 7 is a diagram showing an example of the 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 illustrates a configuration diagram of a system 1 including an information processing device 10 according to the present disclosure. As illustrated in FIG. 1, the system 1 includes a terminal 20 operated by a user, an external server (hereinafter referred to as "LLM") 30 running a large-scale language model (LLM), and the information processing device 10. The information processing device 10 is a device constituting a Retrieval-Augmented Generation (RAG) system. The RAG system is a type of prompt extension technology used for corporate information linkage of LLMs. Specifically, when issuing a generation request to an LLM based on an instruction statement (generation request information), the system searches for similar documents, etc. in a search system in advance, and outputs the obtained similar documents, etc., along with the instruction statement to the LLM to request generation. To realize the functions according to the present disclosure, the information processing device 10 includes a receiving unit 11, a goal setting unit 12, a determination unit 13, and an output unit 14. The functions of each unit are described below.

[0012] The reception unit 11 is a functional unit that receives information related to the problem from an external source (e.g., the terminal 20, or an external server instructed by the terminal 20). The "information related to the problem" here may be information including background knowledge and issues related to the problem, such as the following: "Problem: Should we develop a low-priced model? Background information (1): Information related to the production of the current model (e.g., manufacturing costs) Background information (2): Customer feedback Background information (3): The situation of competitors Issue (1): Improving profits Issue (2): Gaining market share within the industry." Such "information related to the problem" may be received entirely from the terminal 20, or information that appears to be missing may be supplemented by adding information obtained by searching an internal database accessible from the information processing device 10.

[0013] The goal setting unit 12 is a functional unit that sets goals (e.g., external environment macro analysis, company analysis, strategy formulation, tactical formulation, etc.) based on the information about the received problem. For example, a learning model that learns the rate at which a problem matches a goal set for that problem (hit rate) may be prepared in advance, and the goal setting unit 12 may input the target problem into the learning model, thereby acquiring and setting a goal that is expected to match the problem as an output from the learning model.

[0014] The determination unit 13 is a functional unit that determines a framework for making decisions about a problem based on a set objective (e.g., external environment macro analysis, company analysis, strategy formulation, tactics formulation, etc.). For example, if the set objective is "strategy formulation for the company's products," the determination unit 13 determines a "PPM (Product Portfolio Management) framework" as the framework. Note that "meta information for each framework" that is useful for determining the framework may be generated and acquired in advance by instructing the LLM 30 or the like, and the determination unit 13 may determine an appropriate framework according to the objective by referring to the meta information.

[0015] The output unit 14 is a functional unit that outputs to the LLM 30 an instruction (generation request information) for instructing the generation of a decision-making result for a problem and the basis for the decision-making based on the analysis results using the determined framework. The output unit 14 acquires information necessary for the framework determined by the determination unit 13 from information previously stored for each framework. For example, in the case of a "SWOT analysis" as an example of a framework, the information necessary for the framework includes exemplary information on strengths, weaknesses, opportunities, and threats. Such exemplary information may be stored in advance in an in-house database accessible from the information processing device 10, and retrieved from the previously stored information when needed.

[0016] Figure 3 shows an example of information required for a framework. Examples include: "Framework Name Example SWOT Analysis Strengths Strong brand power. SWOT Analysis Strengths Large company size. SWOT Analysis Weaknesses Poor technical capabilities. SWOT Analysis Opportunities Generative AI technology is developing. SWOT Analysis Threat Legislation regarding technology has not kept up."

[0017] The output unit 14 also outputs a directive including an instruction to generate a decision-making result and the basis for the decision-making based on the acquired "information necessary for the framework." Furthermore, the output unit 14 receives task management advice from the LLM 30 as a generation result output from the LLM 30 in response to the input of the directive, and outputs the advice to the terminal 20. Specific examples of the directive ( FIG. 4 ) and specific examples of the generation result by the LLM 30 ( FIG. 5 ) will be described later.

[0018] (Processing Executed in Information Processing Device 10) 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.

[0019] First, the reception unit 11 receives information about the problem (which may include background information and points of contention) from an external source (e.g., the terminal 20 or an external server instructed by the terminal 20) (step S1), and the goal setting unit 12 sets a goal based on the information about the problem, as described above (step S2). Next, the determination unit 13 determines a framework based on the set goal (step S3), and the output unit 14 obtains information necessary for the determined framework from information stored in advance for each framework (step S4).

[0020] Furthermore, the output unit 14 outputs "instructions for generating analysis results using the framework and generating decision-making results and the rationale for the decision-making based on the analysis results" to the prompt, which is input information to the LLM 30 (i.e., instructs the LLM 30 to generate the instructions) (step S5). Figure 4 shows an example of an instruction. An example of an instruction is shown in Figure 4: "Role: I am a consultant. Task: (1) Generate SWOT analysis results based on the input information. (2) Use the SWOT analysis results to generate a document showing the decision-making results and the rationale for the decision-making. Output format: (1) SWOT analysis results: Strengths, Weaknesses, Opportunities, Threats (2) Decision-making results and the rationale for the decision-making. Input information: Problem, Background information... Examples of SWOT: Strengths: Strong sales brand. Strengths: Large company size..."

[0021] Thereafter, the output unit 14 acquires the decision-making result and its basis from the LLM 30 (step S6), and outputs the acquired decision-making result and its basis to the terminal 20 (step S7), thereby enabling the user to confirm the decision-making result and its basis.

[0022] As an example of the generated results, an output example of the decision-making results and their rationale is shown in Figure 5. As shown in Figure 5, the following output example of the decision-making results and their rationale is available: "Framework Attributes Decision-making results Rationale SWOT analysis President Strengthen the strength of XX Because it is effective against other companies SWOT analysis President Overcome weaknesses Want to prevent leakage to other companies SWOT analysis Person in charge Strengthen the strength of XX Because the intellectual property rights to the technology that realizes XX are secured, so other companies cannot follow suit SWOT analysis Person in charge Improve the weakness of XX Because the technology to realize XX has been cultivated within the company."

[0023] In the embodiment described above, the information processing device 10 accepts information about a problem, sets a goal based on the accepted information about the problem, determines a framework for making a decision about the problem based on the set goal, and outputs instructions to the LLM 30 to generate a decision-making result and its rationale for the problem based on the analysis results using the determined framework. This allows the decision-making result and its rationale to be obtained from the LLM 30. By utilizing the LLM 30 in this way, appropriate decision-making results and their rationale can be easily obtained. This allows the user to devote their mental energy and time to the creative activities that they should be engaging in, thereby improving labor productivity.

[0024] (Regarding Alternative Aspect 1) Hereinafter, a two-stage instruction will be described as Alternative Aspect 1. The two-stage instruction refers to an aspect in which, in a first stage, an instruction is given to the LLM 30 to generate analysis results for a problem using a framework, and then, in a second stage, an instruction is given to generate decision-making results for the problem and the basis for the decision-making results based on the analysis results using the framework obtained from the LLM 30.

[0025] In this embodiment, as shown in FIG. 6 , the output unit 14 has a functional block configuration including a first output unit 14A related to the first-stage processing and a second output unit 14B related to the second-stage processing. Specifically, the first output unit 14A outputs instructions to the LLM 30 to perform an analysis of the problem using the framework and obtains the analysis results from the LLM 30. The second output unit 14B outputs instructions to the LLM 30 to instruct the LLM 30 to generate a decision-making result and its rationale for the problem based on the obtained analysis results and obtains the decision-making result and its rationale from the LLM 30. Examples of instructions output by the first output unit 14A and the second output unit 14B will be described later.

[0026] In this mode, the process shown in Fig. 7 is executed. The process shown in Fig. 7 differs from the process in Fig. 2 in steps S5A to S5C, and these differences will be described below.

[0027] After the information processing device 10 acquires the information necessary for the determined framework in step S4, the first output unit 14A outputs an instruction statement to the LLM 30 to instruct the generation of analysis results using the framework (step S5A). Figure 8(a) shows an example of such an instruction statement. An example of an instruction statement is shown in Figure 8(a) as follows: "Role: I am a consultant. Task: Please generate SWOT analysis results based on the input information. Output format: SWOT analysis results - Strengths - Weaknesses - Opportunities - Threats Input information: - Problems - Background information... Examples of SWOT: Strengths: Strong sales brand Strengths: Large company size..."

[0028] The first output unit 14A then acquires the analysis results using the framework output from the LLM 30 (step S5B) and passes them to the second output unit 14B. The second output unit 14B then outputs an instruction to the LLM 30 to generate a decision-making result and its rationale based on the acquired analysis results (step S5C). Figure 8(b) shows an example of such an instruction. An example of an instruction, such as the one shown in Figure 8(b), is: "Role: I am a consultant. Task: Please generate a statement showing the decision-making result and its rationale using the SWOT analysis results. Output format: Decision-making result about the problem; Rationale. Input information: Problem; Background information; SWOT analysis results... Example of information showing the decision-making result and its rationale for the problem. Example: We should increase the number of low-priced models. Reason: There is a possibility of attracting younger customers."

[0029] In the above embodiment, since the analysis results using the framework can be obtained once, the user can check the analysis results as needed. If the analysis results are found to be satisfactory, the process proceeds to the second stage. This has the advantage of allowing the process to proceed while checking the results sequentially.

[0030] (Regarding Alternative Aspect 2) A possible aspect is one in which the role is "decision maker" and the approach to decision-making varies depending on the decision maker (personalizing the approach to decision-making). By specifying a specific person's name or a predetermined characteristic and problem, the decision content to be made can be output. Specifically, using a learning model that has previously been machine-learned to learn the results of past decisions made by specific people or people with predetermined attributes on various problems and the rationale for those decisions, the output unit 14 may output to the LLM 30 an instruction statement that includes an instruction to generate a decision-making result and rationale for the target problem based on at least one of: (1) the name of the specific person designated as the decision maker or specific attribute information related to the decision maker, and (2) information about the target problem for which a decision is to be made. This has the advantage of enabling appropriate decision-making results and rationale to be obtained based on the specified information (a specific person's name or predetermined characteristic and problem).

[0031] (Regarding Alternative Aspect 3) A possible aspect is one in which the role is defined as a "decision maker" and examples are varied depending on the decision maker. Specifically, the output unit 14 uses example expressions prepared in advance according to the attributes of the decision maker to output to the LLM 30 an instruction statement including an instruction to generate a decision-making result and its rationale for the target problem in expressions corresponding to the attribute information on the decision maker included in the user's generation request information, using example expressions prepared in advance according to the attributes of the decision maker. For example, examples of expressions from a managerial perspective may be prepared in advance for the "president," and detailed examples using detailed, specialized expressions may be prepared in advance for the "person in charge," and these may be utilized. Alternatively, examples may be prepared in advance for each attribute (e.g., position within an organization) and utilized. This has the advantage of enabling appropriate decision-making results and their rationale to be obtained according to the "attributes of the decision maker (e.g., position within an organization)" specified by the user.

[0032] (Variations Regarding the Configuration of System 1) System 1 is not limited to the configuration shown in FIG. 1 . As shown in FIG. 9( a), the information processing device 10 may be included in the terminal 20. This configuration can be realized, for example, by installing an application that executes the functions of the information processing device 10 on the terminal 20. The LLM 30 resides externally (e.g., on the cloud). Alternatively, as shown in FIG. 9( b), the information processing device 10 and the LLM 30 may be included in the terminal 20. This configuration can be realized, for example, by installing an application that executes the functions of the information processing device 10 and an application that executes the functions of the LLM 30 on the terminal 20. In any of the configurations shown in FIGS. 1, 9( a), and 9( b), an external server (e.g., an internal server of a company) that can provide information related to business operations resides externally (e.g., on a network). Although not shown, a configuration similar to that shown in FIGS. 9( a) and 9( b) corresponding to the configuration shown in FIG. 6 is also possible.

[0033] The gist of the present disclosure lies in the following [1] to [7]. [1] An information processing device comprising: a receiving unit that receives information about a problem; a goal setting unit that sets a goal based on the received information about the problem; a determination unit that determines a framework for making a decision about the problem based on the set goal; and an output unit that outputs, to a generative AI model, generation request information for instructing the generation of a decision-making result about the problem and a basis for the decision-making based on an analysis result using the determined framework. [2] The information processing device according to [1], wherein the output unit outputs the generation request information including an instruction to generate the decision-making result and the basis based on information necessary for the determined framework, which is acquired from information stored in advance for each framework. [3] The information processing device according to any one of [1] to [3], wherein the output unit includes: a first output unit that outputs, to the generative AI model, generation request information for instructing the generation of an analysis result for the problem using the framework and acquires from the generative AI model the analysis result using the framework, and a second output unit that outputs, to the generative AI model, generation request information for instructing the generation of a decision-making result and a rationale for the problem based on the acquired analysis result using the framework and acquires the decision-making result and the rationale from the generative AI model. [4] The information processing device according to any one of [1] to [3], wherein the output unit outputs the generation request information including an instruction to generate the decision-making result and the rationale for the target problem, in accordance with at least one of: a name of a specific person designated as a decision maker or specific attribute information related to the decision maker, and information on the target problem to be decided, which are included in the generation request information, using a learning model that has been machine-learned in advance to learn results of decision-making on various problems by specific people or people with predetermined attributes.[5] The information processing device according to any one of [1] to [3], wherein the output unit outputs the generation request information including an instruction to generate a decision-making result and a rationale for the problem in an expression corresponding to specific attribute information related to the decision maker included in the generation request information, using example expressions prepared in advance according to the attributes of the decision maker. [6] The information processing device according to any one of [1] to [5], wherein the output unit receives and outputs the decision-making result and the rationale for the problem as a generation result output from the generative AI model in response to input of the generation request information to the generative AI model. [7] An information processing method comprising: a step by an information processing device receiving information related to a problem; a step by the information processing device setting an objective based on the received information about the problem; a step by the information processing device determining a framework for making a decision about the problem based on the set objective; and a step by the information processing device outputting generation request information to a generative AI model, the generation request information instructing the generation of a decision-making result and a rationale for the decision based on an analysis result using the determined framework.

[0034] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 10), 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 for 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.

[0035] 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.

[0036] 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. 10 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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).

[0044] 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).

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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).

[0049] 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.

[0050] 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.

[0051] 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).

[0052] 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).

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0059] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0060] 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.

[0061] 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.

[0062] 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."

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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."

[0067] 1...system, 10...information processing device, 11...reception unit, 12...objective setting unit, 13...determination unit, 14...output unit, 14A...first output unit, 14B...second output unit, 20...terminal, 30...LLM, 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 information about a problem; a goal setting unit that sets a goal based on the received information about the problem; a decision unit that determines a framework for making a decision about the problem based on the set goal; and an output unit that outputs generation request information to a generative AI model to instruct the generation of a decision-making result about the problem and the basis for the decision-making based on an analysis result using the determined framework.

2. The information processing device according to claim 1, wherein the output unit outputs the generation request information including an instruction to generate the decision-making result and the basis based on information necessary for the determined framework, which information is obtained from information stored in advance for each framework.

3. The information processing device of claim 1, wherein the output unit includes: a first output unit that outputs generation request information to the generative AI model to instruct the generation of analysis results for the problem using the framework, and acquires the analysis results using the framework from the generative AI model; and a second output unit that outputs generation request information to the generative AI model to instruct the generation of decision-making results and rationale for the problem based on the acquired analysis results using the framework, and acquires the decision-making results and rationale from the generative AI model.

4. The information processing device of claim 1, wherein the output unit uses a learning model that has been machine-learned in advance to learn the results of decisions made by a specific person or a person with predetermined attributes on various issues and the reasons for those decisions, and outputs the generation request information including an instruction to generate the decision-making results and the reasons for the decision-making regarding the target problem, in accordance with at least one of the name of a specific person designated as a decision maker or specific attribute information related to the decision maker, and information about the target problem to be decided, which are included in the generation request information.

5. The information processing device described in claim 1, wherein the output unit outputs the generation request information, which includes an instruction to generate decision-making results and reasons for the problem, in expressions corresponding to specific attribute information related to the decision maker included in the generation request information, using example expressions prepared in advance according to the attributes of the decision maker.

6. The information processing device described in claim 1, wherein the output unit receives and outputs the decision-making result and the rationale for the problem as a generation result output from the generative AI model in response to input of the generation request information to the generative AI model.

7. An information processing method comprising: a step in which an information processing device receives information about a problem; a step in which the information processing device sets an objective based on the received information about the problem; a step in which the information processing device determines a framework for making a decision about the problem based on the set objective; and a step in which the information processing device outputs generation request information to a generative AI model to instruct the generation of a decision-making result about the problem and the basis for the decision-making based on an analysis result using the determined framework.

Images