Device and method

Abstract

A device (1) comprises: an acquisition unit (11) that acquires contract information relating to a changed contract; and a generation unit (12) that, on the basis of the contract information acquired by the acquisition unit (11), generates a prompt for instructing an LLM (30) to generate advice relating to the changed contract. The contract information may include the degree of appropriateness for the contract. The contract information may include the degree of appropriateness for each of a plurality of changed contracts, and the advice may relate to each of the plurality of contracts and be based on the respective degrees of appropriateness. The advice may include the basis of the advice.

Description

Apparatus and Method

[0001] One aspect of the present disclosure relates to an apparatus and a method for generating a prompt for instructing generative AI (Artificial Intelligence) to generate advice regarding a modified contract.

[0002] The following Patent Document 1 discloses an information processing apparatus that notifies consumers of other rate plans and encourages them to change their rate plans.

[0003] Japanese Unexamined Patent Publication No. 2017-147869

[0004] Even when the information processing apparatus notifies consumers of other rate plans and encourages them to change their rate plans, consumers have little information to use as a basis for determining whether or not to change their rate plans. Accordingly, there is a demand for generating information capable of generating advice regarding a modified contract.

[0005] The apparatus according to one aspect of the present disclosure includes: an acquisition unit that acquires contract information regarding a modified contract; and a generation unit that generates, based on the contract information acquired by the acquisition unit, a prompt for instructing generative AI to generate advice regarding the modified contract.

[0006] In such an aspect, contract information regarding a modified contract is acquired, and based on the acquired contract information, a prompt for instructing generative AI to generate advice regarding the modified contract is generated. That is, information capable of generating advice regarding a modified contract can be generated.

[0007] According to one aspect of the present disclosure, information capable of generating advice regarding a modified contract can be generated.

[0008] This figure shows an example of the system configuration of a system including the device according to the embodiment. This figure shows an example of the functional configuration of the device according to the embodiment. This figure shows an example of a table of communication history information. This figure shows an example of the relationship between the device according to the embodiment and the generated AI. This figure shows a modified version of the relationship in Figure 4. This figure shows an example of a prompt. This figure shows an example of advice. This is a flowchart showing an example of the processing performed by the device according to the embodiment. This figure shows an example of the hardware configuration of the computer used in the device according to the embodiment.

[0009] The embodiments of this disclosure will be described in detail below with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference numerals, and redundant descriptions will be omitted. Furthermore, the embodiments of this disclosure described below are specific examples of the present invention and are not limited to these embodiments unless otherwise stated to limit the present invention.

[0010] Figure 1 is a diagram showing an example of the system configuration of a system 4 including the device 1 according to the embodiment. As shown in Figure 1, the system 4 is composed of the device 1, one or more terminals 2 (hereinafter collectively referred to simply as "terminal 2" as appropriate), and one or more external servers 3 (hereinafter collectively referred to simply as "external server 3" as appropriate). The device 1 and each terminal 2 are connected to each other by a network such as a mobile communication network, and can send and receive information from each other. The device 1 and each external server 3 are connected to each other by a network such as the Internet, and can send and receive information from each other.

[0011] Device 1 is a computer that generates information that can generate advice regarding the amended contract. Device 1 may also have RAG (Retrieval-Augmented Generation) functionality. Details of Device 1 will be described later.

[0012] Terminal 2 is a computer used by the user. The user may be the person who enters into a contract (the contracting party). The user may also be the person who receives advice generated based on the information generated by Device 1. Terminal 2 may also be a mobile communication terminal that performs mobile communication. For example, Terminal 2 may be a tablet, smartphone, or laptop computer. Terminal 2 may be equipped with various functions and sensors that are typical of a mobile communication terminal. In this embodiment, a smartphone is assumed to be Terminal 2, but it is not limited to this.

[0013] For example, a user of terminal 2 may request advice regarding the amended contract from device 1 via terminal 2, device 1 may generate information that can generate such advice in response to the request, the advice generated based on the generated information may be sent back to terminal 2, and the user of terminal 2 may refer to the returned advice. Alternatively, for example, a user of terminal 2 may notify device 1 of information regarding the amended contract via terminal 2, device 1 may generate information that can generate advice regarding the amended contract in response to the notification, the advice generated based on the generated information may be sent back to terminal 2, and the user of terminal 2 may refer to the returned advice.

[0014] External server 3 is a computer that holds external data, which is arbitrary data. External server 3 can transmit the external data required by device 1 to device 1 at any time in response to a request from device 1.

[0015] Figure 2 shows an example of the functional configuration of the device 1. As shown in Figure 2, the device 1 is composed of a storage unit 10, an acquisition unit 11 (acquisition unit), a generation unit 12 (generation unit), and an output unit 13.

[0016] Each functional block of Device 1 is intended to function within Device 1, but is not limited to this. For example, some of the functional blocks of Device 1 may function within a computer device separate from Device 1, connected to Device 1 via a network, while appropriately sending and receiving information with Device 1. Furthermore, some functional blocks of Device 1 may be omitted, multiple functional blocks may be integrated into a single functional block, or a single functional block may be broken down into multiple functional blocks.

[0017] The following describes the functions of the device 1 shown in Figure 2.

[0018] The storage unit 10 stores arbitrary information used in calculations and other operations in the device 1, as well as the results of calculations in the device 1. The information stored in the storage unit 10 may be referenced as appropriate by each function of the device 1.

[0019] The acquisition unit 11 may acquire arbitrary information used in calculations in the device 1 from the storage unit 10, or it may acquire (receive) it from other devices such as an external server 3 via a network. The acquisition unit 11 may acquire arbitrary information in advance prior to any calculations in the device 1, or it may acquire the information when it becomes necessary, in accordance with the requirements of each function of the device 1. The acquisition unit 11 may store the received information in the storage unit 10, or it may output it to other functions of the device 1.

[0020] The acquisition unit 11 may acquire contract information relating to the amended contract.

[0021] The contract may also relate to the subscriber's communications. More specifically, the contract is a pricing plan (contract plan) provided by a mobile carrier (mobile communications operator) that provides mobile communications services, and may be a pricing plan that the user (subscriber) of terminal 2 intending to use the mobile communications service is planning to subscribe to. The pricing plan may be, for example, a plan that allows up to 30 GB (gigabytes; hereafter simply referred to as "GB") of data communication per month for a basic monthly fee of 2,970 yen. The contract may also be a combination of a mobile carrier and (the mobile carrier's) pricing plan. Furthermore, the contract is not limited to communications; it may be any contract.

[0022] The amended contract may be a contract that is planned to be amended (or a new contract) in the future, a contract that is a candidate for amendment (or a new contract), or an amended (or new) contract, in a situation where there is currently another contract (the original contract) or no contract at all.

[0023] Contract information is optional information regarding the amended contract. Contract information may include the degree of appropriateness of the (amended) contract. The degree of appropriateness is a measure of how appropriate the contract is. For example, the degree of appropriateness may be expressed as an integer from "0" to "10", with values ​​closer to "0" indicating less appropriateness and values ​​closer to "10" indicating more appropriateness. The degree of appropriateness of the contract may be the degree of appropriateness of the contract from the perspective of the contracting party. For example, the degree of appropriateness of the contract may be a measure of the contracting party's circumstances, state, environment, requirements, or conditions.

[0024] The contract information may include the appropriateness score for each of the multiple contracts after the amendment. For example, if the multiple contracts after the amendment are Contract A, Contract B, and Contract C, the contract information may include information such as the appropriateness score for Contract A being "1", the appropriateness score for Contract B being "8", and the appropriateness score for Contract C being "4".

[0025] The degree of appropriateness may be calculated based on at least one of the following: communication history information described below, requirements information described below, and user satisfaction (based on user surveys, etc.).

[0026] The acquisition unit 11 may further acquire pre-amendment contract information relating to the contract before the amendment. The pre-amendment contract information is arbitrary information relating to the contract before the amendment. The pre-amendment contract information may include the appropriateness of the (pre-amendment) contract.

[0027] The acquisition unit 11 may further acquire information relating to the basis for the advice described later (information that may serve as the basis for the advice described later).

[0028] For example, the acquisition unit 11 may further acquire communication history information, which is information about the user's (contract holder's) communication history, as information on the basis for the advice. Figure 3 is a diagram showing an example of a communication history information table. In the communication history information shown in Figure 3, "App" indicates the type of application used by the user on terminal 2, "Used Packet Amount" indicates the amount of packets (communication) used by the app, "Usage Time" indicates the time the app (or the app's communication) was used, and "Date" indicates the day the app (or the app's communication) was used.

[0029] For example, the acquisition unit 11 may further acquire requirement information, which is information regarding the contract holder's (user's) requirements for the contract, as information relating to the basis of the advice. The requirement information may be information generated based on communication history information. The requirement information may be specified (set) by the user themselves. For example, the requirement information may be information relating to requirements regarding the amount of packets used (requirements determined based on monthly usage; for example, if it is 20G per month, a 10% margin may be added, and 22G may be required). For example, the requirement information may be requirements regarding usage fees (for example, a maximum of 3500 yen). The requirement information may be a classification of the above requirements. For example, the requirement information may be classified as minimum usage less than 10G, minimum usage 10G or more, minimum usage 20G or more, minimum usage 30G or more, etc. For example, the requirement information may be classified as desired fee less than 1000 yen, desired fee less than 2000 yen, desired fee less than 3000 yen, desired fee less than 4000 yen, etc.

[0030] The requirements information may reflect the user's situation. For example, if the time of day and location information of applications run on terminal 2 can be obtained, it may be estimated whether terminal 2 is being used at home or while out. Alternatively, a survey may be conducted asking the user where they usually use data packets, and that information may be reflected in the requirements information. More specifically, if it can be estimated that mobile communication is being used in an environment with Wi-Fi (registered trademark), it may be assumed that the user will switch from mobile communication to Wi-Fi (registered trademark) communication in a Wi-Fi (registered trademark) environment, and this amount may be deducted from the requirements regarding the amount of data packets used in the requirements information.

[0031] Requirements information may include information about the user's attributes. For example, based on the user's past communication volume, requirements information may include attribute information such as "the user prioritizes communication usage."

[0032] The generation unit 12 generates a prompt to instruct the generation AI to generate arbitrary information.

[0033] Generative AI is a technology that, in response to input from a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output formats indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI generates response information based on that input information. The generative AI may be a conversational AI that includes, for example, a Large Language Model (LLM) and a User Interface (UI) for interacting with the user, enabling text-based or voice-based chat with the user. Examples of such generative AI include tsuzumi®, ChatGPT, GPT®-3.5, GPT-4V, and PaLM2.

[0034] The generated AI may be stored in another device connected to device 1 via a network, and configured to allow information exchange. Figure 4 shows an example of the relationship between device 1 and the generated AI. In the example relationship shown in Figure 4, the generated AI, LLM30, is stored in an external server 3. When needed, device 1 has LLM30 perform processing via the network, receives the execution results, and uses them.

[0035] The generated AI may be stored within device 1. Figure 5 shows a modified example of the relationship shown in Figure 4. In the modified example shown in Figure 4, the generated AI, LLM30, is stored within device 1. When necessary, device 1 executes processing on the LLM30 stored within device 1 and uses the execution result.

[0036] A prompt is information indicating instructions or questions to be entered by a user in an interactive system such as a conversation with a generating AI or a command-line interface (CLI). For example, a prompt may express in text the command to be executed by the generating AI, the task to be performed by the generating AI, the background / context that the generating AI should consider (e.g., role, conditions), the question that the generating AI should answer, and the output format of the response information from the generating AI. In addition, input information that will be the target of the command / task to be executed by the generating AI may be attached to the prompt. Such input information includes data files with filenames containing predetermined extensions, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0037] The generation unit 12 generates a prompt to instruct the generation AI to generate advice regarding the modified contract, based on the contract information acquired by the acquisition unit 11 (or stored by the storage unit 10). In this embodiment, the term "advice" may be replaced with suggestions, proposals, recommendations, text, or content, etc.

[0038] The advice may be advice for each of the multiple (modified) contracts, and may be advice based on the appropriateness of each. That is, the generation unit 12 may generate a prompt to instruct the generation AI to generate advice for each of the multiple contracts, and based on the appropriateness of each. For example, if the multiple modified contracts are contract A, contract B, and contract C, and their appropriateness levels are "1", "8", and "4", the advice may recommend each contract to the user in order of decreasing appropriateness, i.e., "contract B", "contract C", and "contract A".

[0039] The advice may include the basis for that advice. That is, the generation unit 12 may generate a prompt to instruct the generation AI to generate advice regarding the amended contract, including the basis for that advice. The advice may also include information regarding the basis for the advice obtained by the acquisition unit 11.

[0040] The prompt may include information about the contract holder's (user's) communication history (communication history information). That is, the generation unit 12 may generate a prompt that instructs the generation AI to generate advice regarding the modified contract, and may include the user's communication history information. The prompt may also include communication history information acquired by the acquisition unit 11.

[0041] The prompt may include information regarding the client's requirements for the contract (requirements information). That is, the generation unit 12 may generate a prompt that includes requirements information, which is a prompt for instructing the generation AI to generate advice regarding the amended contract. The prompt may also include requirements information acquired by the acquisition unit 11.

[0042] As mentioned above, by providing justification (as advised later) based on at least one of the communication history information and requirements information, it is possible to encourage users to make decisions based on economic rationality. For example, it is possible to quantitatively show, including predicted values, how much the monthly usage fee will be reduced or how much leeway there is in the monthly usage amount.

[0043] The prompt may include shots in few-shot prompting (few-shot prompt, few-shot learning) related to the basis for advice. That is, the generation unit 12 may generate a prompt for instructing generative AI to generate advice regarding the modified contract, the prompt including a shot related to the basis for the advice. The shot related to the basis for advice may be stored in advance by the storage unit 10, or may be acquired by the acquisition unit 11.

[0044] The prompt may include shots in few-shot prompting based on the cognitive bias of the contracting party (user). That is, the generation unit 12 may generate a prompt for instructing generative AI to generate advice regarding the modified contract, the prompt including a shot based on the user's cognitive bias. The shot based on the user's cognitive bias may be stored in advance by the storage unit 10, or may be acquired by the acquisition unit 11. The user's cognitive bias may be, for example, a cognitive bias determined by the apparatus 1 using existing technology based on information about the user.

[0045] The shot based on the user's cognitive bias described above enables modification of expressions to provide psychological encouragement, based on economic rationality, so that (the user) can make a rational judgment. In this way, instead of rephrasing text to promote upselling on the enterprise side, it may be rephrasing text to promote rational judgment on the user side.

[0046] The prompt may include information about the contract before modification (pre-modification contract information). That is, the generation unit 12 may generate a prompt for instructing generative AI to generate advice regarding the modified contract, the prompt including pre-modification contract information. The prompt may include the pre-modification contract information acquired by the acquisition unit 11.

[0047] The generation unit 12 may cause the LLM 30, which is a generative AI, to process the generated prompt, thereby instructing generation of advice on the modified contract, and may obtain the advice on the modified contract generated by the LLM 30 as a result. The generation unit 12 may cause the storage unit 10 to store the advice on the modified contract, or may output the advice to another function of the apparatus 1.

[0048] The generation unit 12 may cause the storage unit 10 to store the generated prompt, or may output the prompt to another functional block of the apparatus 1.

[0049] FIG. 6 is a diagram showing an example of a prompt generated by the generation unit 12.

[0050] In the example of the prompt shown in FIG. 6, the statement "Role: You are a mobile phone shop staff." sets the role of the generative AI. Describing the role contributes to improving the reliability of the advice content (reducing hallucinations) and increasing the user's sense of conviction.

[0051] In the example of the prompt shown in FIG. 6, the statement "Task: For the following user, please simulate the case where the user changes to the target price plan, and create a proposal document that explains the plans and their grounds in the order of recommended plans." specifies the processing to be executed by the generative AI.

[0052] In the example of the prompt shown in FIG. 6, the content "Conditions<Line break>Target user name: Toko Tarou<Line break>Current usage plan: eximon Current usage fee: 6000 yen per month<Line break>Target plans: apamo, iluma" ("<Line break>" indicates an actual line break position and is not included in the prompt as text; the same applies hereinafter) specifies the conditions for the generative AI to execute processing. Specifically, it specifies the name (target user name) of the user who is the target of the advice (target user), the user's current communication usage plan (price plan), the communication usage fee under the user's current (pre-modification) contract (the usage plan), and the target plan which is the post-modification contract.

[0053] Among the examples of prompts shown in Figure 6, "Target user usage history <newline> Monthly packet usage amount Monthly usage time <newline> 2 months ago ... ... <newline> 3 months ago ... ..." ("..." indicates that specific details have been omitted) specifies communication history information.

[0054] In the example of a prompt shown in Figure 6, "Customer's usage requirements: Monthly data usage 22GB, desired payment amount 4000 yen <newline> Customer attributes: A customer who prioritizes communication usage" specifies the requirements information.

[0055] In the example of Pront shown in Figure 6, "Appropriateness of price plan apamo: high, iluma: average" specifies the appropriateness ("high" and "average") for each of the multiple contracts ("apamo" and "iluma").

[0056] In the example of a prompt shown in Figure 6, the phrase "Example of evidence: <newline>You may be able to use it comfortably if you use the Iluma, Wi-Fi (registered trademark) environment." specifies a shot related to the basis of the advice. More specifically, it specifies a shot related to the basis for recommending the changed contract "Iluma".

[0057] In the example of a prompt shown in Figure 6, the sentence "Example of expression: <newline>If you don't change your plan now, you'll lose 20,000 yen a year." specifies a shot based on the target user's cognitive bias. More specifically, it specifies a shot based on loss aversion bias, which is a cognitive bias that the target user possesses.

[0058] In the example of the prompt shown in Figure 6, "Output Image (Omitted)" specifies the output image of the advice that the generating AI should generate (omitted in Figure 6).

[0059] Figure 7 shows an example of advice generated by the generating AI based on the prompt generated by the generation unit 12. In the example of advice shown in Figure 7, the current price plan for the target user "Tokomo Taro" is "eximon," and the recommended replacement price plans are "apamo" and "iluma," in that order, along with the rationale for each recommended replacement price plan.

[0060] The output unit 13 may output (transmit) any information to other devices such as terminal 2 or external server 3 via a network or the like. For example, the output unit 13 may output prompts generated by the generation unit 12, or advice regarding the revised contract obtained by the generation unit 12, to other devices.

[0061] Next, we will explain an example of the process performed by device 1, referring to Figure 8. Figure 8 is a flowchart showing an example of the process (generation process) performed by device 1.

[0062] First, the acquisition unit 11 acquires contract information relating to the amended contract (step S1, acquisition step). Next, the generation unit 12 generates a prompt to instruct the generation AI to generate advice relating to the amended contract based on the contract information acquired in step S1 (step S2, generation step).

[0063] Next, the effects and advantages of the apparatus 1 according to this embodiment will be described.

[0064] The device 1 includes an acquisition unit 11 that acquires contract information relating to the amended contract, and a generation unit 12 that generates a prompt to instruct an AI to generate advice relating to the amended contract based on the contract information acquired by the acquisition unit 11. With this configuration, contract information relating to the amended contract is acquired, and a prompt is generated to instruct an AI to generate advice relating to the amended contract based on the acquired contract information. In other words, it is possible to generate information that can generate advice relating to the amended contract.

[0065] In device 1, the contract information may include a degree of appropriateness for the contract. With this configuration, prompts are generated based on the degree of appropriateness for the contract, making it possible to generate information that can provide more accurate advice that takes the degree of appropriateness for the contract into account.

[0066] In device 1, the contract information may include the appropriateness level for each of the multiple contracts after the modification, and the advice may be advice for each of the multiple contracts, based on their respective appropriateness levels. With this configuration, for example, it is possible to generate information that can produce more accurate advice that takes into account the appropriateness level for each of the multiple contracts.

[0067] In device 1, the advice may include the rationale behind it. This configuration allows for the generation of information that, by including the rationale, can produce more convincing advice.

[0068] In device 1, the contract may also relate to the subscriber's communications, and the prompt may include information regarding the subscriber's communication history. This configuration makes it possible to generate information that, for example, provides advice regarding a revised contract relating to the subscriber's communications, and that can generate more accurate advice that takes into account the subscriber's communication history.

[0069] In device 1, the prompt may include information regarding the client's requirements for the contract. This configuration allows for the generation of information that can, for example, generate more accurate advice that takes into account the client's requirements for the contract.

[0070] In device 1, the prompt may include shots in few-shot prompting regarding the basis for the advice. This configuration allows for the generation of information that can generate advice that reflects shots regarding the basis for the advice.

[0071] In device 1, the prompt may include a shot in a few-shot prompting based on the client's cognitive bias. This configuration allows for the generation of information that can generate advice that reflects a shot based on the client's cognitive bias.

[0072] In device 1, the prompt may include information about the contract before the change. This configuration allows for the generation of information that can provide more accurate advice, for example, by taking the contract before the change into account.

[0073] Traditionally, when considering mobile carrier pricing plans, there have been services that simulate costs by having users answer several questionnaire items. There are also services that estimate the "monthly payment amount" from two months onward based on the user's current contract status and the average data usage over the past three months, or that perform price simulations for a line selected by the user.

[0074] However, each user has different requirements for what constitutes a comfortable service. For example, for users who don't use their mobile phones very often, affordability is important. On the other hand, for users who enjoy real-time online games or watching videos, the smoothness of the connection is extremely important. Because each user has different requirements, simply simulating the cost is not enough to provide users with appropriate information.

[0075] Device 1 can, for example, provide users with advice regarding their revised pricing plans (contracts). This allows users to optimize their line contracts, for example.

[0076] The apparatus 1 of this disclosure may have the following configuration.

[0077] [1] An apparatus comprising: an acquisition unit that acquires contract information relating to a revised contract; and a generation unit that generates a prompt to instruct an AI to generate advice relating to the revised contract based on the contract information acquired by the acquisition unit.

[0078] [2] The apparatus described in [1], wherein the contract information includes the degree of appropriateness for the contract.

[0079] [3] The apparatus as described in [1] or [2], wherein the contract information includes the degree of appropriateness for each of the multiple contracts after the change, and the advice is advice relating to each of the multiple contracts and based on the degree of appropriateness for each of them.

[0080] [4] The apparatus described in any one of paragraphs [1] to [3], including the basis for the advice.

[0081] [5] The Contract relating to the communications of the Contractor, the prompt including information relating to the communications history of the Contractor, the apparatus as described in any one of paragraphs [1] to [4].

[0082] [6] The apparatus described in any one of paragraphs [1] to [5], wherein the prompt includes information relating to the contractor's requirements for the contract.

[0083] [7] The apparatus according to any one of [1] to [6], wherein the prompt includes a shot in a few-shot prompting relating to the basis for the advice.

[0084] [8] The apparatus according to any one of paragraphs [1] to [7], wherein the prompt includes a shot in a few-shot prompting based on the client's cognitive bias.

[0085] [9] The prompt includes information about the contract before the change, as described in any one of paragraphs [1] to [8].

[0086] The block diagrams used in the description of the above embodiments show functional units. 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 one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0087] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0088] For example, Apparatus 1 in one embodiment of the present disclosure may function as a computer that processes the method of the present disclosure. Figure 9 is a diagram showing an example of the hardware configuration of Apparatus 1 according to one embodiment of the present disclosure. Physically, Apparatus 1 may be configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0089] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of device 1 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0090] Each function in device 1 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0091] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the acquisition unit 11, generation unit 12, and output unit 13 described above may be implemented by the processor 1001.

[0092] Furthermore, the processor 1001 reads programs (program code), 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 accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the acquisition unit 11, the generation unit 12, and the output unit 13 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but 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 program may also be transmitted from a network via a telecommunications line.

[0093] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present disclosure.

[0094] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., Compact Disc, Digital Multipurpose Disc, Blu-ray® Disc), a smart card, flash memory (e.g., a card, stick, key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0095] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the acquisition unit 11, generation unit 12 and output unit 13 described above may be implemented by the communication device 1004.

[0096] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0097] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0098] Furthermore, the device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0099] The notification of information is not limited to the manner / embodiments described herein and may be carried out by other means.

[0100] Each aspect / embodiment described in this disclosure may be applied to at least one of the following systems: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0101] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0102] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0103] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0104] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0105] Although the present disclosure has been described in detail above, it will be 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 intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0106] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0107] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0108] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0109] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0110] The terms “system” and “network” as used in this disclosure are interchangeable.

[0111] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0112] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure.

[0113] The terms “determining” and “decision” as used in this disclosure may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, inquiry (e.g., searching in tables, databases or other data structures), and ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory). Furthermore, “determining” may include resolving, selecting, choosing, establishing, and comparing. In other words, "judgment" and "decision" can include considering that some action has been "judged" or "decided." Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0114] The terms “connected,” “coupled,” and any variations thereof mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0115] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0116] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0117] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0118] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0119] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0120] In this 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 "combine" may be interpreted similarly to "different."

[0121] 1...device, 2...terminal, 3...external server, 4...system, 10...storage unit, 11...acquisition unit, 12...generation unit, 13...output unit, 30...LLM, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An apparatus comprising: an acquisition unit that acquires contract information relating to a revised contract; and a generation unit that generates a prompt to instruct an AI to generate advice relating to the revised contract based on the contract information acquired by the acquisition unit.

2. The apparatus according to claim 1, wherein the contract information includes the degree of appropriateness for the contract.

3. The apparatus according to claim 1, wherein the contract information includes the degree of appropriateness for each of the multiple amended contracts, and the advice is advice relating to each of the multiple contracts and based on the degree of appropriateness for each of them.

4. The apparatus according to claim 1, wherein the advice includes the basis for said advice.

5. The apparatus according to claim 1, wherein the contract relates to the communications of the contracting party, and the prompt includes information relating to the communications history of the contracting party.

6. The apparatus according to claim 1, wherein the prompt includes information relating to the contractor's requirements for the contract.

7. The apparatus according to claim 1, wherein the prompt includes a shot in a few-shot prompting relating to the basis for the advice.

8. The apparatus according to claim 1, wherein the prompt includes a shot in a few-shot prompting based on the client's cognitive bias.

9. The apparatus according to claim 1, wherein the prompt includes information regarding the contract prior to the change.

10. A method performed by a computer, comprising: an acquisition step of acquiring contract information relating to a modified contract; and a generation step of generating a prompt to instruct a generating AI to generate advice relating to the modified contract based on the contract information acquired in the acquisition step.

Images