Generation device and generation method

Abstract

According to the present invention, a RAG system comprises: a reception unit that receives hearing request information for a pseudo market investigation of a commodity or the like; an acquisition unit that acquires information on a target setting of a commodity or the like in response to the reception of the hearing request information; a generation unit that generates a prompt for instructing generation of information related to a target such as a commodity on the basis of the information on the target setting; and an input unit that controls a generative AI model for generating information related to the target 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 generating a persona by breaking down components such as input keywords into a hierarchical structure.

[0003] JP 2011-100380 A

[0004] Here, conducting market research on a product or service requires significant time and financial costs.

[0005] The present disclosure has been made in consideration of the above-described circumstances, and aims to provide a generation device and a generation method that can conduct research on products or services quickly and at low cost.

[0006] A generation device according to one aspect of the present disclosure includes a reception unit that receives hearing request information for pseudo-market research on a product or service, an acquisition unit that acquires information related to target settings for the product or service in response to the reception of the hearing request information, a generation unit that generates a prompt to instruct the generation of information related to the target of the product or service based on the information related to the target setting, and a control unit that controls a generation AI model that generates information related to the target based on the prompt.

[0007] In a generation device according to one aspect of the present disclosure, information regarding target setting for a product or the like is acquired in response to hearing request information for a pseudo market research. A prompt is generated based on the acquired information, instructing the generation of information related to the target for the product or the like. The information related to the target is then generated by a generation AI model based on the prompt. This configuration automates the process from acquiring information related to target setting to generating the prompt and generating information related to the target by the generation AI model, thereby enabling easy and rapid generation of information related to the target. Furthermore, by generating information related to the target for a product or the like, simple (pseudo) market research can be conducted for the corresponding product or the like using the information related to the target. Furthermore, such research eliminates the need for large-scale user research, thereby reducing financial costs. As described above, the generation device according to one aspect of the present disclosure enables research related to products or services to be conducted quickly and at low cost.

[0008] According to the present disclosure, research on products or services can be conducted quickly and at low cost.

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

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

[0011] FIG. 1 is a diagram showing the device configuration of a pseudo market research system according to this embodiment. The pseudo market research system shown in FIG. 1 is a system that conducts simulated market research for a product or service. Here, "conducting simulated research" may mean conducting research using procedures that differ from those used in general market research (PoC, acceptability research, user research, etc.) and that achieve the same level of effectiveness as general market research. The pseudo market research system conducts simulated market research by selecting targets according to the product or service and generating information related to the targets. Hereinafter, products or services may be referred to as "products, etc."

[0012] 1, the pseudo market research 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 who wants to conduct a pseudo market research. The terminal 10 may be, 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 pseudo market research system may include any number of terminals 10, two or more.

[0014] The server device 30 is a device that stores a generative AI model 31 and enables the provision of information related to a target, such as a product, using the generative AI model 31 (details will be described later). 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, but 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 pseudo market research system may include multiple server devices 30. Although the above describes an example of a large-scale language model, other AI models may also be used. The generative AI model 31 may be provided in the RAG system 20 rather than in a separate server device 30.

[0015] The RAG system 20 includes, as functional components, a reception unit 21, an acquisition unit 22, a generation unit 23, an input unit 24 (control unit), and a storage unit 25. 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 hearing request information for a pseudo market research on products, etc. The reception unit 21 receives the above-mentioned various information from the terminal 10 used by a user who wishes to conduct the pseudo market research. The reception unit 21 may receive hearing request information that includes at least information indicating the products, etc. that are the subject of the pseudo market research. The hearing request information may include "information related to products, etc." and "information related to target setting," which will be described later. Furthermore, the hearing request information may include "information related to the number of targets (personas) to be set" (details will be described later).

[0017] The storage unit 25 stores a knowledge DB in which information about products, etc. is associated with target demographics. The various information defined in the knowledge DB may be input by the user in advance or may be included in the hearing request information received by the reception unit 21. The information about products, etc. defined in the knowledge DB may be, for example, at least one of the name, type, price, quality, purpose, usage scenario, and advertising information about the product or service. The information about the advertisement of the product or service may be information indicating the content of the advertisement (retroactive content), distribution / publication period, medium (television commercial, SNS, magazine advertisement, etc.), information indicating the talent / character used, information indicating the media (specific name of the SNS, etc.), etc. The information about products, etc. defined in the knowledge DB may be information other than the above, such as information about the characteristics of the products, etc. (e.g., sales, market share, popularity, popularity ranking on information sites, etc.). The knowledge DB may also include various information about competing products, etc., of the product, etc., that are the subject of the pseudo-market research.

[0018] The target demographic is associated with information about a product or the like (for example, the type of product or the like) and is information that indicates a typical user image of a product or the like (for example, "30s, female, sales position"). Note that in the knowledge DB, "information about target setting," which will be described later, may be defined as information about multiple target demographics associated with information about a product or the like. In the following description, the target is assumed to be a persona (a fictitious main customer image) of the product or the like.

[0019] The acquisition unit 22 acquires information regarding persona settings (target settings) for a product or the like in response to the acceptance of the hearing request information by the acceptance unit 21. The acquisition unit 22 may identify a target demographic associated with the product or the like indicated in the hearing request information by referring to the knowledge DB in the storage unit 25, and acquire the target demographic as information regarding the persona settings (target settings). Alternatively, when information regarding persona settings is included in the hearing request information, the acquisition unit 22 may acquire information regarding persona settings from the hearing request information. In other words, the acquisition unit 22 may acquire information regarding persona settings directly specified by the user in the hearing request information.

[0020] Information regarding persona setting is information that indicates a typical user profile that uses a product, etc., and may be shown, for example, as "Name: Docomo Hanako, Age: 36, Gender: Female, Residence: Shibuya-ku, Tokyo, Education: Graduated from the Faculty of Economics at Ahamo University, Occupation: Sales position at an advertising agency, Hobbies: Camping."

[0021] The acquisition unit 22 may determine the number of personas based on information regarding the number of targets (personas) to be set, which is included in the hearing request information, and may acquire information regarding persona settings for each persona. For example, if the hearing request information includes information indicating the number of personas to be set (e.g., 10), the acquisition unit 22 may acquire information regarding the corresponding number of persona settings. Furthermore, if the hearing request information includes information indicating the degree of the number of personas to be set (e.g., "more," "fewer"), the acquisition unit 22 may acquire information regarding the corresponding number of persona settings. For example, if the information indicating the degree of the number of personas is "more," the acquisition unit 22 may acquire information regarding approximately 15 persona settings.

[0022] Although the number of personas is preferably as large as possible, there is a limit due to prompt constraints (limits on the number of input tokens). For this reason, the number of personas may be determined based on the number of tokens. For example, if the number of other tokens to be input is not large, the number of personas may be set to, for example, about 15, so that the number of personas is greater than the standard number (for example, 10). Furthermore, if the number of other tokens to be input is normal, the number of personas may be set to, for example, about 10. Furthermore, if the number of other tokens to be input is large, the number of personas may be set to, for example, about 5, so that the number of personas is less than the standard number (for example, 10).

[0023] The generation unit 23 generates a prompt for instructing generation of information related to the persona (target) of a product, etc., based on information related to the persona (target). The generation unit 23 generates a first prompt for instructing generation of information indicating the persona, which is information related to the persona.

[0024] FIG. 2 is a diagram showing an example of a prompt generated by the RAG system 20 (more specifically, the generation unit 23) and an example of an output corresponding to the prompt. More specifically, it is a diagram showing an example of the first prompt and an example of an output from the generative AI model 31 corresponding to the first prompt. Note that FIGS. 2 to 5 show a series of processing flows for a certain example. The prompts shown in FIGS. 2 to 5 may be generated simultaneously or sequentially (e.g., first the prompt shown in FIG. 2, then the prompt shown in FIG. 3, and finally the prompts shown in FIGS. 4 and 5). When the prompts are generated sequentially, subsequent prompts may be generated taking into account the output of the generative AI model 31 for the previous prompt.

[0025] In the example shown in Figure 2, assume that "employees who have issues with communication within their department" is acquired as information for persona setting for a pseudo-market survey on a new communication service (a service that avoids the psychological pressure caused by sudden call sounds by calling out with a voice instead of a call sound, thereby enabling casual conversation between employees). In this case, as shown in Figure 2, the generation unit 23 generates a prompt that specifies "Please think of personas for 10 employees who have issues with communication within their department," as well as "Please include the following items: name, age, gender, responsibilities, and issues they have." In response to this prompt, in the example shown in Figure 2, information representing 10 personas is generated by the generation AI model 31.

[0026] The generation unit 23 generates a second prompt for instructing the generation of information related to the persona, which is information indicating the persona's evaluation of a product or the like. The evaluation information may be multiple-choice information or free-comment information. The multiple-choice information may be, for example, a score indicating satisfaction with the product or the like, information indicating how the person learned about the product or the like (e.g., commercials, social media, web advertisements, referrals, stores, etc.), information indicating the reason for choosing the product or the like (e.g., reasonable price, high name recognition, high quality, friendly sales staff, solid after-sales service), information indicating whether the price is appropriate, information indicating the product's quality, information indicating the level of functionality, ease of use, opportunities for use, motivation for repurchase, etc. The free-comment information may be an impression of the product or the like, why the person purchased / contracted, under what conditions the person would like to purchase / contract, concerns, reasons for refraining from purchasing / contracting, etc. Note that evaluation criteria information for the product or the like may be specified for each persona in the knowledge DB. Such evaluation criteria information may be taken into consideration when generating the second prompt. Furthermore, information indicating evaluations may be generated for each time axis of a persona (needs recognition, product recognition, comparison and consideration, purchase / contract, use, continuation / repurchase). Furthermore, the knowledge DB may specify condition information regarding price ranges for each persona (information indicating a standard amount to be paid for each combination of information about multiple products).

[0027] The generation unit 23 may generate, as the second prompt, a first hearing prompt that asks the persona whether they have a positive or negative opinion of the product, etc., along with the reason (see FIG. 3). The generation unit 23 may generate, as the second prompt, a second hearing prompt that asks a persona who has a negative opinion of the product, etc., about improvements to the product, etc. (see FIG. 4). The generation unit 23 may generate, as the second prompt, a third hearing prompt that asks a persona who has a positive opinion of the product, etc., about their perception of the price of the product, etc. (a reasonable price range).

[0028] FIG. 3 is a diagram showing an example of a prompt generated by the RAG system 20 (specifically, the generation unit 23) and an example of an output corresponding to the prompt. Specifically, it is a diagram showing an example of the first hearing prompt and an example of an output from the generation AI model 31 corresponding to the first hearing prompt. In the example shown in FIG. 3 , the generation unit 23 generates a prompt that specifies the following content: "Please tell us, based on your own persona, how each of the above 10 people feels about a new communication service that uses a voice call instead of a call sound to avoid the psychological pressure caused by sudden call sounds and enable casual conversations between employees." In addition, the prompt also specifies the following content: "For the items, please choose either "I want to use it" or "I don't want to use it" and include the reason." In response to such a prompt, in the example shown in FIG. 3 , the generation AI model 31 generates answers from each of the personas set in response to the first prompt.

[0029] FIG. 4 is a diagram showing an example of a prompt generated by the RAG system 20 (specifically, the generation unit 23) and an example of an output corresponding to the prompt. Specifically, it is a diagram showing an example of the second hearing prompt and an example of an output from the generation AI model 31 corresponding to the second hearing prompt. In the example shown in FIG. 4 , the generation unit 23 generates a prompt that specifies the content, "For the three people who answered that they do not want to use it, under what conditions would you like to use it?" In response to such a prompt, in the example shown in FIG. 4 , answers corresponding to the second hearing prompt are generated by the generation AI model 31 from each of the three personas who answered that they do not want to use it in response to the first hearing prompt. Note that in the example shown in FIG. 4 , a further prompt is specified in response to the answer to the second hearing prompt: "What would be a summary of improvements based on the answers of the three people who answered that they do not want to use it?", and the answers of the three people are summarized.

[0030] 5 is a diagram showing an example of a prompt generated by the RAG system 20 (specifically, the generation unit 23) and an example of an output corresponding to the prompt, specifically, an example of the third hearing prompt and an example of an output from the generation AI model 31 corresponding to the third hearing prompt. In the example shown in FIG. 5, the generation unit 23 generates a prompt that specifies the content, "For the seven people who answered that they would like to use the service, how much would they be willing to pay per month for this service?" In response to such a prompt, in the example shown in FIG. 5, answers corresponding to the third hearing prompt are generated by the generation AI model 31 from each of the seven personas who answered that they would like to use the service in response to the first hearing prompt.

[0031] Returning to Fig. 1 , the input unit 24 controls the generation AI model 31, which generates information related to the persona (target) based on the prompt generated by the generation unit 23. The input unit 24 inputs the various prompts described above to the generation AI model 31. The generation AI model 31 generates and outputs information related to the persona (target) in accordance with the input prompt.

[0032] Next, the process of the pseudo market research will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the process of the pseudo market research executed in the pseudo market research system. Note that the following process flow is an example and is not intended to be limiting.

[0033] 6, information about products and the like is input in advance into a knowledge DB (step S1). In the knowledge DB, information about products and the like is stored in association with target demographics.

[0034] Then, hearing request information for a pseudo market research on products, etc. is received from the user (step S2). In response to the reception of the hearing request information, for example, a knowledge DB is searched (step S3), and information on persona settings associated with products, etc. in the form of pseudo market research is acquired.

[0035] Then, a first prompt is generated to instruct the generation of information indicating a persona for a product, etc. based on information regarding the persona setting, and the first prompt is input into the generation AI model 31 to set persona information for multiple people (step S4).

[0036] Next, as a second prompt, a first hearing prompt is generated to ask the persona whether they have a positive or negative opinion of the product, etc. (whether they would like to use it or not), and this first hearing prompt is input into the generation AI model 31, thereby obtaining an answer as to whether the persona would like to use it or not (step S5).

[0037] Furthermore, as a second prompt, a second hearing prompt is generated to ask a persona who is negative about the product, etc. about areas for improvement of the product, etc., and by inputting this second hearing prompt into the generation AI model 31, an answer regarding areas for improvement of the product, etc. is obtained from the negative persona (step S6).

[0038] In addition, as a second prompt, a third hearing prompt is generated to ask a persona who is positive about the product, etc. about their perception of the price of the product, etc., and by inputting this third hearing prompt into the generation AI model 31, an answer regarding the perception of the price of the product, etc. is obtained from the positive persona (step S7).

[0039] Next, the effects of the RAG system 20 according to this embodiment will be described.

[0040] The RAG system 20 of this embodiment includes a reception unit 21 that receives hearing request information for pseudo market research on products, etc., an acquisition unit 22 that acquires information regarding target settings for products, etc. in response to the reception of the hearing request information, a generation unit 23 that generates a prompt to instruct the generation of information related to targets for products, etc. based on the information regarding the target settings, and an input unit 24 that controls a generation AI model 31 that generates information related to targets based on the prompt.

[0041] In the RAG system 20 according to the present embodiment, information regarding target setting for a product or the like is acquired in response to the pseudo-market research hearing request information. A prompt is generated based on the acquired information, instructing the generation of information related to the target for the product or the like. The target-related information is then generated by the generation AI model 31 based on the prompt. This configuration automates the process from acquiring information related to target setting to generating the prompt and generating information related to the target by the generation AI model 31, thereby enabling easy and rapid generation of target-related information. Furthermore, by generating information related to the target for a product or the like, simplified (pseudo) market research can be conducted for the corresponding product or the like using the target-related information. Furthermore, such research eliminates the need for large-scale user research, thereby reducing financial costs. As described above, the RAG system 20 according to the present embodiment enables research related to products or the like to be conducted quickly and at low cost.

[0042] The target may be a persona of a product, etc. According to this configuration, it is possible to conduct a highly accurate survey of a product, etc., keeping in mind the main customer image of the product, etc.

[0043] The generation unit 23 may generate a first prompt for instructing generation of information indicating a persona, which is information related to the persona. With this configuration, a persona for a product or the like can be appropriately set, and a survey of the product or the like can be performed with high accuracy.

[0044] The generation unit 23 may generate a second prompt for instructing the generation of information related to the persona, which is information indicating the persona's evaluation of the product, etc. With this configuration, the evaluation by the persona can be obtained and a highly accurate survey of the product, etc. can be conducted.

[0045] The generation unit 23 may generate, as the second prompt, a first hearing prompt that asks the persona whether they have a positive or negative opinion of the product, etc., along with the reasons for their opinion. With this configuration, it is possible to appropriately investigate the degree to which the product, etc., is acceptable to the persona.

[0046] The generation unit 23 may generate, as the second prompt, a second hearing prompt that asks a persona who is negative about a product, etc. about improvements to the product, etc. According to this configuration, it is possible to obtain improvements from a persona who is negative about a product, etc., and acquire information that can be used for future product development, etc.

[0047] The generation unit 23 may generate, as the second prompt, a third hearing prompt that asks a persona who has a positive attitude toward a product, etc., about their perception of the price of the product, etc. With this configuration, it is possible to investigate the reasonable perception of the price of the product, etc.

[0048] The RAG system 20 further includes a memory unit 25 that stores a knowledge database in which information about products and the like is associated with target demographics, the receiving unit 21 receives hearing request information including at least information indicating products and the like that are the subject of the pseudo market research, and the acquiring unit 22 may refer to the knowledge database to identify the target demographic associated with the information indicating the products and the like indicated in the hearing request information, and acquire the target demographic as information regarding target setting. With this configuration, information regarding target setting can be acquired easily and quickly.

[0049] The storage unit 25 may store a knowledge DB that specifies at least one of the name, type, price, quality, purpose, usage scenario, and advertising information of the product, etc. With this configuration, by appropriately storing the information about the product, etc. and using the associated target demographic, it is possible to appropriately acquire information about target setting from the information about the product, etc.

[0050] The generating device and generating method of the present disclosure have the following configuration.

[0051] [1] A generation device comprising: a reception unit that receives hearing request information for a pseudo-market research on a product or service; an acquisition unit that acquires information related to target setting for the product or service in response to the reception of the hearing request information; a generation unit that generates a prompt to instruct generation of information related to a target of the product or service based on the information related to the target setting; and a control unit that controls a generation AI model that generates information related to the target based on the prompt.

[0052] [2] The generation device according to [1], wherein the target is a persona of the product or service.

[0053] [3] The generation device according to [2], wherein the generation unit generates a first prompt for instructing generation of information indicating the persona, which is information related to the persona.

[0054] [4] The generation device according to [3], wherein the generation unit generates a second prompt for instructing the generation of information relating to the persona, the information indicating the persona's evaluation of the product or service.

[0055] [5] The generation device according to [4], wherein the generation unit generates, as the second prompt, a first hearing prompt that asks the persona whether they have a positive or negative opinion of the product or service, along with the reason.

[0056] [6] The generation device according to [5], wherein the generation unit generates, as the second prompt, a second hearing prompt that asks the persona who is negative about the product or service about areas for improvement of the product or service.

[0057] [7] The generation device according to [5] or [6], wherein the generation unit generates, as the second prompt, a third hearing prompt that asks the persona who is positive about the product or service about their price perception of the product or service.

[0058] [8] A generation device according to any one of [1] to [7], further comprising a memory unit that stores a knowledge DB in which information relating to products or services is associated with a target demographic, wherein the reception unit receives the hearing request information including at least information indicating the product or service that is the subject of the pseudo-market research, and the acquisition unit refers to the knowledge DB to identify the target demographic associated with the information indicating the product or service indicated in the hearing request information, and acquires the target demographic as information relating to the target setting.

[0059] [9] The generating device according to any one of [1] to [8], wherein the storage unit stores the knowledge DB in which at least one of the following information about the product or service is specified as information about the product or service: name, type, price, quality, purpose, usage scenario, and advertising.

[0060]

[10] A method for generating a prompt performed by a generating device, the method comprising: receiving hearing request information for a pseudo-market research on a product or service; acquiring information related to target setting for the product or service in response to receiving the hearing request information; generating a prompt for instructing generation of information related to a target of the product or service based on the information related to the target setting; and controlling a generating AI model that generates information related to the target based on the prompt.

[0061] 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.

[0062] 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.

[0063] For example, the RAG system 20 constituting the pseudo market research 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. FIG. 7 is a diagram illustrating an example of the hardware configuration of the RAG system 20 according to this embodiment. The RAG system 20 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 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.

[0064] 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.

[0065] 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.

[0066] 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, acquisition unit 22, generation unit 23, input unit 24, etc. may be realized by the processor 1001.

[0067] 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, acquisition unit 22, generation unit 23, and input unit 24 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.

[0068] 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.

[0069] 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.

[0070] 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 a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned reception unit 21, input unit 24, etc. may be realized by the communication device 1004.

[0071] 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).

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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).

[0078] 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).

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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."

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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."

[0095] 20...RAG system (generation device), 21...reception unit, 22...acquisition unit, 23...generation unit, 24...input unit (control unit), 25...storage unit, 31...generated AI model.

Claims

1. A generation device comprising: a reception unit that receives hearing request information for pseudo-market research on a product or service; an acquisition unit that acquires information related to target settings for the product or service in response to the reception of the hearing request information; a generation unit that generates a prompt to instruct the generation of information related to the target of the product or service based on the information related to the target setting; and a control unit that controls a generation AI model that generates information related to the target based on the prompt.

2. The generation device according to claim 1, wherein the target is a persona of the product or service.

3. The generating device according to claim 2, wherein the generating unit generates a first prompt for instructing the generation of information indicating the persona, which is information related to the persona.

4. The generation device according to claim 3, wherein the generation unit generates a second prompt for instructing the generation of information relating to the persona, the information indicating the persona's evaluation of the product or service.

5. The generation device according to claim 4, wherein the generation unit generates, as the second prompt, a first hearing prompt that asks the persona whether they have a positive or negative opinion of the product or service, along with their reasons.

6. The generation device according to claim 5, wherein the generation unit generates, as the second prompt, a second hearing prompt that asks the persona who is negative about the product or service about areas for improvement of the product or service.

7. The generation device according to claim 5, wherein the generation unit generates, as the second prompt, a third hearing prompt that asks the persona who is positive about the product or service about their price perception of the product or service.

8. A generation device as described in claim 1, further comprising a memory unit that stores a knowledge DB in which information regarding products or services is associated with target demographics, wherein the reception unit receives the hearing request information including at least information indicating the products or services that are the subject of the pseudo-market research, and the acquisition unit identifies the target demographic associated with the information indicating the products or services indicated in the hearing request information by referring to the knowledge DB, and acquires the target demographic as information regarding the target setting.

9. The generation device according to claim 8, wherein the memory unit stores the knowledge DB in which at least one of the following information regarding the product or service is specified: name, type, price, quality, purpose, usage scenario, and advertising of the product or service.

10. A method for generating prompts performed by a generating device, comprising: accepting hearing request information for pseudo-market research on a product or service; acquiring information regarding target setting for the product or service in response to accepting the hearing request information; generating a prompt for instructing the generation of information related to the target of the product or service based on the information regarding the target setting; and controlling a generating AI model that generates information related to the target based on the prompt.

Images