Generation device and generation method

Abstract

A RAG system 20 comprises: a reception unit 21 that receives information regarding terms of use of a commodity or a service, and information regarding the commodity or the service; an extraction unit 22 that extracts a feature portion in the information regarding terms of use on the basis of information regarding the commodity or the service; a determination unit 23 that determines influence information regarding the influence of the feature portion on a user of the commodity or the service; a generation unit 24 that generates a prompt for indicating generation of content for explaining information regarding terms of use on the basis of the influence information; and an input unit 25 that controls a generative AI model 31 for generating the content on the basis of the prompt.

Description

Generation device and generation method

[0001] One aspect of the present disclosure relates to a generating device and a generating method.

[0002] Patent Document 1 discloses a technique for unifying various expressions in privacy policies.

[0003] Japanese Patent Application Laid-Open No. 2018-147299

[0004] Here, information such as terms of use and privacy policy (information on terms of use) can be skipped by users due to its volume or difficulty to understand. Providers of products (businesses) want to ensure that users fully understand the important parts of the information on terms of use in order to avoid any future problems with users.

[0005] The present disclosure has been made in consideration of the above-mentioned situation, and aims to provide a generation device and a generation method that can avoid subsequent problems by properly explaining information regarding terms of use to users.

[0006] A generation device according to one aspect of the present disclosure includes a reception unit that receives information regarding the terms of use of a product or service and the product or service information, an extraction unit that extracts characteristic parts of the information regarding the terms of use based on the product or service information, a determination unit that determines impact information regarding the impact that the characteristic parts will have on users of the product or service, a generation unit that generates a prompt to instruct the generation of content that explains the information regarding the terms of use based on the impact information, and a control unit that controls a generation AI model that generates the content based on the prompt.

[0007] In a generation device according to one aspect of the present disclosure, characteristic portions of information regarding terms of use are extracted based on information about a product or the like, impact information regarding the impact of the characteristic portions on a user is determined, a prompt for generating content explaining the information about the terms of use is generated based on the impact information, and the prompt is input to a generation AI model. With this configuration, characteristic portions of the terms of use are extracted based on information about the product or the like, and explanatory content about the terms of use is generated taking into account the impact of the characteristic portions on a user. This allows information included in the terms of use that is characteristic and highly important (has a large impact) to users of the product or the like to be appropriately explained to the user. This allows information about the terms of use to be appropriately explained to the user, and ultimately avoids subsequent problems between the user and the provider (business operator) (problems resulting from the user's insufficient understanding of the information about the terms of use).

[0008] According to one aspect of the present disclosure, subsequent problems can be avoided by properly explaining information regarding terms of use to users.

[0009] Fig. 1 is a diagram showing the device configuration of a content generation system according to this embodiment. Fig. 2 is a diagram showing an example of a prompt generated by the RAG system. Fig. 3 is a diagram showing an example of output. Fig. 4 is a diagram showing an example of output. Fig. 5 is a diagram showing an example of output. Fig. 6 is a flowchart showing processing executed by the RAG system. Fig. 7 is a diagram showing an example of the hardware configuration of the RAG system.

[0010] The embodiments of the present disclosure will be described with reference to the accompanying drawings. Where possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0011] FIG. 1 is a diagram illustrating the device configuration of a content generation system according to this embodiment. The content generation system illustrated in FIG. 1 is a system that generates content explaining information related to the terms of use of a product or service. Hereinafter, the product or service will be referred to as a "product, etc." The information related to the terms of use may be, for example, a terms of use or a privacy policy. Terms of use are information that specifies rules regarding the handling and use of a product, etc., including, for example, a provision that suspends service provision to a user if a specific act is performed, or a provision that a penalty will be charged. A privacy policy is information that specifies how a user's personal information is handled, including, for example, a provision that uses (provides) the user's information for a specific purpose. The content explaining the information related to the terms of use may be content that summarizes part of the information related to the terms of use, or may be content that adds explanatory text, images, etc. to a summary of the information related to the terms of use.

[0012] 1, the content generation system includes a terminal 10, a Retrieval-Augmented Generation (RAG) system 20, and a server device 30, which are configured to be able to communicate with each other via a network including a wireless communication network and a fixed communication network. The RAG system 20 constitutes a generation device that generates a prompt based on information received from the terminal 10. A prompt is information indicating an instruction or question input to an AI model in an interactive system such as a dialogue with an AI model or a command line interface (CLI).

[0013] The terminal 10 is a device used by a user of the product or the like (a user who views content that explains information about terms of use). The terminal 10 is, for example, a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, a game console, or the like. Note that while only two terminals 10 are illustrated in FIG. 1, the content generation system may include any number of terminals 10 greater than or equal to two.

[0014] The server device 30 is a device that stores a generative AI model 31 and enables the provision of content (content explaining information regarding terms of use) to users using the generative AI model 31. The generative AI model is a model that can generate content in response to a prompt including input information, according to any one or a combination of the instructions, context, question, and output format indicated by the prompt, and return the content as response information. The prompt can also include input information, in which case the generative AI model 31 generates response information targeted at the input information. The generative AI model 31 may be, for example, an interactive AI that includes a large language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this embodiment, an example is described in which the server device 30 provides content, etc., using one generative AI model 31. However, the server device 30 may also provide content, etc., using multiple generative AI models. Although only one server device 30 is illustrated in FIG. 1 , the content generation system may include multiple server devices 30. Furthermore, although the above describes an example of a large-scale language model, other AI models may also be used. The generative AI model 31 generates a question or answer for the user based on a prompt.

[0015] The RAG system 20 includes, as functional components, a reception unit 21, an extraction unit 22, a determination unit 23, a generation unit 24, an input unit 25 (control unit), and a storage unit 26. The RAG system 20 inputs a prompt corresponding to input information from the terminal 10 to the server device 30, and relays response information from the server device 30 to the prompt to the terminal 10. The RAG system 20 also has a function to generate a prompt based on the input information from the terminal 10. The function of each functional unit of the RAG system 20 will be described in detail below.

[0016] The reception unit 21 receives information regarding the terms of use of the product, etc., and information about the product, etc. The reception unit 21 receives the above-mentioned various information from the terminal 10 operated by the user of the product, etc. The terminal 10 transmits the above-mentioned various information to the RAG system 20 in response to an operation performed by the user when a privacy policy, etc. is displayed, for example, when purchasing a product, etc. (for example, the user selects the "Point Check" button shown in the left diagram of Figure 3). The reception unit 21 receives the above-mentioned various information transmitted from the terminal 10. Note that the reception unit 21 may also receive the above-mentioned various information from a device other than the terminal 10. The reception unit 21 outputs the received information to the extraction unit 22.

[0017] As described above, the information regarding the terms of use of the product, etc. is the terms of use or the privacy policy. The information regarding the product, etc. is information indicating the product, etc., such as the name of the product, the name of the type (category) of the product, etc.

[0018] The reception unit 21 may further receive user information in addition to the various types of information described above. User information is information about the user, such as user history information or user attribute information. User history information is information about the user's past viewing history of information about the terms of use for one or more products, etc. User history information may be information indicating what products, etc., which parts of the terms of use the user viewed, and for how long. User attribute information may include the user's age, generation, preference information, etc. Preference information may include, for example, information about what type of output content (videos, leaflets, etc.) the user prefers.

[0019] The extraction unit 22 extracts characteristic portions from the information regarding the terms of use based on information about the product, etc. The extraction unit 22 may, for example, extract portions that are thought to have a significant impact on the user when using the product, etc. (i.e., portions that may cause future trouble if not understood) as characteristic portions from the information regarding the terms of use. For example, the storage unit 26 may store, for each product, etc. (or for each type of product, etc.), cases in which a violation of the terms of use has led to a claim, lawsuit, or other trouble, by associating the relevant portions of the terms of use with the details of the trouble as trouble occurrence events. The extraction unit 22 may then refer to the trouble occurrence events stored in the storage unit 26 and extract portions corresponding to the information about the product, etc. In other words, the extraction unit 22 may extract, as characteristic portions, information related to the details previously stored as trouble occurrence events from the information regarding the terms of use received by the reception unit 21.

[0020] The extraction unit 22 may extract, as characteristic portions of the information regarding the terms of use, portions that are likely to be unfamiliar to users and that they do not understand. For example, the storage unit 26 may store common content (common terms of use) in the terms of use for each type of product, etc. Such common terms of use are relatively familiar to users, and information other than the common terms of use is unfamiliar to users. The extraction unit 22 may extract characteristic portions from information regarding the terms of use received by the reception unit 21 other than the common terms of use (common terms of use stored in the storage unit 26) that is pre-associated with a type of product, etc. identified from the information regarding the product, etc. received by the reception unit 21. The type of product, etc. identified from the information regarding the product, etc. may be, for example, the type (category) of product, etc. indicated in the information regarding the product, etc., or a type of product, etc. similar to the product, etc. indicated in the information regarding the product, etc. This makes it possible, for example, to pre-register common content in terms of use for rental clothing offered by multiple different businesses and extract any content that differs from the pre-registered content as characteristic portions.

[0021] Furthermore, the extraction unit 22 may extract characteristic portions from information related to the terms of use received by the reception unit 21 other than common terms of use (common terms of use stored in the storage unit 26) that are associated in advance with a type of product, etc. that is not similar (dissimilar) to the product, etc. identified from the information on the product, etc. received by the reception unit 21. This makes it possible, for example, when the product, etc. is rental clothing, to register in advance content common to terms of use for rental DVDs (products, etc., dissimilar to clothing) provided by multiple different businesses, and extract those that differ from this as characteristic portions.

[0022] Common content of the terms of use includes, for example, information indicating the type of product, prohibited actions by users (for example, damaging rental products (in a malicious manner)), and consequences of prohibited actions (for example, payment will be charged up to the product price set by the manufacturer, etc.).

[0023] The determination unit 23 determines impact information regarding the impact that the characteristic portion extracted by the extraction unit 22 has on the user of the product, etc. For example, the storage unit 26 may store a learning model that has learned the relationship between the content of a sentence and the degree of impact on the user. The determination unit 23 may then input the content of the sentence corresponding to the characteristic portion into the learning model, thereby deriving the degree of impact that the content of the sentence corresponding to the characteristic portion has on the user, and determine the degree of impact as the impact information.

[0024] For example, suppose that the following sentence has been extracted as a characteristic part: "If you damage a rental product (and if the damage is severe), we will charge you up to the product price set by our company." In this case, the determination unit 23 inputs the sentence into the learning model and obtains an output value indicating the degree of influence (e.g., "0.77").

[0025] The determination unit 23 may determine information other than the degree of impact as the impact information. For example, the storage unit 26 may store a learning model that has learned the relationship between the content of a sentence and the type of impact on a user. The learning model may have learned the relationship between the content of a sentence and tag information indicating the type of impact (loss of a rental item, damage to a rental item, etc.). The determination unit 23 may then input the content of a sentence corresponding to a characteristic portion into the learning model, thereby deriving the type of impact that the content of the sentence corresponding to the characteristic portion has on a user, and determine the type of impact as the impact information.

[0026] For example, suppose that the following sentence has been extracted as a feature portion: "If you damage a rental product (and if the damage is severe), we will charge you up to the product price set by our company." In this case, the determination unit 23 inputs the sentence into the learning model and obtains an output of the impact type, for example, "damage to rental product."

[0027] The generation unit 24 generates a prompt for instructing the generation of content explaining information related to the terms of use based on the impact information determined by the determination unit 23. The prompt uses text to express, for example, commands to be executed by the generation AI model 31 (interactive AI model), tasks to be executed by the generation AI model 31, background / context (e.g., roles, conditions) to be considered by the generation AI model 31, questions to be answered by the generation AI model 31, and the output format of response information from the generation AI model 31. The prompt may also include input information to be used as the target of commands / tasks to be executed by the generation AI model 31. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data refers to data such as document data, table data, and graph data that can be processed by a default application program.

[0028] FIG. 2 is a diagram showing an example of a prompt generated by the RAG system 20. The prompt shown in FIG. 2 specifies a role, a task, a condition, and an output format. The role is information that specifies what role the generative AI model 31 will play in outputting, and here it is specified as "You are a lawyer." The task is information that indicates an outline of the instructions to the generative AI model 31, and here it is specified as "Generate a text document that explains the characteristic parts of the terms of use."

[0029] The condition is information indicating detailed conditions for the task. In the example shown in FIG. 2, the condition is specified as "Please refer to the impact level. Also, please write an explanation by referring to the commentary information." The impact level is the impact level derived by the determination unit 23. The commentary information is, for example, information (explanation or advice) set according to the type of impact derived by the determination unit 23 (details will be described later). In the example shown in FIG. 2, the prompt specifically exemplifies the characteristic parts of the terms of use, the impact level, and the commentary information. In this way, the condition may include examples.

[0030] In the example shown in Figure 2, the condition states, "Please write a description of the features that explains the differences from general terms of use," and an example of general terms of use is given. Furthermore, the condition states, "Please also include a legal explanation in accordance with the Civil Code."

[0031] The output format is information that indicates the final format in which the content will be output. In the example shown in Figure 2, three types of information are specified as the output format: "content of the characteristic part," "explanation of the characteristic part," and "legal commentary."

[0032] As described above, the generation unit 24 may specify the characteristic part and the impact information, and may generate a prompt that instructs the user to explain the characteristic part based on the impact information (impact level). The generation unit 24 may output the characteristic part and the impact information in the prompt only when the impact level exceeds a predetermined threshold (e.g., 0.6).

[0033] The generation unit 24 may generate a prompt that instructs the user to determine an upper limit of the number of characters for the description of the characteristic part based on the influence information (degree of influence). The generation unit 24 may determine a higher upper limit of the number of characters as the degree of influence increases.

[0034] The generation unit 24 may generate a prompt that instructs providing an explanation or advice for each type of impact derived by the determination unit 23. In this case, the storage unit 26 stores, for example, commentary information (explanation or advice) for each type of impact. The generation unit 24 then refers to the storage unit 26 to identify the commentary information (explanation or advice) corresponding to the type of impact derived by the determination unit 23. The generation unit 24 may exemplify the identified commentary information in the prompt.

[0035] The generation unit 24 may generate a prompt that instructs the user to determine an upper limit of the number of characters for the description of the characteristic part based on the user's history information received by the reception unit 21, specifically, the user's viewing history of information regarding the terms of use of one or more products, etc. More specifically, the generation unit 24 may generate a prompt that instructs the user to determine an upper limit of the number of characters for the description of the characteristic part based on the history information and the impact information. In this case, if the generation unit 24 determines from the history information that the user views the terms of use for a long time, the generation unit 24 may lower the upper limit of the number of characters and reduce the amount of description because the user views the terms of use carefully. Furthermore, if the generation unit 24 determines from the history information that the user views the terms of use for a long time, the generation unit 24 may increase the upper limit of the number of characters and increase the amount of description because the user may not understand the terms of use even if they read them carefully.

[0036] The generation unit 24 may generate a prompt indicating the output type of content based on the user attribute information received by the reception unit 21. For example, the generation unit 24 may indicate the output type as a video for young people and a leaflet for people other than young people, or may change the output type based on the user's setting information.

[0037] The input unit 25 controls the generative AI model 31 based on the prompt generated by the generation unit 24. The input unit 25 inputs the prompt to the generative AI model 31. The generative AI model 31 generates and outputs content that explains information related to the terms of use in response to the input prompt.

[0038] 3 to 5 are diagrams showing examples of content output (examples of the final display on the terminal 10). The left diagram of FIG. 3 shows the state before content explaining information about the terms of use is displayed. When the user presses the "Point Check" and "Agree" buttons on this screen, content explaining information about the terms of use is generated through the various processes described above, and the screens shown in the center diagram and the right diagram of FIG. 3 are displayed. Note that the center diagram and the right diagram of FIG. 3 are, for example, screens that transition between each other (screens on different pages). As shown in the center diagram and the right diagram of FIG. 3, from top to bottom, the screen lists the type of terms of use, a summary of the terms of use, an illustration evocative of the summary content, and a legal explanation in accordance with the Civil Code. Note that where the type of terms of use is indicated, a link or the like may be provided to allow the user to navigate to the source of the summarized terms of use.

[0039] Furthermore, as shown in Figure 4, content explaining information regarding the terms of use may be displayed in leaflet format, or as shown in Figure 5, content explaining information regarding the terms of use may be displayed in video format.

[0040] Next, the processing executed by the RAG system 20 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the processing executed by the RAG system.

[0041] As shown in FIG. 6, first, the RAG system 20 receives information on terms of use and information on products and the like from the user via the terminal 10 (step S1).

[0042] Next, in the RAG system 20, characteristic parts of the information regarding the terms of use are extracted based on the information about the product, etc. (step S2).

[0043] Next, in the RAG system 20, influence information regarding the influence that the characteristic portion has on the user of the product or the like is determined (step S3).

[0044] Next, a prompt is generated based on the impact information to instruct the generation of content (explanation content) that explains the information regarding the terms of use (step S4).

[0045] Finally, in the RAG system 20, the generated prompt is input to the generative AI model 31 (step S5).

[0046] Next, the effects of the RAG system 20 according to this embodiment will be described.

[0047] The RAG system 20 of this embodiment comprises a reception unit 21 that receives information regarding the terms of use of a product or service and information about the product or service, an extraction unit 22 that extracts characteristic parts of the information regarding the terms of use based on the information about the product or service, a determination unit 23 that determines impact information regarding the impact that the characteristic parts will have on users of the product or service, a generation unit 24 that generates a prompt to instruct the generation of content that explains the information about the terms of use based on the impact information, and an input unit 25 that controls a generation AI model 31 that generates content based on the prompt.

[0048] In the RAG system 20 according to this embodiment, characteristic portions of the information on the terms of use are extracted based on information on the product, etc., impact information relating to the impact of the characteristic portions on the user is determined, a prompt for generating content explaining the information on the terms of use is generated based on the impact information, and the prompt is input to the generation AI model 31. With this configuration, characteristic portions of the terms of use are extracted based on information on the product, etc., and explanatory content on the terms of use is generated taking into account the impact of the characteristic portions on the user. This allows information included in the terms of use that is characteristic and highly important (has a large impact) to the user of the product, etc. to be appropriately explained to the user. This allows information on the terms of use to be appropriately explained to the user, and ultimately avoids subsequent problems between the user and the provider (business operator) (problems resulting from the user's insufficient understanding of the information on the terms of use).

[0049] The extraction unit 22 may extract, as characteristic parts, information other than the common terms of use that is associated in advance with the type of product or service identified from the product or service information received by the reception unit 21, from the information regarding the terms of use received by the reception unit 21. This makes it possible to appropriately extract, as characteristic parts, content that is unfamiliar to users and that is likely not understood by the users, and to appropriately explain to the users information that contributes to avoiding trouble.

[0050] The extraction unit 22 may extract, as a characteristic part, information related to contents that have been stored in advance as trouble occurrence matters from the information related to the terms of use received by the reception unit 21. This makes it possible to appropriately explain to the user information that contributes to avoiding trouble.

[0051] The determination unit 23 may use a learning model that has learned the relationship between the content of a sentence and the degree of influence it has on a user to derive the degree of influence that the content of a sentence corresponding to a characteristic part has on a user, and determine the degree of influence as the influence information. This makes it possible to easily and accurately derive the degree of influence, and to easily and appropriately explain to the user information that is highly important (has a large influence) to the user.

[0052] The generation unit 24 may define the characteristic part and the impact information, and may generate a prompt that instructs the user to explain the characteristic part based on the impact information. This allows content that appropriately explains the characteristic part according to the impact information to be generated, making it possible to easily and appropriately explain information that is highly important (has a large impact) to the user.

[0053] The generation unit 24 may generate a prompt that instructs determining an upper limit of the number of characters for the description of the characteristic part based on the impact information. This allows the upper limit of the number of characters for the description of the characteristic part to be determined taking into account the degree of impact, making it possible, for example, to increase the amount of description for information with a large degree of impact.

[0054] The determination unit 23 may use a learning model that has learned the relationship between the content of the sentence and the type of impact on the user to derive the type of impact that the content of the sentence corresponding to the characteristic part has on the user and determine the type of impact as impact information, and the generation unit 24 may generate a prompt that instructs the provision of an explanation or advice for each type of impact. This allows an appropriate explanation to be given according to the type of impact, making it possible to appropriately avoid subsequent problems.

[0055] The receiving unit 21 may further receive history information regarding the user's past viewing history of information regarding the terms of use of one or more products or services, and the generating unit 24 may generate a prompt that instructs the user to determine an upper limit on the number of characters for the description of the characteristic part based on the history information and the impact information. This makes it possible to lower the upper limit on the number of characters and reduce the amount of description for a user who views carefully, for example, and to display content appropriate to the user's viewing style.

[0056] The receiving unit 21 may further receive attribute information of the user, and the generating unit 24 may generate a prompt indicating the type of content to output based on the attribute information. This makes it possible to display content that is easy for the user to view appropriately, such as outputting a video for a young user.

[0057] The generating device and generating method of the present disclosure have the following configuration.

[0058] [1] A generation device comprising: a reception unit that receives information regarding terms of use for a product or service and information about the product or service; an extraction unit that extracts characteristic parts in the information regarding the terms of use based on the information about the product or service; a determination unit that determines impact information regarding the impact that the characteristic parts will have on a user of the product or service; a generation unit that generates a prompt to instruct the generation of content that explains the information about the terms of use based on the impact information; and a control unit that controls a generation AI model that generates the content based on the prompt.

[0059] [2] The generation device described in [1], wherein the extraction unit extracts, from the information regarding the terms of use received by the reception unit, information other than common terms of use that is pre-associated with the type of product or service identified from the information regarding the product or service received by the reception unit, as the characteristic part.

[0060] [3] The generation device according to [1] or [2], wherein the extraction unit extracts, from the information about the terms of use received by the reception unit, information related to content that has been pre-stored as a problem occurrence item, as the characteristic part.

[0061] [4] The generating device according to any one of [1] to [3], wherein the determination unit uses a learning model that has learned the relationship between the content of a sentence and the degree of influence it has on a user to derive the degree of influence that the content of a sentence corresponding to the characteristic part has on a user, and determines the degree of influence as the influence information.

[0062] [5] The generating device according to any one of [1] to [4], wherein the generating unit defines the characteristic part and the impact information, and generates the prompt that instructs the user to explain the characteristic part based on the impact information.

[0063] [6] The generating device according to any one of [1] to [5], wherein the generating unit generates the prompt instructing the user to determine an upper limit on the number of characters for the description of the characteristic part based on the impact information.

[0064] [7] A generation device described in any one of [1] to [6], wherein the determination unit uses a learning model that has learned the relationship between the content of the sentence and the type of impact it has on the user to derive the type of impact that the content of the sentence corresponding to the characteristic part has on the user, and determines the type of impact as the impact information, and the generation unit generates the prompt that instructs the provision of an explanation or advice for each type of impact.

[0065] [8] The generation device according to any one of [1] to [7], wherein the reception unit further receives historical information regarding the user's past viewing history of information regarding terms of use of one or more products or services, and the generation unit generates the prompt instructing the user to determine an upper limit on the number of characters for the description of the characteristic part based on the historical information and the impact information.

[0066] [9] The generation device according to any one of [1] to [8], wherein the reception unit further receives attribute information of the user, and the generation unit generates the prompt indicating an output type of the content based on the attribute information.

[0067]

[10] A method for generating a prompt by a generating device, the method including: receiving information regarding terms of use for a product or service and information about the product or service; extracting characteristic parts in the information about the terms of use based on the information about the product or service; determining impact information regarding the impact of the characteristic parts on a user of the product or service; generating a prompt for instructing the generation of content explaining the information about the terms of use based on the impact information; and controlling a generative AI model that generates the content based on the prompt.

[0068] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or 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 connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0069] 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.

[0070] For example, the RAG system 20 constituting the content generation system according to an embodiment of the present disclosure may function as a computer that performs processing of the control method of the present disclosure. Figure 7 is a diagram illustrating an example of the hardware configuration of the RAG system 20 according to this embodiment. The above-described RAG system 20 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, and the like. The RAG system 20 may be configured as a computer device including at least one processor, such as a CPU or GPU, or may be configured as a computer device including multiple processors or may include multiple computer devices. The terminal 10 and the server device 30 may also have a similar hardware configuration.

[0071] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the RAG system 20 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0072] Each function in the RAG system 20 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.

[0073] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 21, extraction unit 22, determination unit 23, generation unit 24, input unit 25, etc. may be realized by the processor 1001.

[0074] 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 programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the reception unit 21, extraction unit 22, determination unit 23, generation unit 24, and input unit 25 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also 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 also be transmitted from a network via a telecommunications line.

[0075] The memory 1002 is a computer-readable recording medium and may be configured, for example, by 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 control method according to an embodiment of the present disclosure.

[0076] 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.

[0077] 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, or a communication module. 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). For example, the above-mentioned reception unit 21, input unit 25, etc. may be realized by the communication device 1004.

[0078] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts 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. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0079] 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.

[0080] Furthermore, the RAG system 20 may 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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).

[0085] 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).

[0086] 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 for illustrative purposes only and does not limit the present disclosure in any way. For example, while the terminal 10, the RAG system 20, and the server device 30 (devices that store the generative AI model 31) have been described, these configurations (functions) may be implemented entirely in the terminal 10, entirely in a cloud device, or in one or more other terminals and devices. Furthermore, the functions of the RAG system 20 and the functions of the generative AI model 31 may be implemented in the same device or in different devices.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0094] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0095] 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.

[0096] The terms "connected," "coupled," or any variation thereof, refer to 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" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0097] 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."

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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."

[0102] 20...RAG system (generation device), 21...reception unit, 22...extraction unit, 23...determination unit, 24...generation unit, 25...input unit, 31...generated AI model.

Claims

1. A generation device comprising: a reception unit that receives information regarding terms of use for a product or service and information about the product or service; an extraction unit that extracts characteristic parts of the information about the terms of use based on the information about the product or service; a determination unit that determines impact information regarding the impact that the characteristic parts will have on users of the product or service; a generation unit that generates a prompt to instruct the generation of content that explains the information about the terms of use based on the impact information; and a control unit that controls a generation AI model that generates the content based on the prompt.

2. The generation device of claim 1, wherein the extraction unit extracts, from the information regarding the terms of use received by the reception unit, information other than common terms of use that is pre-associated with the type of product or service identified from the product or service information received by the reception unit, as the characteristic portion.

3. The generation device according to claim 1, wherein the extraction unit extracts, from the information regarding the terms of use received by the reception unit, information related to content that has been pre-stored as a problem occurrence item as the characteristic part.

4. The generation device of claim 1, wherein the determination unit uses a learning model that has learned the relationship between the content of the sentence and the degree of influence it has on the user to derive the degree of influence that the content of the sentence corresponding to the characteristic part has on the user, and determines the degree of influence as the influence information.

5. The generating device according to claim 1, wherein the generating unit defines the characteristic portion and the impact information, and generates the prompt that instructs to explain the characteristic portion based on the impact information.

6. The generating device according to claim 1, wherein the generating unit generates the prompt instructing to determine an upper limit of the number of characters for the description of the characteristic part based on the influence information.

7. The generation device described in claim 1, wherein the determination unit uses a learning model that has learned the relationship between the content of the sentence and the type of impact it has on the user to derive the type of impact that the content of the sentence corresponding to the characteristic part has on the user and determines the type of impact as the impact information, and the generation unit generates the prompt that instructs the provision of explanation or advice for each type of impact.

8. The generation device of claim 1, wherein the reception unit further receives historical information regarding the user's past viewing history of information regarding the terms of use of one or more products or services, and the generation unit generates the prompt instructing the user to determine an upper limit on the number of characters for describing the characteristic part based on the historical information and the impact information.

9. The generating device according to claim 1, wherein the receiving unit further receives attribute information of the user, and the generating unit generates the prompt indicating an output type of the content based on the attribute information.

10. A method for generating a prompt by a generation device, comprising: receiving information regarding the terms of use of a product or service and information about the product or service; extracting characteristic parts of the information about the terms of use based on the information about the product or service; determining impact information regarding the impact of the characteristic parts on users of the product or service; generating a prompt based on the impact information to instruct the generation of content that explains the information about the terms of use; and controlling a generative AI model that generates the content based on the prompt.

Images